Wiki Log

[2026-06-27] init | wiki initialized with SDLC agent-skill ontology

  • Created namespaces: framework, capability, sdlc-stage, artifact, pattern
  • Added CONVENTIONS.md (Tolaria-style frontmatter schema, relationship vocabulary, synthesis model)
  • Sources: none yet (initialize-only)

[2026-06-27] ingest | GSD (Git. Ship. Done.) framework

  • Raw: raw/gsd/2026-06-27-gsd-core-framework.md (docs.opengsd.net + github.com/open-gsd/gsd-core)
  • Created framework: gsd
  • Created capabilities (commands): gsd-discuss-phase, gsd-plan-phase, gsd-execute-phase, gsd-verify-work, gsd-ship
  • Created capabilities (sub-agents): gsd-phase-researcher, gsd-planner, gsd-plan-checker, gsd-executor, gsd-verifier
  • Created sdlc-stage projections: stage-discuss, stage-plan, stage-execute, stage-verify, stage-ship
  • Created artifacts: artifact-context-md, artifact-plan-md, artifact-research-md, artifact-uat-md, artifact-atomic-commit, artifact-pull-request
  • Created patterns: pattern-spec-driven-development, pattern-fresh-context-subagents, pattern-wave-parallelism, pattern-plan-verification-loop
  • Conflict recorded: docs homepage “Research→…” vs README/detailed pages “Discuss→…” (canonical: Discuss) — noted in gsd.md and stage-discuss.md
  • Scope note: documented the 5 workflow commands + 5 core sub-agents; remaining 60+ commands and 29 sub-agents catalogued in gsd.md for future ingest

[2026-06-27] edit | bullet-list formatting for capability enumerations

  • CONVENTIONS.md: added “Formatting conventions” — enumerate commands/sub-agents as one-per-line bullets ([[link]] — role note), grouped under sub-headings for long rosters
  • gsd.md: converted Commands, namespaces, Sub-agents (documented + not-yet-documented, now grouped by function), Artifacts, Patterns from inline ·/prose runs to bullet lists
  • Pattern pages: expanded “Applied by” single-bullet runs into per-capability bullets
  • Artifact pages: expanded “Produced by” runs into per-capability bullets

[2026-06-28] ingest | Matt Pocock — Skills for Real Engineers (mattpocock/skills)

  • Raw: raw/matt-pocock-skills/2026-06-28-skills-for-real-engineers.md (github.com/mattpocock/skills + README)
  • Created framework: matt-pocock-skills
  • Created capabilities (skills): mp-grill-me, mp-grilling, mp-grill-with-docs, mp-to-prd, mp-to-issues, mp-domain-modeling, mp-codebase-design, mp-tdd, mp-prototype, mp-diagnosing-bugs, mp-improve-codebase-architecture, mp-handoff
  • Created artifacts: artifact-prd, artifact-issue, artifact-adr, artifact-domain-model, artifact-handoff-doc
  • Created patterns: pattern-grilling, pattern-test-driven-development, pattern-vertical-slice, pattern-systematic-debugging, pattern-session-handoff, pattern-deep-modules, pattern-throwaway-prototype
  • Cross-framework synthesis (the second-framework payoff):
    • equivalent_to cluster: mp-diagnosing-bugs ↔ gsd-debugger (created gsd-debugger page to anchor it)
    • shared patterns now applied by BOTH frameworks: pattern-grilling (gsd-discuss-phase + mp-grill*), pattern-vertical-slice (gsd-plan-phase —mvp + mp-to-issues), pattern-test-driven-development (gsd-plan-phase —tdd + mp-tdd), pattern-systematic-debugging (gsd-debugger + mp-diagnosing-bugs)
  • Updated (cascade): gsd.md (added gsd-debugger + cross-framework See Also), gsd-discuss-phase (applies pattern-grilling), gsd-plan-phase (applies pattern-vertical-slice + pattern-test-driven-development), artifact-context-md (CONTEXT.md naming-conflict annotation), stage-discuss, stage-plan, stage-execute, stage-verify (both-framework backlinks + equivalents)
  • Conflict recorded: CONTEXT.md filename means different artifacts in GSD (locked decisions) vs MP (domain glossary) — annotated in both artifact-context-md and artifact-domain-model
  • Scope note: documented 12 core SDLC skills as capability pages; 9 meta/niche skills (ask-matt, triage, setup-matt-pocock-skills, setup-pre-commit, git-guardrails-claude-code, migrate-to-shoehorn, writing-great-skills, teach, scaffold-exercises) catalogued in matt-pocock-skills.md

[2026-07-01] edit | CONVENTIONS: stage re-derivation process + first re-derivation

  • CONVENTIONS.md: added “Stage re-derivation (keep stages framework-neutral)” section (generalize/split/merge/add/retire rules, ≥2-framework thresholds, minimize, optional aka: field, safe rename-cascade procedure); added re-derivation as ingest step 5; sharpened sdlc-stage node-type definition; reframed candidate arcs as reference points not canonical names
  • First re-derivation (2 frameworks in evidence) — renamed GSD-branded stages to framework-neutral SDLC vocabulary:
    • stage-discuss → stage-align (aka: GSD Discuss, MP grilling)
    • stage-execute → stage-implement (aka: GSD Execute, MP build/TDD/prototype)
    • stage-verify → stage-validate (aka: GSD Verify, MP architecture audit)
    • stage-ship → stage-release (aka: GSD Ship; single-framework evidence, retained)
    • stage-plan → kept (already generic; aka: GSD Plan, MP PRD/issues/design)
  • Cascade: updated all implements: edges, prose, See Also, and index paths across ~25 pages; added aka: to all 5 stage pages; bumped stage updated: to 2026-07-01
  • Note: historical log entries above retain the old stage names (they record what the stages were called at the time)

[2026-07-01] edit | capture split candidates on stage-plan

  • stage-plan.md: added ”## Split candidates” section tracking stage-specify (spec/PRD authoring) and stage-design (deep-module design); each with distinction, evidence tally (1 strong vote each — MP splits, GSD folds in), and decisive trigger (spec-first framework e.g. SpecKit/OpenSpec → stage-specify; third design-distinct framework → stage-design)
  • CONVENTIONS.md: added “Park pending splits on the stage page” rule — split candidates live under a ## Split candidates heading as the per-ingest review queue
  • No renames/new stages yet — evidence still below the ≥2-framework threshold

[2026-07-04] ingest | Addy Osmani — Agent Skills (addyosmani/agent-skills)

  • Raw: raw/addy-agent-skills/2026-07-04-agent-skills.md (github.com/addyosmani/agent-skills — README + docs/comparison.md)
  • Created framework: addy-agent-skills (third framework; broadest yet — 24 skills + 4 personas + 8 commands over a six-phase lifecycle Define→Plan→Build→Verify→Review→Ship)
  • Created capabilities (skills, 24): addy-using-agent-skills, addy-interview-me, addy-idea-refine, addy-spec-driven-development, addy-planning, addy-incremental-implementation, addy-tdd, addy-context-engineering, addy-source-driven-development, addy-doubt-driven-development, addy-frontend-ui, addy-api-design, addy-browser-testing, addy-debugging, addy-code-review, addy-code-simplification, addy-security, addy-performance, addy-git-workflow, addy-ci-cd, addy-deprecation, addy-documentation, addy-observability, addy-shipping
  • Created capabilities (sub-agents / personas, 4): addy-code-reviewer, addy-test-engineer, addy-security-auditor, addy-web-performance-auditor
  • Created artifacts (6): artifact-spec-md, artifact-review-report, artifact-security-audit, artifact-perf-audit, artifact-changelog, artifact-launch-checklist
  • Created patterns (10): pattern-anti-rationalization, pattern-adversarial-review, pattern-source-grounding, pattern-context-engineering, pattern-contract-first, pattern-measure-first, pattern-trunk-based-development, pattern-shift-left, pattern-feature-flags, pattern-parallel-persona-review
  • Cross-framework synthesis (three-framework payoff):
    • equivalent_to clusters extended to 3 frameworks: grilling (addy-interview-me ↔ mp-grill-me ↔ gsd-discuss-phase), TDD (addy-tdd ↔ mp-tdd ↔ gsd --tdd), debugging (addy-debugging ↔ mp-diagnosing-bugs ↔ gsd-debugger), vertical-slice plan (addy-planning ↔ mp-to-issues ↔ gsd-plan-phase)
    • new 2-framework clusters: addy-spec-driven-development ↔ mp-to-prd (spec authoring), addy-api-design ↔ mp-codebase-design (interface/deep-module design), addy-incremental-implementation ↔ gsd-execute-phase (execute loop), addy-shipping ↔ gsd-ship (ship orchestration)
  • STAGE RE-DERIVATION (third framework in evidence):
    • PROMOTED stage-specify (author the spec/PRD, distinct from task decomposition): Addy’s spec-driven-development became the 2nd framework (with MP’s to-prd) to treat spec authoring as its own step → cleared the ≥2-framework bar. Split out of stage-plan; moved mp-to-prd’s implements stage-plan → stage-specify; wired addy-spec-driven-development. aka: { matt-pocock-skills: to-prd, addy-agent-skills: spec-driven-development }
    • PARKED stage-review (quality gate: is it good?) as the strongest split candidate on stage-validate: Addy cleanly separates Verify (does it work) from Review (is it good), but is the only framework treating them as distinct phases (MP contributes only review-side, GSD only functional-side) — below the ≥2 bar. Decisive trigger noted: a second framework separating quality review as its own phase (likely Superpowers).
    • stage-design candidate refreshed: Addy adds a dedicated design skill (addy-api-design) but folds it into Build → design is now a dedicated capability in 2 frameworks but a distinct phase in only 1 (MP); still parked.
    • stage-release parked a watch-item (operate/maintain) for Addy’s observability + deprecation folded into Ship.
  • Cascade (updated + dates refreshed to 2026-07-04): gsd.md + matt-pocock-skills.md (added addy-agent-skills See Also cross-links); stage-align, stage-plan, stage-implement, stage-validate, stage-release (Addy backlinks, aka, equivalents, split-candidate updates); mp-to-prd (stage move + equivalent_to); 10 counterpart capabilities (reverse equivalent_to + See Also); artifact-atomic-commit, artifact-plan-md, artifact-adr (Addy Produced-by backlinks); pattern-grilling, pattern-test-driven-development, pattern-vertical-slice, pattern-systematic-debugging, pattern-fresh-context-subagents, pattern-spec-driven-development, pattern-deep-modules (Addy Applied-by backlinks)
  • Scope: documented all 24 skills + 4 personas as capability pages (full coverage). The 8 slash commands are thin skill-invokers, catalogued as a phase↔command↔skill↔stage table on the framework page rather than given separate pages; 7 reference checklists + hooks catalogued on the framework page.
  • Noted for a future ingest: Superpowers (obra) — referenced in Addy’s docs/comparison.md; likely trigger for promoting stage-review.

[2026-07-04] ingest | OpenSpec — spec-driven development (Fission-AI/OpenSpec)

  • Raw: raw/openspec/2026-07-04-openspec-framework.md (github.com/Fission-AI/OpenSpec — README + docs/concepts.md + docs/commands.md)
  • Created framework: openspec (fourth framework; the wiki’s purest spec-driven system — fluid/iterative/easy/brownfield-first)
  • Created capabilities (commands, 6 — core workflow paged): openspec-explore, openspec-propose, openspec-apply, openspec-verify, openspec-sync, openspec-archive
  • Created artifacts (3): artifact-spec-delta (signature — ADDED/MODIFIED/REMOVED requirement deltas + Given/When/Then scenarios), artifact-proposal-md, artifact-design-md
  • Created patterns (1): pattern-living-specification (permanent spec-as-source-of-truth maintained via merged deltas — OpenSpec’s distinctive contribution)
  • Cross-framework synthesis (four-framework payoff):
    • equivalent_to clusters extended: specify (openspec-propose ↔ addy-spec-driven-development ↔ mp-to-prd), execute (openspec-apply ↔ gsd-execute-phase ↔ addy-incremental-implementation), validate (openspec-verify ↔ gsd-verify-work / gsd-verifier), finalize/ship (openspec-archive ↔ gsd-ship ↔ addy-shipping), align/explore (openspec-explore ↔ gsd-discuss-phase / addy-idea-refine)
    • added reciprocal equivalent_to edges on all 10 counterpart capability pages + a reciprocal See Also bullet on each
  • STAGE RE-DERIVATION (fourth framework in evidence — no renames/splits/merges/adds this ingest):
    • stage-specify reinforced to three frameworks: openspec-propose centers on authoring the spec (as spec deltas) before code, joining MP + Addy. Stage now beyond doubt.
    • stage-align now four-framework: added openspec-explore. Noted a second flavor — codebase-investigation (OpenSpec/Addy idea-refine) alongside human-interrogation (grilling cluster). One framework only for explicit codebase-explore → no split.
    • stage-plan: OpenSpec folds plan into propose (design.md + tasks.md); its implements edge points at stage-specify. stage-design split candidate refreshed — OpenSpec adds a dedicated design.md artifact as a discrete step in proposal→specs→design→tasks, so design is now a dedicated capability/artifact in 3 frameworks but a distinct phase in only 1 (MP); still parked.
    • stage-validate: openspec-verify added on the functional/spec-conformance side only (OpenSpec ships no quality review) → does NOT advance the parked stage-review split (still Addy-only as distinct phases).
    • stage-release: added openspec-sync + openspec-archive. Recorded two flavors of release — ship-to-prod (GSD/Addy) vs spec-maintenance (OpenSpec: merge delta into living spec, no deploy/CI/observability). Addy’s ops capabilities still unique.
  • Cascade (updated + dates 2026-07-04): pattern-spec-driven-development (OpenSpec applied-by + living-spec note); artifact-plan-md (OpenSpec tasks.md producer); artifact-adr (design-md See Also); all 6 stage pages (backlinks, aka, equivalents, split-candidate refresh); 10 counterpart capabilities (reciprocal equivalent_to + See Also); framework See Also cross-links on gsd, addy-agent-skills, matt-pocock-skills
  • Scope: paged the 6 core workflow commands (explore/propose/apply/verify/sync/archive). Expanded-profile commands (new, continue, ff, bulk-archive, onboard) are thin artifact-generation/batch/tutorial wrappers → catalogued as a table on the framework page (per full-coverage-but-catalogue-thin-wrappers convention). Terminal CLI (init/update/config/validate/list/show/diff/archive) catalogued as a tooling table, not lifecycle capabilities. Legacy /openspec: commands noted as deprecated.

[2026-07-04] ingest | Spec Kit — spec-driven development (github/spec-kit)

  • Raw: raw/speckit/2026-07-04-speckit-framework.md (github.com/github/spec-kit — README + github.github.com/spec-kit + spec-driven.md)
  • Created framework: speckit (fifth framework; GitHub’s reference implementation of SDD — Spec→Plan→Tasks→Implement; largest community, 106K★)
  • Created capabilities (commands, 10 — full per-command coverage per user preference): speckit-constitution, speckit-specify, speckit-clarify, speckit-plan, speckit-tasks, speckit-analyze, speckit-implement, speckit-checklist, speckit-converge, speckit-taskstoissues
  • Created artifacts (2): artifact-constitution (signature — immutable project-wide governing principles in numbered articles, .specify/memory/constitution.md), artifact-checklist (“unit tests for your English” — requirements quality gate). Reused artifact-spec-md (spec.md), artifact-design-md (plan.md/data-model.md/contracts), artifact-research-md (research.md), artifact-plan-md (tasks.md), artifact-issue (taskstoissues).
  • Created patterns (1): pattern-project-constitution (externalize immutable principles into one governing doc + gate every artifact against it — SpecKit’s distinctive contribution)
  • Cross-framework synthesis (five-framework payoff):
    • equivalent_to clusters extended: specify (speckit-specify → mp-to-prd/addy-spec-driven/openspec-propose; now FOUR-framework), execute (speckit-implement → gsd-execute/openspec-apply/addy-incremental; now FIVE-framework), grilling/align (speckit-clarify → gsd-discuss/mp-grill-me/addy-interview-me), decompose (speckit-tasks → mp-to-issues/addy-planning), plan (speckit-plan → gsd-plan-phase), plan-verification (speckit-analyze ↔ gsd-plan-checker; now TWO-framework), validate (speckit-converge ↔ openspec-verify), issue-export (speckit-taskstoissues ↔ mp-to-issues)
    • added reciprocal equivalent_to edges + See Also bullets on all counterpart capability pages
  • Pattern promotions from single- to two-framework: pattern-contract-first (Addy + SpecKit contracts/), pattern-plan-verification-loop (GSD + SpecKit). pattern-spec-driven-development, pattern-test-driven-development, pattern-grilling extended with SpecKit.
  • STAGE RE-DERIVATION (fifth framework in evidence — no renames/merges this ingest):
    • stage-specify reinforced to four frameworks: speckit-specify is the literal /specify step. SpecKit adds a distinctive spec-quality gate (speckit-checklist → artifact-checklist).
    • stage-align now five-framework: added speckit-clarify (grilling, spec-first ordering variant). PARKED stage-govern split candidate: speckit-constitution establishes project-wide governing principles gated across artifacts — a genuine governance activity, but SpecKit is the only framework with it (others embed principles inside skills; OpenSpec has none). Below the ≥2 bar. Decisive trigger: a second framework with a set-the-project-principles capability.
    • stage-plan: added speckit-plan + speckit-tasks + speckit-analyze + speckit-taskstoissues. Plan-verification cluster promoted to two-framework (gsd-plan-checker ↔ speckit-analyze). stage-design candidate refreshed — SpecKit emits dedicated design artifacts (data-model.md + contracts/) within plan → design now a dedicated capability/artifact in 4 frameworks but a distinct phase in only 1 (MP); still parked.
    • stage-implement: added speckit-implement (strictest test-first — TDD mandated by the constitution).
    • stage-validate: added speckit-converge on the functional/spec-conformance side (action-oriented — re-plans the gap into new tasks rather than only reporting). SpecKit ships no quality-gate review → does NOT advance the parked stage-review split (still Addy-only as distinct phases).
    • stage-release: SpecKit adds NO backlink — it stops at the validate loop; no deploy/PR/launch/observability command. Noted on the stage page.
  • Cascade (updated + dates 2026-07-04): patterns spec-driven-development, test-driven-development, grilling, contract-first, plan-verification-loop; artifacts plan-md, spec-md, research-md, design-md, issue (SpecKit producers); all 6 stage pages (backlinks, aka, equivalents, split-candidate refresh); counterpart capabilities mp-to-prd, addy-spec-driven-development, openspec-propose, gsd-execute-phase, openspec-apply, addy-incremental-implementation, gsd-discuss-phase, mp-grill-me, addy-interview-me, gsd-plan-phase, mp-to-issues, addy-planning, gsd-plan-checker, openspec-verify (reciprocal equivalent_to + See Also); index.md
  • Scope: paged all 10 slash commands (5 core + 5 optional) for full per-command coverage. The Specify CLI (init/self/integration/extension/preset/bundle) catalogued as a tooling table on the framework page, not lifecycle capabilities. Noted source discrepancy on speckit-checklist (current docs = requirements-quality; older spec-driven.md = code-vs-spec) — followed current docs.
  • Housekeeping: removed stray </content> tags left in pattern-contract-first.md and artifact-spec-md.md while editing them.

[2026-07-04] ingest | BMAD-METHOD v6 (bmad-code-org/BMAD-METHOD)

  • Raw: raw/bmad/2026-07-04-bmad-method-framework.md (docs.bmad-method.org + github.com/bmad-code-org/BMAD-METHOD @ v6.10.0 + module repos + DeepWiki)
  • Created framework: bmad (sixth framework; the most role-oriented & lifecycle-complete — six named personas over Analysis→Planning→Solutioning→Implementation, scale-adaptive, context-engineered)
  • Created capabilities — sub-agent personas (6): bmad-analyst (Mary), bmad-tech-writer (Paige), bmad-pm (John), bmad-ux-designer (Sally), bmad-architect (Winston), bmad-dev (Amelia)
  • Created capabilities — workflow skills (19): bmad-brainstorming, bmad-forge-idea, bmad-research, bmad-product-brief, bmad-prfaq, bmad-document-project (align); bmad-prd, bmad-ux, bmad-spec (specify); bmad-architecture, bmad-create-epics-and-stories, bmad-check-implementation-readiness, bmad-sprint-planning, bmad-create-story (plan); bmad-dev-story, bmad-quick-dev (implement); bmad-code-review (validate); bmad-correct-course (plan/change); bmad-retrospective (release)
  • Created artifacts (3): artifact-story (signature — context-rich story-[slug].md), artifact-architecture (ARCHITECTURE-SPINE.md, invariants-only), artifact-product-brief (brief.md + PRFAQ/forged-idea variants). Reused artifact-prd (prd.md), artifact-spec-md (SPEC kernel), artifact-design-md (UX DESIGN.md+EXPERIENCE.md), artifact-research-md, artifact-atomic-commit, artifact-review-report.
  • Created patterns (2): pattern-persona-agents (signature — named expert persona per role + Party Mode), pattern-scale-adaptive-planning (signature — size ceremony to work; Levels 0-4 / Quick-Method-Enterprise tracks; JIT design)
  • Cross-framework synthesis (six-framework payoff):
    • specify cluster → FIVE-framework: bmad-prd ↔ mp-to-prd / addy-spec-driven-development / openspec-propose / speckit-specify (reciprocal equivalent_to + See Also on all four)
    • execute cluster → SIX-framework: bmad-dev-story ↔ gsd-execute-phase / openspec-apply / addy-incremental-implementation / speckit-implement
    • decompose cluster: bmad-create-epics-and-stories ↔ mp-to-issues / addy-planning / speckit-tasks
    • PLAN-VERIFICATION promoted to THREE-framework: bmad-check-implementation-readiness ↔ gsd-plan-checker / speckit-analyze (pattern-plan-verification-loop)
    • code-review cluster: bmad-code-review ↔ addy-code-review (equivalent_to; was []); ideation: bmad-brainstorming ↔ addy-idea-refine; codebase-investigation: bmad-document-project ↔ openspec-explore; correct-course ↔ speckit-converge (See Also)
  • Pattern promotions from single- to multi-framework: pattern-adversarial-review (Addy + BMAD), pattern-parallel-persona-review (Addy + BMAD), pattern-context-engineering (Addy + BMAD), pattern-fresh-context-subagents (+BMAD → GSD+Addy+BMAD); extended: pattern-spec-driven-development, pattern-grilling (5fw), pattern-test-driven-development (5fw), pattern-vertical-slice (4fw)
  • STAGE RE-DERIVATION (sixth framework — no renames/splits/merges/adds; all candidates refreshed):
    • stage-align → six-framework. BMAD is the first to populate all three align flavors at once (grilling via facilitator personas, codebase-investigation via document-project, ideation via brainstorming) + adds an adversarial pressure-testing sub-flavor (forge-idea, prfaq). stage-govern NOT advanced — BMAD’s project-context.md/customize.toml are dev rules, not an immutable charter; still SpecKit-only.
    • stage-specify → five-framework (bmad-prd); BMAD reinforces structurally by giving specify its own Planning phase between Analysis and Solutioning.
    • stage-plan: added bmad-architect/architecture/create-epics-and-stories/check-implementation-readiness/sprint-planning/create-story/correct-course. stage-design candidate refreshed — BMAD has a dedicated architecture capability + a named Solutioning phase, but Solutioning bundles design+decomposition, so it does NOT isolate design from decomposition as a distinct phase; design now a dedicated capability in FIVE frameworks, distinct phase in only one (MP). Still parked.
    • stage-implement → six-framework execute cluster (bmad-dev-story + bmad-quick-dev); create-story noted as the plan→implement bridge.
    • stage-validate: added bmad-code-review (adversarial). stage-review split NOT advanced — BMAD ships a genuine quality-gate (code-review + optional TEA module) cleanly separated from functional testing, but inside the Implementation loop, not as a distinct phase; review now a dedicated capability in ~3 frameworks but a distinct phase in only one (Addy).
    • stage-release: added bmad-retrospective — a THIRD flavor of release (“learning close-out”), alongside ship-to-prod (GSD/Addy) and spec-maintenance (OpenSpec). BMAD core, like SpecKit, ships no deploy step — but unlike SpecKit it DOES add a close-out backlink. Cluster left as non-equivalent (terminal acts differ too much).
  • Scope: paged the 6 BMM personas + 19 lifecycle workflow skills (full per-capability coverage per user preference). Cross-phase utility skills (party-mode, advanced-elicitation, review layers, checkpoint-preview, sprint-status, generate-project-context, qa-generate-e2e-tests, dev-auto, shard-doc, help/customize/index-docs) catalogued as a table on the framework page. Optional modules (BMB, CIS, TEA, GDS, WDS, BMad Loop) catalogued as a table, not paged (like GSD’s Pi/Browser and OpenSpec’s expanded profile) — TEA’s Murat noted as BMAD’s quality-reviewer, clustering with stage-validate.
  • Conflict recorded (version drift): v4/v5 shipped separate Scrum Master (Bob) / Product Owner (Sarah) / BMad Master / BMad Orchestrator agents; v6 folds SM+QA into the Developer (Amelia), epic breakdown into the PM (John), orchestration into the party-mode skill. Some secondary sources (DeepWiki) still list a sm/”Bob” agent; v6 docs canonical at “six named agents.” Annotated on bmad.md.
  • Version note: v6 migrated to a Claude-Code Agent-Skills architecture (SKILL.md) and replaced the classic numeric Levels 0-4 with stakes-calibrated tracks (Quick Flow / BMad Method / Enterprise); both representations documented on pattern-scale-adaptive-planning.
  • Cascade (updated + dates 2026-07-04): patterns spec-driven-development, plan-verification-loop, grilling, test-driven-development, vertical-slice, adversarial-review, parallel-persona-review, context-engineering, fresh-context-subagents; artifacts prd, spec-md, design-md, research-md, atomic-commit, review-report, issue, proposal-md; counterpart capabilities mp-to-prd, addy-spec-driven-development, openspec-propose, speckit-specify, gsd-execute-phase, openspec-apply, addy-incremental-implementation, speckit-implement, mp-to-issues, addy-planning, speckit-tasks, gsd-plan-checker, speckit-analyze, addy-code-review, addy-idea-refine, openspec-explore, speckit-converge (reciprocal equivalent_to + See Also); framework See Also on gsd, openspec, speckit, matt-pocock-skills, addy-agent-skills; all 6 stage pages; index.md
  • Housekeeping: removed stray </content> tags found in pattern-parallel-persona-review.md, pattern-adversarial-review.md, pattern-context-engineering.md, artifact-review-report.md, and framework/addy-agent-skills.md while cascading.

[2026-07-04] ingest | Compound Engineering (Every — EveryInc/compound-engineering-plugin)

  • Raw: raw/compound-engineering/2026-07-04-compound-engineering-every.md (every.to essay, Shipper & Klaassen, 2025-12-11) + 2026-07-04-compound-engineering-plugin.md (GitHub README + docs/skills + repo tree via gh api)
  • Created framework: compound-engineering (seventh framework; the only self-feeding loop — Brainstorm→Plan→Work→Simplify→Review→Compound + autonomous /lfg; 80/20 planning-review split; knowledge compounding to docs/solutions/)
  • NEW CANONICAL STAGE — stage-learn (the headline). User asked whether the “compound” step is a new SDLC stage. Answer per the re-derivation rules: yes. Learning-capture was already latent as the “learning close-out” flavor of stage-release (bmad-retrospective, single-framework, parked). CE’s ce-compound (+ ce-compound-refresh, ce-explain) gives it a second framework, clearing the ≥2-framework bar — same mechanism that promoted stage-specify out of stage-plan.
    • STAGE SPLIT (stage-release → stage-learn): moved bmad-retrospective implements: stage-release → stage-learn (+ applies pattern-knowledge-compounding); rewrote bmad-retrospective body + See Also. Created sdlc-stage/stage-learn.md (definition, why-distinct-not-a-flavor, two flavors: agent-grounding corpus vs team retrospective, spec-flavored cousin = openspec-sync). Edited stage-release: aka (dropped bmad, added compound-engineering), “three flavors”→“two flavors” note + promotion note, added CE ship-to-prod backlinks (ce-commit/commit-push-pr/resolve-pr-feedback/promote/product-pulse), rewrote cross-framework equivalents + See Also. This is the wiki’s 7th canonical stage and arguably the first genuinely new stage the agent era adds (machine-consumable learnings, not a rename of a classic phase).
  • Created capabilities (26 lifecycle skills, full per-capability coverage): align — ce-strategy, ce-ideate, ce-pov, ce-brainstorm, ce-sweep; plan — ce-plan, ce-doc-review; implement — ce-work, ce-worktree, ce-debug, ce-polish; validate — ce-simplify-code, ce-code-review, ce-optimize, ce-test-browser, ce-test-xcode, ce-dogfood; release — ce-commit, ce-commit-push-pr, ce-resolve-pr-feedback, ce-promote, ce-product-pulse; learn — ce-compound, ce-compound-refresh, ce-explain; orchestrator — lfg (subtype command; implements list plan..release).
  • Created artifacts (4): artifact-solution-doc (signature — machine-consumable docs/solutions/ learning), artifact-brainstorm-md (docs/brainstorms/ requirements-only), artifact-strategy-md (STRATEGY.md anchor), artifact-explainer (ce-explain). Reused artifact-plan-md, artifact-review-report, artifact-atomic-commit, artifact-pull-request.
  • Created patterns (3): pattern-knowledge-compounding (signature — the stage-learn technique; shared CE + BMAD), pattern-autonomous-loop (/lfg + ce-dogfood), pattern-worktree-isolation (ce-worktree/ce-work; filesystem counterpart to fresh-context subagents).
  • Cross-framework synthesis (seven-framework payoff):
    • execute cluster → SEVEN-framework: ce-work ↔ gsd-execute-phase / openspec-apply / addy-incremental-implementation / speckit-implement / bmad-dev-story
    • grilling/align: ce-brainstorm ↔ addy-interview-me / mp-grill-me / gsd-discuss-phase / speckit-clarify; ideation: ce-ideate ↔ bmad-brainstorming / addy-idea-refine
    • plan: ce-plan ↔ gsd-plan-phase / addy-planning / speckit-plan / speckit-tasks; plan-verification → FOUR-framework: ce-doc-review ↔ gsd-plan-checker / speckit-analyze / bmad-check-implementation-readiness
    • debugging: ce-debug ↔ gsd-debugger / mp-diagnosing-bugs / addy-debugging; simplify (clean 1:1): ce-simplify-code ↔ addy-code-simplification; code-review: ce-code-review ↔ addy-code-review / bmad-code-review; optimize: ce-optimize ↔ addy-performance; browser QA: ce-test-browser + ce-dogfood ↔ addy-browser-testing; commit: ce-commit ↔ addy-git-workflow; finalize: ce-commit-push-pr ↔ gsd-ship / addy-shipping / openspec-archive
    • learn cluster (new): ce-compound ↔ bmad-retrospective (left non-equivalent — differing terminal acts, like the release cluster)
    • added reciprocal equivalent_to edges on all counterpart capability pages (30 edits)
  • STAGE RE-DERIVATION (seventh framework):
    • stage-learn PROMOTED (see above).
    • stage-align → seven-framework (ce-brainstorm/ideate/pov/strategy/sweep); added CE ideation + a new evaluate-external-inputs sub-flavor (ce-pov). stage-govern NOT advanced — CE’s STRATEGY.md is a product-strategy context anchor, not an immutable gated charter; still SpecKit-only.
    • stage-plan → seven-framework; plan-verification promoted to FOUR frameworks (ce-doc-review, persona-fan-out variant). design candidate unchanged.
    • stage-implement → seven-framework execute cluster (ce-work + worktree/debug/polish).
    • stage-validate: stage-review split strengthened but NOT promoted — CE makes Simplify (4) + Review (5) explicit distinct loop phases (closer to Addy than BMAD), so review-as-a-distinct-phase now appears in TWO frameworks (Addy, CE); but CE lacks a co-equal functional-validation phase (testing skills are on-demand), so the clean Verify∥Review partition is still cleanest in Addy alone. Not promoted — also avoids two stage-splits in one ingest (minimize rule). Decisive trigger refreshed.
    • stage-release: two flavors now (learning close-out moved out).
  • Cascade (updated + dates 2026-07-04): all 6 stage pages (backlinks, aka, equivalents, split-candidate refresh) + new stage-learn; 30 counterpart capabilities (reciprocal equivalent_to); reused artifacts plan-md/review-report/atomic-commit/pull-request (CE Produced-by); reused patterns parallel-persona-review, adversarial-review, fresh-context-subagents, systematic-debugging, measure-first, deep-modules, grilling, vertical-slice, source-grounding, trunk-based-development, context-engineering, plan-verification-loop (CE Applied-by); framework See Also cross-links on gsd, addy-agent-skills, openspec, speckit, bmad, matt-pocock-skills; index.md (framework + 26 capabilities + stage-learn + stage-release edit + 4 artifacts + 3 patterns).
  • Scope: paged all 26 lifecycle skills + lfg (full per-capability coverage per user preference). The 26 shared sub-agents (research/grounding, review specialists, design/planning) + ~23 review-persona lenses are catalogued grouped-by-function on the framework page rather than individually paged (per the catalogue-thin-helpers convention, as with GSD’s sub-agent roster) — noted here for a future ingest if per-sub-agent pages are wanted. Infra/product-specific skills ce-setup, ce-proof (Proof editor), ce-riffrec-feedback-analysis (Riffrec) catalogued on the framework page, not paged.

[2026-07-05] ingest (addendum) | Compound Engineering — page all 26 sub-agents

  • User directed full per-sub-agent coverage (reinforces the standing full-coverage memory, which already covers sub-agents). Reversed the prior “catalogue-only” scoping for the 26 CE sub-agents.
  • Created 26 sub-agent capability pages (subtype: sub-agent, ce--prefixed per the framework-prefixed unique-basename convention), each filed by intrinsic activity:
    • align (9): ce-repo-profiler, ce-learnings-researcher, ce-slack-researcher, ce-web-researcher, ce-issue-intelligence-analyst, ce-external-evidence-researcher, ce-precedent-activity-scout, ce-project-grounding-scout, ce-media-analyzer
    • plan (6): ce-agent-native-planning-strategist, ce-architecture-strategist, ce-spec-flow-analyzer, ce-git-history-analyzer, ce-data-migration-reviewer, ce-deployment-verification-agent
    • implement (1): ce-figma-design-sync
    • validate (5): ce-security-sentinel, ce-performance-oracle, ce-pattern-recognition-specialist, ce-data-integrity-guardian, ce-repo-research-analyst
    • release (1): ce-pr-comment-resolver
    • learn (4): ce-best-practices-researcher, ce-framework-docs-researcher, ce-session-historian, ce-work-recap-scout
    • Note: the compound-council reviewers (security/performance/pattern/data-integrity) are filed by intrinsic activity (validate) with their ce-compound learning role noted, since that’s where their cross-framework counterparts live; the pure researchers/historians file under learn.
  • Descriptions sourced from the actual agent definitions (gh api on skills//references/agents/.md).
  • New cross-framework equivalent_to (reciprocal both ways): ce-security-sentinel ↔ addy-security-auditor; ce-performance-oracle ↔ addy-web-performance-auditor.
  • Wiring: delegates_to populated on 11 dispatching skills (ce-brainstorm/ideate/pov/plan/work/optimize/sweep/resolve-pr-feedback/compound/explain/code-review) → their sub-agents; framework page sub-agent roster rewritten from code-name catalogue to grouped wikilink list (“each paged”); produced-by backlinks added on artifact-security-audit (+ce-security-sentinel), artifact-perf-audit (+ce-performance-oracle), artifact-launch-checklist (+ce-deployment-verification-agent), artifact-explainer (+ce-work-recap-scout), artifact-solution-doc (+7-member council); applied-by bullets added on patterns fresh-context-subagents, source-grounding, knowledge-compounding, adversarial-review, measure-first, plan-verification-loop, context-engineering, deep-modules; index.md +26 sub-agent rows; framework updated → 2026-07-05.
  • Retained catalogue-only (non-lifecycle): ~23 review-persona lenses inside ce-code-review/ce-doc-review (bundled reference lenses, not standalone agents), and infra/product skills ce-setup/ce-proof/ce-riffrec-feedback-analysis.

[2026-07-05] ingest | gstack (Garry Tan / YC) — eighth framework, largest here

  • Source: github.com/garrytan/gstack (MIT). Raw: raw/gstack/2026-07-05-gstack-framework.md (README + AGENTS.md + ETHOS.md verbatim + generated SKILL.md frontmatter catalogue).
  • Framework page framework/gstack.md created. Sprint: Think→Plan→Build→Review→Test→Ship→Reflect. The largest framework in the wiki (~54 skills). Ethos: Boil the Ocean / Search Before Building / User Sovereignty.
  • CAPABILITIES: 54 pages created (full per-capability coverage per standing memory) — all 53 SKILL.md skills + the root router (gstack-router; equivalent_to addy-using-agent-skills). All subtype: command (gstack ships slash-command skills; role personas rather than separately-paged sub-agents). Filed by sprint stage:
    • align (1): gstack-office-hours (grilling cluster).
    • plan (7): gstack-plan-ceo-review/plan-eng-review/plan-design-review/plan-devex-review/autoplan/plan-tune/design-consultation.
    • specify (1): gstack-spec (sixth framework in the specify cluster; Codex quality gate).
    • implement (10): gstack-design-shotgun/design-html/investigate/scrape/careful/freeze/guard/unfreeze/context-save/context-restore + pair-agent.
    • validate (18): Review-side gstack-review/codex/design-review/devex-review/cso/health/ios-design-review; Test-side gstack-qa/qa-only/benchmark/ios-qa/ios-fix; enabling gstack-browse/open-gstack-browser/setup-browser-cookies/ios-sync.
    • release (8): gstack-ship/land-and-deploy/canary/landing-report/document-release/document-generate/setup-deploy/ios-clean.
    • learn (5): gstack-retro/learn/skillify/setup-gbrain/sync-gbrain.
    • no-stage (4, meta/utility): gstack-diagram/make-pdf/benchmark-models/gstack-upgrade + gstack-router.
  • NEW artifacts (3): artifact-design-mockup (design-shotgun variants), artifact-diataxis-docs (document-generate/-release), artifact-retrospective (gstack-retro + bmad-retrospective — the team-process learn flavor).
  • NEW patterns (2): pattern-edit-guardrails (gstack signature: careful/freeze/guard + auto-freeze), pattern-cross-model-review (gstack /codex + CE ce-code-review — two frameworks).
  • Cross-framework equivalent_to wired: gstack-office-hours↔grilling cluster; gstack-spec↔specify cluster (speckit-specify/addy-spec-driven/mp-to-prd/openspec-propose/bmad-prd); gstack-investigate↔debugging cluster; gstack-review↔code-review cluster; gstack-cso↔addy-security-auditor/ce-security-sentinel/addy-security; gstack-benchmark↔addy-performance/-web-performance-auditor/ce-optimize/-performance-oracle; gstack-qa↔ce-test-browser/addy-browser-testing/ce-dogfood; gstack-ios-qa↔ce-test-xcode; gstack-ship↔gsd-ship/addy-shipping/openspec-archive/ce-commit-push-pr; gstack-canary↔ce-product-pulse; gstack-retro↔bmad-retrospective; gstack-learn↔ce-compound/-refresh; gstack-context-save/restore↔mp-handoff; gstack-router↔addy-using-agent-skills; gstack-design-consultation↔bmad-ux; plan-eng-review↔gsd-plan-checker/speckit-analyze/bmad-check-implementation-readiness/ce-doc-review.
  • STAGE RE-DERIVATION (eighth framework):
    • stage-learn → THREE frameworks (beyond doubt). gstack ships BOTH flavors — team retrospective (gstack-retro → artifact-retrospective) + agent-grounding corpus (gstack-learn → artifact-solution-doc) + capability-compounding (gstack-skillify). First framework to populate both flavors at once.
    • stage-validate: stage-review split BAR NOW CLEARED (⚑ not yet executed). gstack is the SECOND framework (after Addy) with a clean Review phase ∥ Test phase partition — the exact decisive trigger. Marked cleared on the stage page + index with a recommendation to promote (stage-validate functional + stage-review quality gate) as a focused next pass — deferred because it’s a ~17-capability re-pointing cascade across the existing wiki that merits its own verifiable ingest, not bundling into gstack’s (already large) one.
    • stage-release: stage-operate candidate strengthened to capability-level in THREE frameworks (Addy + CE + gstack). gstack is the first with a genuine deploy command (land-and-deploy) separate from ship + a post-deploy monitor (canary), but still nests them under release rather than a standalone Operate phase — so strengthened, not promoted.
    • stage-align → EIGHT frameworks (gstack-office-hours, grilling flavor).
    • stage-specify → SIX frameworks (gstack-spec; cross-model quality gate).
    • stage-plan → plan-verification now FIVE frameworks (gstack-plan-eng-review; persona-panel variant via autoplan).
    • stage-implement → execute cluster + gstack build/guardrails/session/pairing.
    • No stage renamed, split, merged, or added this ingest (two candidates now flagged for a follow-up split pass).
  • Cascade (dates → 2026-07-05): all 7 stage pages (aka + gstack backlink subsections + count/split-candidate updates); 11 reused artifacts (Produced-by gstack bullets — via subagent); 15 reused patterns (Applied-by gstack bullets — persona-agents/session-handoff/knowledge-compounding/autonomous-loop done inline, other 13 via subagent, incl. framework-count bumps on persona-agents [+gstack], session-handoff [3rd], knowledge-compounding [3rd]); index.md (framework row + 55 capability rows + 3 artifacts + 2 patterns + 7 stage summaries + ~18 pattern rows + 11 artifact rows).
  • Dangling-wikilink check: clean (0 new; the 6 pre-existing hits are CONVENTIONS.md example placeholders).
  • FOLLOW-UP RECOMMENDED: promote the now-cleared stage-review split (Verify∥Review) as a focused pass.

[2026-07-05] re-derivation (split) | stage-validate → stage-validate + stage-review

  • Executed the follow-up flagged above. Promoted stage-review as the 8th canonical stage, splitting the (previously widest) stage-validate into its two long-parked halves once gstack became the 2nd framework (after Addy) with a clean Verify (functional) ∥ Review (quality) phase partition — clearing the ≥2-framework bar (same mechanism as stage-specify ← stage-plan and stage-learn ← stage-release).
  • stage-validate (functional — “does it work”): UAT, runtime/browser tests, spec-conformance, iOS device tests. 16 capabilities retained: gsd-verify-work, gsd-verifier, addy-browser-testing, openspec-verify, speckit-converge, ce-test-browser, ce-dogfood, ce-test-xcode, gstack-qa, gstack-qa-only, gstack-ios-qa, gstack-ios-fix, + gstack enabling (browse, open-gstack-browser, setup-browser-cookies, ios-sync). Frameworks: GSD, Addy, OpenSpec, SpecKit, CE, gstack (6).
  • stage-review (quality gate — “is it good”): code review, security, performance, simplification, architecture, design/DX audit. 26 capabilities re-pointed implements: [[stage-validate]][[stage-review]]:
    • MP: mp-improve-codebase-architecture.
    • Addy (its Review phase + /ship personas): addy-code-review, addy-code-simplification, addy-security, addy-performance, addy-code-reviewer, addy-test-engineer, addy-security-auditor, addy-web-performance-auditor.
    • BMAD: bmad-code-review.
    • CE (loop steps 4–5 + review sub-agents): ce-simplify-code, ce-code-review, ce-optimize, ce-security-sentinel, ce-performance-oracle, ce-pattern-recognition-specialist, ce-data-integrity-guardian, ce-repo-research-analyst.
    • gstack (its Review phase): gstack-review, gstack-codex, gstack-cso, gstack-benchmark, gstack-design-review, gstack-devex-review, gstack-health, gstack-ios-design-review.
    • Frameworks: MP, Addy, BMAD, CE, gstack (5). GSD, OpenSpec, and Spec Kit ship no review capability (functional validators only) — the clean absence that made the split correct.
  • Classification rule (framework-neutral, by activity): run it and observe → validate; read it and judge quality → review. equivalent_to clusters kept intact within one stage (code-review, security, performance, simplification, browser-testing, iOS-test). Judgment calls: gstack-benchmark → review (performance cluster, not “Test” despite gstack’s label); addy-test-engineer → review (Addy’s Review-phase /ship persona); gsd-verifier → validate (goal-backward = functional).
  • New page: sdlc-stage/stage-review.md (full projection: promoted-note, why-distinct, backlinks by framework, clusters, See Also). Rewrote sdlc-stage/stage-validate.md to functional-only (removed the review backlinks, narrowed the definition/aka, replaced the split-candidate section with a “resolved” note).
  • Cascade (dates → 2026-07-05): re-pointed 26 capability pages (implements + body stage-validatestage-review); framework pages gstack (Review heading + stage list → all 8), addy-agent-skills (Review row + Verify∥Review note + stage list), bmad (Implementation row + TEA note + stage list; no functional validate), compound-engineering (loop table Simplify/Review + split Validate section into Review+Validate + review sub-agent tags + stage list), matt-pocock-skills (heading “(Verify)”→“(Review)” + See Also); lfg range (+stage-review); ce-doc-review / ce-resolve-pr-feedback (references to ce-code-review’s stage); artifacts review-report/security-audit/perf-audit (gate stage → review); patterns deep-modules/measure-first/cross-model-review/adversarial-review/parallel-persona-review (stage refs → review); stage-implement/-release/-learn See Also. index.md: stage-validate row rewritten + new stage-review row + 16 capability-row parentheticals (validate→review).
  • Stage count now 8: align · specify · plan · implement · validate · review · release · learn.
  • Dangling-wikilink check: to be confirmed clean post-cascade.

[2026-07-09] ingest (update) | Matt Pocock — Skills for Real Engineers v1.1

  • Re-ingest of github.com/mattpocock/skills at v1.1 (was 2026-06-28). New raw: raw/matt-pocock-skills/2026-07-09-skills-v1.1-update.md (README + full SKILL.md catalogue across engineering/productivity/misc/deprecated/in-progress/personal + CHANGELOG v1.1 highlights). Old raw retained (immutable).
  • RENAMES (page + full wikilink cascade across 20 files; log.md history left intact):
    • to-prdmp-to-spec — “spec” is now the through-line term; produces artifact-spec-md, no longer artifact-prd (still opens “you may know this as a PRD”).
    • to-issues + to-planmp-to-tickets (to-issues deleted) — tracer-bullet tickets with blocking edges; local tickets.md vs native tracker links; wide-refactor expand–contract.
  • NEW capability pages (7): mp-implement (execute — MP’s first first-class execute skill; joins the 7-framework execute cluster), mp-code-review (review — two-axis Standards∥Spec + Fowler smell baseline; graduated from in-progress review; code-review cluster now 5-framework), mp-research (plan — background primary-source agent → artifact-research-md; ↔ gsd-phase-researcher), mp-wayfinder (plan — investigation-ticket map for oversized work; graduated from decision-mapping), mp-resolving-merge-conflicts (implement), mp-triage (align — issue/PR triage → agent-ready briefs; ↔ ce-sweep; newly paged), mp-ask-matt (router; ↔ addy-using-agent-skills + gstack-router; newly paged).
  • CONTENT updates to existing pages: mp-tdd (reference-only red → green; refactor moved to mp-code-review; “seam” leading word), mp-domain-modeling (absorbed deprecated ubiquitous-language; +artifact-adr), mp-prototype (now model-invoked), mp-grilling (confirmation gate + facts-vs-decisions HITL guarantee). Framework page rewritten: documented main flow (idea→grill→to-spec→to-tickets→implement→code-review via mp-ask-matt), new deprecated/in-progress/personal catalogues.
  • Deprecations noted (not paged; were never paged): ubiquitous-language (→ domain-modeling), design-an-interface, qa, request-refactor-plan.
  • Reciprocal equivalent_to edges added on 13 counterpart pages (code-review ×4, execute ×6, gsd-phase-researcher, router ×2 + closed the addy↔gstack-router gap). Renamed skills’ reciprocals maintained by the wikilink cascade.
  • STAGE re-derivation (no new stage / split / merge): stage-align (+mp-triage intake), stage-specify (mp now → spec not PRD), stage-plan (+mp-research, +mp-wayfinder), stage-implement (+mp-implementexecute cluster now 7 frameworks; +mp-resolving-merge-conflicts), stage-review (+mp-code-reviewcode-review cluster now 5 frameworks). aka updated on all 5; dates → 2026-07-09. MP still ships no functional stage-validate, stage-release, or stage-learn capability.
  • Artifacts: artifact-prd → BMAD-only (MP moved to spec); artifact-spec-md +mp-to-spec; artifact-issue +mp-to-tickets/mp-triage/mp-wayfinder; artifact-research-md +mp-research; artifact-review-report +mp-code-review.
  • index.md: MP framework row + 2 renamed rows + 7 new capability rows + 4 changed rows + 5 artifact rows + stage dates.
  • Dangling-wikilink check: clean (see below).

[2026-07-09] ingest | BM Skills (Builder Methods) — PRD Creator (+ 2 utilities)

  • Source: github.com/buildermethods/bm-skills (Brian Casel). A Claude Code plugin marketplace of small, independent builder utilities — not a full-SDLC framework; ingested primarily to capture the PRD Creator. Raw: raw/bm-skills/2026-07-09-bm-skills.md (README + CLAUDE + 3 SKILL.md + PRD step catalogue).
  • Framework page framework/bm-skills.md (noted explicitly as a light utility collection, not a lifecycle engine).
  • CAPABILITIES (3 paged, full coverage): bm-prd-creator (focus — specify; non-technical-builder interview → visual HTML/markdown PRD + milestones/N-{slug}/prompt.md files; strict what-not-how boundary), bm-design-system (implement — React+Tailwind v4 design-system scaffold + AGENTS.md guardrails; ↔ addy-frontend-ui), bm-favicon-creator (no stage — pure asset utility, like gstack-make-pdf/diagram).
  • Specify cluster → seven frameworks: bm-prd-creator joins bmad-prd / mp-to-spec / addy-spec-driven-development / openspec-propose / speckit-specify / gstack-spec. Reciprocal equivalent_to added on all 6 (+ addy-frontend-uibm-design-system). Its distinctive angle: audience (non-technical builder), visual HTML PRD, milestone prompts.
  • Artifacts: artifact-prd regains a second producer (bm-prd-creator) alongside bmad-prd; artifact-plan-md +bm-prd-creator (milestone prompt files); artifact-design-md +bm-design-system (code-scaffold form).
  • STAGE re-derivation: no new stage / split / merge (small ingest). stage-specify (+bm-prd-creator → 7-framework convergence; aka +bm-skills), stage-implement (+bm-design-system; aka +bm-skills). MP/gstack/etc. unaffected.
  • index.md: +bm-skills framework row, +3 capability rows, updated artifact-prd/plan-md/design-md + stage-specify rows.
  • Dangling-wikilink check: clean (below).

[2026-07-13] ingest | nano-spec (Tao An) — 4-document spec pack

  • Source: github.com/tao-hpu/nano-spec (Tao An, MIT, 46★) + intro article “The Sweet Spot Between Chaos and Over-Engineering in AI-Assisted Development” (Generative AI / Medium, 2025-12-01). Raw: raw/nano-spec/2025-12-01-nano-spec.md (README + SKILL.md verbatim + article digest). A deliberately minimal, tool-agnostic spec methodology — “Spec-driven thinking, nano-sized docs”; not a full-SDLC framework (like bm-skills).
  • Framework page framework/nano-spec.md carries the requested source_url (repo) and docs_url (article) frontmatter properties in addition to the standard sources:/raw:.
  • CAPABILITIES (3 paged, full coverage per the one-page-per-action convention; one /nano-spec skill, $ACTION = create/status/update, re-published as system-prompt configs for 9 other agents): nano-spec-create (focus — specify; generates the 4-doc pack), nano-spec-status (no stage — read-only progress report; session-handoff), nano-spec-update (no stage — living-doc maintenance; session-handoff).
  • Specify cluster → eight frameworks: nano-spec-create joins bm-prd-creator / mp-to-spec / addy-spec-driven-development / openspec-propose / speckit-specify / bmad-prd / gstack-spec. Reciprocal equivalent_to added on all 7. Its distinctive angle: weight — the minimalist pole (fixed 4-file pack, ~10-min setup, tool-agnostic) opposite the gated maximalists and OpenSpec’s living spec.
  • NEW artifact artifact-nano-spec-pack (nano-spec’s signature: tasks/{name}/ README+todo+doc+log). Component mappings also wired to existing artifacts: artifact-plan-md (+nano-spec todo.md), artifact-adr (+nano-spec doc.md Key Decisions).
  • PATTERNS: pattern-spec-driven-development (+nano-spec, minimalist instance; also back-filled missing bm-prd-creator backlink), pattern-scale-adaptive-planning (+nano-spec — a fixed middle tier on the no-spec→nano→full-spec spectrum, the pattern applied at the methodology level; now 3-framework), pattern-session-handoff (+nano-spec — the always-current 4-file pack is the handoff; now 4-framework).
  • STAGE re-derivation: no new stage / split / merge / retire (small, single-stage ingest); no parked split candidate cleared. stage-specify (+nano-spec-create → 8-framework; aka +nano-spec; date 2026-07-13). nano-spec ships no stage-plan/stage-implement/stage-validate/stage-review/stage-release/stage-learn capability (its log.md is within-task journaling, not cross-iteration knowledge-compounding).
  • index.md: +nano-spec framework row, +3 capability rows, +artifact-nano-spec-pack row; updated stage-specify, artifact-plan-md, artifact-adr, and 3 pattern rows.
  • Dangling-wikilink check: clean (below).

[2026-07-17] ingest | Superpowers (Jesse Vincent / Prime Radiant) — 14-skill methodology

  • Source: github.com/obra/superpowers @ v6.1.1 (Jesse Vincent, Prime Radiant; MIT; release announcement blog.fsck.com 2025-10-09). Raw: raw/superpowers/2026-07-17-superpowers.md (README + plugin.json + all 14 skills/*/SKILL.md verbatim; supporting files noted, not reproduced). A complete methodology from a small library — 14 skills, no personas, no commands, no deploy — made whole by a bootstrap (sp-using-superpowers) that forces skill invocation before any action; cross-harness (Claude Code/Codex/Cursor/Kimi/OpenCode/Pi/…).
  • Framework page framework/superpowers.md: the mandatory-skill bootstrap, the gated pipeline (brainstorm→worktree→plan→subagent-driven→TDD→review→finish), 4 philosophy pillars, capabilities by function, artifacts, patterns, See Also.
  • CAPABILITIES (14 paged, full coverage; all subtype: skill, prefix sp-): sp-using-superpowers (meta/router; no stage; ↔ addy-using-agent-skills/gstack-router/mp-ask-matt), sp-brainstorming (align; grilling), sp-writing-plans (plan; decompose), sp-subagent-driven-development + sp-executing-plans (implement; execute cluster), sp-test-driven-development (implement; TDD), sp-systematic-debugging (implement; debugging), sp-using-git-worktrees (implement; worktree-isolation), sp-dispatching-parallel-agents (implement; parallel dispatch), sp-verification-before-completion (validate; novel claim-verification gate), sp-requesting-code-review (review) + sp-receiving-code-review (review; novel — the review-reception side no other framework pages), sp-finishing-a-development-branch (release), sp-writing-skills (learn; capability-compounding).
  • NEW pattern pattern-evidence-before-claims (Superpowers’ signature — verify then assert; sp-verification-before-completion). NEW artifact artifact-skill-doc (a SKILL.md; ↔ gstack-skillify).
  • STAGE re-derivation: no new stage / split / merge / rename — Superpowers fits the existing 8 stages, touching 7 (no stage-specify: design folds into brainstorming→writing-plans, like GSD). Notable reinforcement: it is the 3rd framework (after Addy, gstack) with a clean functional-validate ∥ quality-review partition (verification-before-completion ∥ code-review), and the 4th framework in stage-learn (capability-compounding flavor). Split candidates unchanged: stage-govern (no constitution), stage-design (folds design in), stage-operate (no deploy). aka + dates → 2026-07-17 on stage-align/plan/implement/validate/review/release/learn.
  • CLUSTER growth: execute → 8-framework (+sp-executing-plans/sp-subagent-driven-development); decompose/plan → 6; code-review → 6-framework (+sp-requesting-code-review); debugging cluster +sp-systematic-debugging (tightest tie gstack-investigate, shared Iron Law + stop-after-3); TDD +sp-test-driven-development; grilling/align → 9-framework (+sp-brainstorming); worktree-isolation → 2-framework (ce-worktreesp-using-git-worktrees); finalize/release → 5-framework; capability-compounding gstack-skillifysp-writing-skills; routers +sp-using-superpowers.
  • Reciprocal equivalent_to edges added on 33 counterpart pages: debugging ×5 (gsd-debugger/mp-diagnosing-bugs/addy-debugging/ce-debug/gstack-investigate), routers ×3, code-review ×5, TDD ×2, grilling ×5, execute ×7 (+SDD on gsd-execute-phase & bmad-dev-story), plan ×6, release ×5, plus ce-worktree ↔ sp-using-git-worktrees and gstack-skillify ↔ sp-writing-skills. Also back-filled missing gstack-review ↔ (addy/bmad/ce)-code-review and gstack-office-hours ↔ (grilling cluster) and gstack-ship ↔ (release cluster) reciprocals encountered during the pass.
  • PATTERN pages updated with Superpowers backlinks + Shared tallies: anti-rationalization (co-signature), fresh-context-subagents, test-driven-development, systematic-debugging, worktree-isolation (1→2), adversarial-review, grilling, knowledge-compounding, vertical-slice, trunk-based-development, wave-parallelism.
  • index.md: +superpowers framework row, +14 capability rows, +pattern-evidence-before-claims row, +artifact-skill-doc row; updated 7 stage rows, 11 pattern tally rows, and artifacts design-md/plan-md/pull-request/review-report/atomic-commit.
  • Stage count unchanged: 8 — align · specify · plan · implement · validate · review · release · learn.
  • Dangling-wikilink check: clean (below).

[2026-07-19] docs | artifact index — visual map of the 34 artifacts

  • Not an ingest: no new source, no ontology/edge changes. Added a reader-facing index for the artifact/ namespace (the namespace had none; only sdlc-stage/ did).
  • NEW wiki/artifact/index.md: a whole-lifecycle flow overview Mermaid diagram of all 34 artifacts grouped by producing stage (solid leads-to/feeds/gates edges + dotted grounds-next-loop back-edges), then a stage-by-stage detail section — one Mermaid per SDLC stage, each in the layout that fits its artifacts (Align two-cluster · Specify hub-around-spec · Plan pipeline · Implement converge · Validate repair-loop · Review fan-in · Release converge/diverge · Learn hub + loop-back). Boundary artifacts from adjacent stages shown as dashed rounded nodes for context. Closes with a stage-ordered table of all 34 (Obsidian wikilinks) + See Also.
  • Each of the 8 stage-detail section headings links to its stage page (../sdlc-stage/stage-<x>.md); all 8 targets verified.
  • index.md: ## artifact intro now links the new visual artifact index.
  • All 9 Mermaid blocks validated via @mermaid-js/mermaid-cli; artifact wikilinks + stage links resolve. Dangling-wikilink check: clean.

[2026-07-20] refactor | rename artifact-context-md → artifact-phase-context (naming symmetry)

  • Not an ingest: no new source. Resolved a slug asymmetry around the cross-framework CONTEXT.md clash. GSD’s phase-context artifact was slugged by filename (artifact-context-md) while MP’s was slugged by meaning (artifact-domain-model), implying the GSD page “owned” the canonical name when neither does.
  • Renamed wiki/artifact/artifact-context-md.mdartifact-phase-context.md (git mv); H1 retitled CONTEXT.md (phase context)Phase context (CONTEXT.md) to mirror Domain model (CONTEXT.md) (meaning-first). Both CONTEXT.md artifacts are now filed by what they are; the colliding filename belongs to neither slug.
  • Updated all wikilinks/backlinks (9 pages): index.md (row + domain-model clash note prose), framework/gsd.md, capability/gsd-discuss-phase.md (produces: + body), sdlc-stage/stage-specify.md, sdlc-stage/stage-align.md, artifact/artifact-spec-md.md, artifact/artifact-brainstorm-md.md, artifact/artifact-domain-model.md (reciprocal clash note), artifact/index.md.
  • Reciprocal naming-conflict callouts and the Align-stage same filename, different artifact dotted edge left intact. Historical log entries above retain the old slug as-written.
  • Dangling-wikilink check: clean.

[2026-07-20] docs | CONVENTIONS.md — ontology-at-a-glance Mermaid diagram

  • Not an ingest: no new source, no ontology/edge changes. Added a visual summary of the schema itself at the top of CONVENTIONS.md (before the Node types table), since the diagram depicts the meta-model the conventions define — not the concrete articles the index.md files list.
  • NEW ## The ontology at a glance section: a Mermaid flowchart showing the 5 node types (framework/capability/sdlc-stage/artifact/pattern) and 6 stored edges (belongs_to/implements/produces/applies/delegates_to/equivalent_to), all originating from capability as the hub; plus a dashed derived-projection edge (sdlc-stage synthesized from implements-backlinks). Distinct node shapes per type; solid = stored frontmatter edge, dashed = derived. Cross-links to the Node types + Relationship vocabulary tables.
  • Diagram validated via @mermaid-js/mermaid-cli (renders clean).

[2026-07-20] edit | reclassify mp-wayfinder: stage-plan → stage-align

  • Not an ingest: no new source. Corrected one capability’s implements: edge. mp-wayfinder maps an oversized effort as a tracker of investigation tickets that resolve decisions (“Plan, don’t do — tickets resolve decisions, not deliverables”) and hands its output to mp-to-spec / mp-to-tickets. Since mp-to-spec IS stage-specify, wayfinder must sit upstream of the spec — i.e. it shapes what to build (stage-align), not decompose-the-how (stage-plan). Fits stage-align’s definition (align on what to build and why; capture/lock decisions) as a large-scale decision-mapping flavor.
  • capability/mp-wayfinder.md: implements stage-plan → stage-align; See Also stage link + rationale; updated date.
  • sdlc-stage/stage-plan.md: removed the mp-wayfinder backlink; dropped wayfinder from the matt-pocock-skills aka; updated date.
  • sdlc-stage/stage-align.md: added mp-wayfinder backlink (decision-mapping flavor) under Matt Pocock; added wayfinder to the matt-pocock-skills aka; updated date.
  • framework/matt-pocock-skills.md: moved mp-wayfinder from the “Skills — plan” group to “Skills — align / elicitation & intake”.
  • index.md: mp-wayfinder row now reads “(align)”; updated date. Framework-count on both stages unchanged (MP already counted on each). No stage added/removed/renamed. artifact-issue.md left as-is (stage-neutral; wayfinder still produces tracker issues).

[2026-07-20] docs | SDLC index — framework × stage support matrix

  • Not an ingest: no new source, no ontology/edge changes. Added a second table to sdlc-stage/index.md: 11 frameworks (rows) × 8 canonical stages (columns), each cell an emoji support level. Derived mechanically from the implements: edges of every capability (framework = belongs_to, stage = implements), then graded.
  • Legend: 🟢 native (dedicated step / several capabilities) · 🟡 partial (1–2 caps, not a distinct phase) · 🔗 folded into an adjacent stage · ➖ none. Rows ordered by lifecycle coverage (gstack/CE/Superpowers full-8 at top → nano-spec point-tool at bottom).
  • Footnote captures nuance the emoji can’t: OpenSpec Release = spec-merge not deploy (gstack the only real deploy); folded cases (GSD/Superpowers/CE fold specify into Align/Plan; OpenSpec folds plan into propose); BM Skills + nano-spec are deliberate point tools. Consistent with the existing Note that GSD/OpenSpec/Spec Kit ship no Review and Spec Kit no Release.

[2026-07-20] docs | SDLC index — off-stage capability column + summary

  • Extended the framework × stage support matrix with a 9th Off-stage column: a count (not a support level — kept visually distinct from the 🟢/🟡/🔗/➖ stage cells) of each framework’s capabilities that map to no lifecycle stage. Counts: gstack 5, Matt Pocock 2, nano-spec 2, Addy 1, Superpowers 1, BM Skills 1; GSD/OpenSpec/Spec Kit/BMAD/Compound Engineering 0.
  • NEW ### Off-stage capabilities subsection: the 12 no-stage capabilities grouped by kind — routing/dispatch & bootstrap (the near-universal cluster: addy-using-agent-skills ↔ mp-ask-matt ↔ gstack-router ↔ sp-using-superpowers), session/context continuity (mp-handoff), spec-pack state ops (nano-spec-status/update), publishing & diagrams (gstack-diagram/make-pdf), tooling & self-maintenance (gstack-benchmark-models/upgrade, bm-favicon-creator).
  • Insight recorded: process-owning frameworks (GSD/OpenSpec/Spec Kit/BMAD/CE) keep everything on-lifecycle (zero off-stage); toolkit/marketplace-style ones ship standalone utilities around the pipeline. All 15 wikilinks verified.

[2026-07-26] ingest | Sandcastle + Warren — NEW runtime node type (execution layer)

  • Ontology extension (6th node type). Added runtime — the agent execution/orchestration substrate (sandbox isolation, parallelism, AFK autonomy, steering, persistence): where and how an agent runs, vs the process layer’s what. Motivated by the observation (confirmed with the user) that Sandcastle and Warren are a genuinely different entity type from the process frameworks: they ship no SDLC capabilities and would contribute nothing to stage synthesis if force-fit as frameworks. Rather than dilute framework or pollute the framework×stage matrix, they get their own layer.
  • The seam is pattern, not sdlc-stage. A runtime carries no belongs_to/implements/equivalent_to; it stores exactly one new edge — enables: (runtime → pattern[]) — the infra-side realization of patterns that capabilities apply at the process level. pattern pages now collect two backlink rosters: Applied by (capabilities) + Enabled by (infrastructure) (runtimes).
  • CONVENTIONS.md: opening scope para (added the execution layer); “ontology at a glance” now “Six node types, seven relationship edges”; Mermaid diagram gains RT{{runtime}} + RT -->|enables| PAT; node-types table + runtime subtypes (library|platform) + runtime frontmatter example + enables row in the relationship vocabulary + derived-edges note + naming-convention row; NEW ## The execution layer (runtimes) section (orthogonal layer, synthesis-as-matrix-not-nodes with a parked graduation trigger, runtime ingest workflow).
  • NEW raw/runtime/ with verbatim README captures: 2026-07-26-sandcastle.md, 2026-07-26-warren.md.
  • NEW wiki/runtime/:
    • sandcastle.md (subtype library) — Matt Pocock’s TS SDK; enables: worktree-isolation + autonomous-loop + wave-parallelism + session-handoff. The library pole.
    • warren.md (subtype platform) — Jaymin West’s self-hosted control plane (os-eco, v0.9.10); enables: autonomous-loop + worktree-isolation + knowledge-compounding + session-handoff. The platform pole.
    • index.md — layer overview + orchestration-concern comparison matrix (the runtime analogue of the stage synthesis) + broader-category note (Conductor, Container-use, Sculptor, os-eco siblings).
  • Cascade — added Enabled by (infrastructure) subsections + refreshed sources/updated on 5 patterns: pattern-worktree-isolation (sandcastle+warren), pattern-autonomous-loop (sandcastle+warren), pattern-wave-parallelism (sandcastle), pattern-session-handoff (sandcastle+warren), pattern-knowledge-compounding (warren — the standout: .mulch/ bakes stage-learn’s compounding into the runtime).
  • Deliberately not linked: pattern-fresh-context-subagents (these runtimes isolate the filesystem/process, not the agent’s context window — that’s worktree-isolation’s territory; the harness owns context).
  • index.md: intro now names six namespaces; NEW ## runtime section (2 rows + matrix pointer); 5 pattern rows annotated with their infra-side + dates bumped to 2026-07-26.
  • No stage added/renamed/retired (runtimes implement no stage). Stage set unchanged at 8.
  • Verification: dangling-wikilink check across wiki/ — clean; every [[sandcastle]]/[[warren]] and enables: target resolves.

[2026-07-31] ingest | Claude Code — NEW harness node type (agent-program layer) — SCHEMA + PROOF PAGE

  • Ontology extension (7th node type). Added harness — the agent program itself (Claude Code, pi, OpenCode, …): the loop that loads a framework’s skills/commands and drives the model’s tool-call cycle. Motivated (confirmed with the user) by the observation that the two existing layers were already defined against it — frameworks were described as “cross-harness” and runtimes as “harness-agnostic” — yet it had no node. It is the middle/pivot layer: not a framework (ships execution primitives, not an SDLC methodology) and not a runtime (it is the thing runtimes spawn/wrap, one layer up).
  • Two new stored edges + a second enables domain. framework --runs_on--> harness[] (the first forward edge a framework page stores — turns “cross-harness” prose into structure) and runtime --runs--> harness[] (turns “harness-agnostic” prose into structure). harness --enables--> pattern[] reuses the enables edge (now domain = runtime or harness), so pattern pages gain a third backlink roster: Provided by (harness) alongside Applied by (capabilities) and Enabled by (infrastructure) (runtimes). “Ontology at a glance” now reads “Seven node types, nine relationship edges.”
  • CONVENTIONS.md: opening scope para (two substrate layers, harness as pivot); “ontology at a glance” para + Mermaid (HAR{{harness}} + FW -->|runs_on| HAR, RT -->|runs| HAR, HAR -->|enables| PAT); node-types table + harness subtypes (terminal|ide) + harness frontmatter example + framework-now-carries-runs_on note + runs_on/runs/broadened-enables rows in the relationship vocabulary + derived-edges note (harness is both target and source, like capability) + naming-convention row; NEW ## The harness layer section (framework/runtime boundary test, synthesis-as-matrix-not-nodes with parked graduation trigger, harness ingest workflow).
  • NEW raw/harness/2026-07-31-claude-code.md — source capture from Anthropic Claude Code docs + Agent SDK.
  • NEW wiki/harness/:
    • claude-code.md (subtype terminal) — reference terminal harness; enables: fresh-context-subagents + edit-guardrails + session-handoff + context-engineering; full capability matrix + interaction surfaces + primitives.
    • index.md — layer overview + capability-comparison matrix (one column until pi/OpenCode land) + broader-category note (pi, OpenCode, Codex, Aider, Gemini CLI, Amp; Cursor/Copilot/Windsurf on the ide pole).
  • Cascade (proof slice) — added Provided by (harness) subsections + refreshed sources/updated→2026-07-31 on the 4 patterns Claude Code enables: pattern-fresh-context-subagents (Agent/Task tool), pattern-edit-guardrails (hooks + permission modes — the substrate under gstack careful/freeze/guard), pattern-session-handoff (compaction + --resume), pattern-context-engineering (CLAUDE.md/memory + MCP + skill loader). Wired runs: [[claude-code]] on sandcastle + warren; runs_on: [[claude-code]] on superpowers + gstack.
  • index.md: intro now names seven namespaces; NEW ## harness section (claude-code row + matrix pointer); ## runtime blurb now also points through the harnesses it runs:.
  • No stage added/renamed/retired (a harness implements no stage). Stage set unchanged at 8.
  • STAGED — remaining work (the “rest”, pending user review of the shape):
    • Ingest pi and OpenCode as full pages (turns the one-column matrix into a real cross-harness comparison).
    • Fleet-wide runs_on: wiring across the other 9 frameworks (GSD/CE/Addy/BMAD/SpecKit/OpenSpec/BM/nano-spec/matt-pocock) + bump their updated:/index rows.
    • Extend runs: on sandcastle/warren to the full provider lists (needs Codex/Cursor/OpenCode/Copilot/pi pages or stubs so nothing dangles — currently only [[claude-code]] wired to keep the dangling-link check clean).
  • Verification: dangling-wikilink check across wiki/ — clean; every [[claude-code]] reference resolves. Not-yet-paged harnesses (pi, opencode, codex, cursor, copilot) are named in bold plain text (runtime “broader category” precedent), never as wikilinks, so nothing dangles.

[2026-07-31] ingest | pi + OpenCode harnesses; fleet-wide runs_on:; “officially supported” rule — completes the harness layer

  • Completes the STAGED work from the proof slice above, after user review of the shape. User decision recorded: runs_on: / runs: link only to officially supported/documented harnesses, not any a framework could theoretically run on.
  • Convention (CONVENTIONS.md): runs_on/runs vocab rows now say “officially supports/documents”; NEW Support scope paragraph — an edge = documented support; a supported harness with no page yet is recorded in prose (not a dangling edge) and wired when ingested, so stored edges trail documented support until every referenced harness has a page.
  • Two new harness pages (both subtype: terminal, MIT, model-agnostic), from web-researched raw captures raw/harness/2026-07-31-{opencode,pi}.md:
    • opencode.md — Anomaly (ex-SST); batteries-included + model-agnostic; enables: all four patterns (fresh-context-subagents, edit-guardrails, session-handoff, context-engineering). The open/model-agnostic pole.
    • pi.md — Zechner/Earendil; minimal core (4 tools; sub-agents/MCP/permissions/plan-mode excluded → extensions); enables: only session-handoff + context-engineering. The minimalist pole and the harness-layer counterpart to nano-spec.
  • The layer’s sharpest finding, now encoded: pattern-fresh-context-subagents and pattern-edit-guardrails are harness primitives in claude-code + opencode but absent from pi’s core — a pattern that is a primitive in some harnesses and not others. Both pattern pages’ harness rosters now carry an explicit Not pi bullet.
  • Fleet-wide runs_on: wired on all 11 framework pages (paged subset only — claude-code/opencode/pi), from cited official-support evidence per framework: claude-code+opencode+pi → compound-engineering, superpowers; claude-code+opencode → gsd, addy-agent-skills, gstack, nano-spec; claude-code-only → matt-pocock-skills, openspec, speckit, bmad, bm-skills.
  • runs: extended: sandcastle → claude-code+opencode+pi; warren → claude-code+pi (paged subset of their documented provider lists).
  • Cascade: the 4 enabled patterns’ Provided by (harness) rosters + sources/updated refreshed (opencode on all 4; pi on session-handoff + context-engineering). harness/index.md — 3-member table, 3-column capability matrix, NEW Framework support (runs_on: inverse) matrix (the central home for full documented-support lists incl. unpaged harnesses in plain text), updated patterns-supplied + broader-category. wiki/index.md — 3 harness rows; claude-code.md backlinks now list all 11 frameworks.
  • Unpaged-but-officially-supported harnesses (Codex, Cursor, Copilot, Gemini CLI, Kimi, Windsurf, Qwen, Antigravity, Factory Droid, sapling, …) recorded as plain text in the framework-support matrix + harness/index.md ingest queue, per the Support-scope rule — candidates for future ingest.
  • No stage change (harnesses implement no stage). Stage set unchanged at 8. Harness layer now: 3 pages.
  • Verification: dangling-wikilink check across wiki/ — clean (see below); every runs_on:/runs:/enables: edge target resolves to a page.

[2026-08-02] ingest | Factory Droid harness — the fourth terminal harness, the model-routing pole

  • Source → raw/harness/2026-08-02-factory-droid.md (web-researched capture: docs.factory.ai/cli overview + custom-droids + agents-md + pricing, factory.ai/product/droids).
  • New harness page wiki/harness/factory-droid.md (subtype: terminal, proprietary), enables: all four patterns — fresh-context-subagents (Custom Droids: fresh context + own session + per-droid model, Task tool + run_in_background), edit-guardrails (autonomy levels off/low/medium/high via --auto + read-only review + hooks + approval workflows), session-handoff (own-session subagents + Sessions API + headless droid exec), context-engineering (AGENTS.md standard + skills + 40+ MCP servers + plugins).
  • The distinctive axis: model routing. Where claude-code is Anthropic-only and opencode/pi are “model-agnostic,” Droid makes routing between models first-class — Anthropic/OpenAI/Google/open-weight, mid-session swap, complexity-tiered per-subagent, BYOK, plus a free open-weight Droid Core tier. Second signature: Missions (harness-native multi-agent orchestration; noted runtime-adjacent per the boundary test). Primitive set is otherwise Claude-Code-shaped (Custom Droids/Skills/Hooks/Plugins ≈ 1:1).
  • runs_on: wired on the three individual-author cross-harness frameworks that officially name Factory Droid — compound-engineering, gstack, superpowers (moved from prose-only to stored edges; updated: bumped on all three).
  • Cascade: the 4 enabled patterns’ Provided by (harness) rosters + See-Also harness lines now include factory-droid. harness/index.md — 4-member table, 4-column capability matrix, model-access spectrum prose rewritten, framework-support matrix bolds factory-droid for CE/gstack/superpowers, patterns-supplied bullets + broader-category + ingest-queue updated (Factory Droid removed from queue; count 3→4). wiki/index.md — new factory-droid harness row.
  • No stage added/renamed/retired (a harness implements no stage). Stage set unchanged at 8. Harness layer now: 4 pages.
  • Verification: dangling-wikilink check across wiki/ — clean; every [[factory-droid]] reference resolves to the new page. Remaining unpaged-but-supported harnesses (Codex, Cursor, Copilot, Gemini CLI, Kimi, Windsurf, Qwen, Antigravity, sapling) still recorded as bold plain text per the Support-scope rule.

[2026-08-05] schema | NEW topic overlay layer + first topic (Fowler’s Harness Engineering)

  • Motivation: a recurring user question — how to make agents follow project conventions and refine that over time (rules files, standards docs, ADRs, verifiers, solution corpora, CLAUDE.md). Concluded it is not a new ontology node but a cross-cutting family already decomposed across artifact + pattern + harness; what was missing was (a) connective tissue and (b) a page-type for authored, top-down reference hubs (a “pattern that links patterns” would be a category error, since patterns are minted bottom-up from capability backlinks).
  • CONVENTIONS.md: added the topic layer — an eighth namespace topic/ that is explicitly not one of the seven ontology node types but a curated overlay (Map of Content) sitting above the graph. New section “The topic layer (curated overlays)”: the four-way distinction (index / sdlc-stage / pattern / topic), the overlay rule (topics store no edges, are never evidence, and must not add authored “referenced-by” rosters to targets — Obsidian’s auto-backlink panel is fine), lean frontmatter (type: topic), the discipline (≥3 namespaces, few, hand-maintained), and an authoring note (no stage re-derivation, no backlink cascade). Added a naming-table row (topic-<name>) and an overlay note under the node-types table.
  • New: raw/reference/2026-08-05-fowler-harness-engineering.md (immutable capture of martinfowler.com/articles/harness-engineering.html) + wiki/topic/topic-harness-engineering.md. The topic adopts Fowler’s vocabulary — guides (feedforward) / sensors (feedback) closed by a steering loop; computational vs inferential controls; keep quality left — and threads it through existing wiki pages, while explicitly reconciling Fowler’s broad “harness” ≠ this wiki’s harness node. Flags two concepts the wiki lacks (harnessability / ambient affordances) as a candidate future pattern, and folds in the “as models improve, the authored guide layer thins to the non-derivable kernel” analysis.
  • Light vocab edits (cross-links, not new rosters): pattern-shift-left (“keep quality left”), pattern-plan-verification-loop + pattern-adversarial-review + pattern-evidence-before-claims (framed as sensors; computational-vs-inferential), each with a See-Also to the topic. pattern-context-engineering + pattern-knowledge-compounding See-Also to the topic (guide-delivery / steering-loop).
  • index.md: new ## topic section + intro note. No stage change (a topic implements none).

[2026-08-05] ingest | Agent OS (Builder Methods) — v3 standards/guide-layer framework; 9th specify-cluster member

  • Source → raw/agent-os/2026-08-05-agent-os.md (web-researched capture: buildermethods.com/agent-os sub-pages + github.com/buildermethods/agent-os README/CHANGELOG/git-tree/raw command files). Captured v3.0.0 (released 2026-01-20) — a major refocus: v3 retired v2’s implementation/orchestration commands (create-spec/create-tasks/execute-tasks) and all sub-agents, keeping only the standards + spec-shaping layer. A live example of the “delete the derivable, keep the non-derivable” thesis on topic-harness-engineering.
  • New framework wiki/framework/agent-os.md (runs_on: [[claude-code]]; Cursor/Windsurf/Codex/Antigravity in prose per support-scope). Brian Casel / Builder Methods (also ships bm-skills), MIT, ~5.2K★. Identity: a deliberately non-full-SDLC framework (with bm-skills + nano-spec) whose primary value is the persistent guide layer.
  • 5 capability pages (all subtype: command, no sub-agents in v3): agent-os-discover-standards, agent-os-index-standards, agent-os-inject-standards (the three cross-cutting guide-layer commands — no canonical stage, implements: []); agent-os-plan-product (→ stage-align, product-direction flavor; equivalent_to ce-strategy); agent-os-shape-spec (→ stage-specify, 9th specify-cluster member).
  • 2 new artifacts: artifact-standards (the signature — declarative conventions + index.yml matcher; the advisory/mined counterpart to SpecKit’s gated artifact-constitution) and artifact-product-docs (mission/roadmap/tech-stack; counterpart to CE’s STRATEGY.md).
  • equivalent_to cascade: added [[agent-os-shape-spec]] to all 8 existing specify-cluster members (addy-spec-driven-development, bm-prd-creator, bmad-prd, gstack-spec, mp-to-spec, openspec-propose, speckit-specify, nano-spec-create) + [[agent-os-plan-product]] to ce-strategy (reciprocal).
  • Pattern rosters: Agent OS added to pattern-context-engineering (flagship — inject/index/discover-standards), pattern-knowledge-compounding (standards-compounding via sync-to-profile), pattern-grilling (AskUserQuestion-only interaction), pattern-scale-adaptive-planning, pattern-spec-driven-development. artifact-spec-md gains shape-spec.
  • Stage re-derivation: no add/rename/split/merge/retire — stage set unchanged at 8. stage-align now 10 frameworks (plan-product, product-direction flavor); stage-specify now 9 (shape-spec, uniquely standards-binding). The stage-govern split candidate updated: Agent OS sharpens but does not advance it — its standards are externalized-but-advisory (injected, not gated), landing with CE on the “read as context” side; the gated bar stays at one framework (Spec Kit). Noted the real second cluster is likely “advisory externalized standards” (→ the guide layer).
  • Cascade: runs_on: wired to claude-code; claude-code roster 11 → 12 frameworks (+ page/index/harness-matrix rows). index.md — framework row, 5 capability rows, 2 artifact rows, stage-align/stage-specify + 5 pattern summary rows refreshed.
  • Verification: dangling-wikilink check across wiki/ — see below.