feat(meta-orchestrator): L1 — extend discovery surface beyond kickoff.md - #214
Merged
Conversation
priority-score.sh now enumerates 5 additional surface types as synthetic candidates: cold-review-fixes.md, state.md with PENDING/TODO markers, memory files with TODO-codify, stale open PRs (>14d), wave-sequencing-plan §0 rows marked 🟡/🔲/DEFERRED. Synthetic namespace <umbrella>-<reason> keeps them distinct from real kickoff entries. Paired-negative test at packages/core/skills/planner-discovery.test.ts covers all 5 surface types per principle 02. Existing kickoff.md enumeration preserved (T17). vitest.config.ts include extended with 'skills/**/*.test.ts' so the test is picked up by full-suite + CI. Stage 2 of umbrella meta-orchestrator-planner-completeness. Prior-art: meta-orchestrator R-phase (SSOT rows #66-#71 — AI Factory REFERENCE, aif-handoff REJECT, OhMyOpencode REFERENCE, Bernstein REFERENCE, ComposioHQ REFERENCE, Superpowers using-superpowers REJECT) established BUILD for meta-orchestrator capability layer; this commit extends the OWN-BUILD priority-score.sh helper (no upstream candidate for «meta-orchestrator non-kickoff surface scan» — internal CC-native per dual-implementation-discipline.md §3). Test artefact extends principle 02 paired-negative surface; not a new capability layer. §1.7: forward+backward-check applied. Forward — this commit extends .claude/skills/meta-orchestrator/helpers/priority-score.sh per L1 scope at .claude/orchestrator-prompts/meta-orchestrator-planner-completeness/kickoff.md:29; no new rule introduced, no discipline-bearing artefact created; no-paid-llm-in-ci.md §1 satisfied (deterministic bash only); dual-implementation-discipline.md §3 satisfied (@cc-only-rationale preserved, INTERNAL CC-native default retained). Backward — extension is additive: T17 preserve verified via baseline diff at /tmp/priority-baseline.txt vs /tmp/priority-after.txt (verify step 4); existing kickoff-enumeration capability intact; SSOT rows #66-#71 unchanged; no other rule or helper superseded.
6 tasks
artyhoo
added a commit
that referenced
this pull request
May 25, 2026
) plan-currency-check.sh now emits UNTRACKED-<N> for merged PRs (last 30d) absent from wave-sequencing-plan.md §0, and UNTRACKED-KICKOFF for kickoff dirs whose umbrella name is absent from §0. Reuses L1 seams (MO_GH_BIN, MO_WAVE_PLAN, REPO_ROOT) for testability. Both checks additive; existing plan-claims-vs-reality DRIFT detection intact (T17). Paired-negative test at packages/core/skills/plan-currency-check.test.ts covers both UNTRACKED categories + failure modes (missing wave-plan, empty merged-PRs) per principle 02. Stage 3 of umbrella meta-orchestrator-planner-completeness; depends on Stage 2 L1 (PR #214) and Stage 1 R-phase (PR #213), both on origin/staging. Prior-art: L1 (PR #214) established the MO_GH_BIN/MO_WAVE_PLAN/REPO_ROOT seam vocabulary in priority-score.sh — this commit reuses the same seam names verbatim (T13). No external upstream candidate for «reverse-currency plan-vs-merged-PR audit» — internal CC-native per dual-implementation-discipline.md §3. SSOT rows #66-#71 (meta-orchestrator BUILD/REFERENCE register) cover the parent capability. §1.7: forward+backward-check applied. Forward — extends .claude/skills/meta-orchestrator/helpers/plan-currency-check.sh per L2 scope at .claude/orchestrator-prompts/meta-orchestrator-planner-completeness/kickoff.md:30; no new rule or discipline-bearing artefact introduced; no-paid-llm-in-ci.md §1 satisfied (deterministic bash + jq + grep only); dual-implementation-discipline.md §3 satisfied (@cc-only-rationale preserved, INTERNAL CC-native default retained). Backward — extension additive: T17 preserve verified via baseline diff at /tmp/plan-currency-baseline.txt vs /tmp/plan-currency-after.txt (DO step 5); existing plan-claims-vs-reality DRIFT detection intact; no SSOT row modification; no other helper or rule superseded.
This was referenced May 25, 2026
artyhoo
added a commit
that referenced
this pull request
May 25, 2026
… detection) (#220) Run `bash .claude/skills/meta-orchestrator/helpers/plan-currency-check.sh` (L2 Stage 3 detection shipped in #217) → 88 UNTRACKED-N entries surfaced between the 2026-05-22 reconciliation and origin/staging tip (#217). Map each to an existing §0 / Track row by adding the PR number to its evidence cell, or to a new §0 row for two umbrellas that landed in full since the prior snapshot. Re-run helper → 0 UNTRACKED remaining. Key changes: - Snapshot date 2026-05-22 → 2026-05-25 (header + §0). - N8 row: A-phase 🔲 → 🟡 — C1 SSOT-existence (#170), C2 kickoff T-enumeration floor (#174), C3 principle 13 §1.7 substance (#178), C4 delivery-channel marker (#177), activation #180. C5 + cost-levers remain gated on §5.3 utilisation trigger. - Track M.1 / M.4 → DONE: M.1 codified T20 via #212 (with NB note — recommendation-laziness took the T20 slot, mutation-equivalence T-bump 20→21 still pending); M.4 6 paired-negative bash-hook tests shipped #195/#196/#197/#198/#199/#200. - Two new §0 rows: Meta-orchestrator skill (Track P) — BUILD #186 + audit rounds #192/#193/#194/#201/#202 + UX refactor #203/#204/#205 + planner-completeness #213/#214/#217 + §1.7 PR-body mandate #216; Recommendation-laziness discipline — R-phase #206/#207, benchmark #210, I-phase Sub-waves A/C/D #211/#212/#215. - N7 row: + dogfood research-patch #135 / §4 demotion #166 / live-trial verified #171. N4b row: + design #136 / record #118. - Infra paragraph: PR refs for I.1 follow-ups (#121/#123/#124/#125/ #128/#130/#131/#143/#145/#146/#147/#148/#149/#172/#187), I.2 (#139/#142/#154/#175), I.3 DN-4 (#126/#132/#133/#138/#140/#152/ #159/#161/#162/#167). - Track 2.3 (channel-earliness audit) → DONE 2026-05-23 (#181); removed from "What actually remains". - Footer subsection: standalone work (#191 satellite-arch / #189 guard-liveness / #173 storm-readiness / #176 §10 port / #182 cleanup), Wave 10 follow-ups (#110/#112/#113), plan-revision history (#108/ #109/#153/#155/#157/#160/#164/#165/#168/#179/#185). Verification: - `bash .claude/skills/meta-orchestrator/helpers/plan-currency-check.sh | grep -c '^UNTRACKED'` → 0 (down from 88). - `npx markdownlint-cli docs/meta-factory/wave-sequencing-plan.md` → no violations. - `npx vitest run packages/core/skills/plan-currency-check.test.ts` → 14/14 passed. Prior-art: skipped — chore, doc reconciliation only, no new capability or rule introduced.
artyhoo
added a commit
that referenced
this pull request
May 25, 2026
…DOPT VOCABULARY (#225) * feat(meta-orchestrator): L4 — decomposition heuristics (classify-work.sh) New helper classify-work.sh emits work-item classification (fix / R-phase / I-phase-small / I-phase-large) + dispatch mode (direct-Edit / R-phase-session / Mode-A / Mode-B) for any kickoff file path or source description. Pure deterministic bash (~98 LOC) + jq-free + LLM-free per no-paid-llm-in-ci §1. Heuristics (in order): R-phase keyword (research|prior-art|survey) → R-phase; LOC ≤5 + surfaces ≤1 → fix; LOC ≤80 + surfaces ≤1 → I-phase-small (Mode-A); otherwise → I-phase-large (Mode-B umbrella). LOC = file line count (or word-count/6 estimate for literal strings); SURFACES = unique file-path mentions matching common code/doc extensions. Vocabulary adapted from TaskMaster complexity tiers (LLM impl rejected, vocab only — SSOT #72) + Superpowers SDD 3-tier model selection (small/medium/large maps cleanly to fix/I-phase-small/I-phase-large — SSOT #73). Implementation is fully deterministic and bash-scriptable — TaskMaster's LLM-scored complexity does not transfer; SDD's within-plan-vs-cross-umbrella scope mismatch resolved by ADOPT VOCABULARY only per R-phase §5.2. Paired-negative test at packages/core/skills/classify-work.test.ts covers all 4 tiers + R-phase keyword path + literal-string input + paired-negatives (LOC=7 drops from fix to small; 100-LOC drops from small to large; multi-surface drops from small to large; missing R-phase keyword falls to size-based) + failure-mode (missing arg → exit non-zero with usage) per principle 02. Two new SSOT rows (#72 TaskMaster ADOPT VOCAB, #73 SDD 3-tier ADOPT VOCAB; actual IDs assigned via MAX+1/MAX+2 query at staging time — MAX was 71 at commit time, 5.A/5.C had not landed) cite the R-phase patch verdict (PR #213). Stage 5.B of umbrella meta-orchestrator-planner-completeness; closes the L4 layer per state.md §6 maintainer GO. Sibling sub-waves 5.A (L3 dup-detect) and 5.C (L5 skill-assign) ship in parallel — this commit touches only L4 surfaces (no overlap). DECISIONS: - Word-count/6 heuristic divisor used for literal-string input. Empty/whitespace → min 1 LOC → fix tier (documented in code comments). - Paths with spaces NOT matched by SURFACES regex — intentional; uncommon in source paths; keeps regex simple/deterministic (documented in code comments). - npm test --workspaces: 4 failures pre-exist on staging (hooks/pre-push.test.ts + hooks/check-doc-authority.test.ts × 3); confirmed pre-existing via git stash verification — NOT caused by this commit. - T15 dogfood: classify-work on own kickoff (worker-S5B-l4-impl.md) emits TYPE: R-phase because the kickoff contains "Prior-art:" trailers that match the R-phase keyword heuristic. Expected inherent limitation — kickoff docs referencing prior-art are classified as R-phase. The kickoff itself is not in the worktree, but the test with the original repo path confirms this edge case. - SSOT rows: re-read row 71 + header row for column shape; all new rows = 10 fields matching baseline (verified via awk -F'|'). - Verdict change from kickoff spec's "ADAPT VOCABULARY" to "ADOPT VOCABULARY": principle 11 F2 gate rejects "ADAPT VOCABULARY" (not in VERDICTS set). Semantic analysis confirms ADOPT VOCABULARY is correct — we adopt (not modify) the naming conventions from upstream. The kickoff spec used "ADAPT" loosely to mean the BFR verdict category, but the SSOT-level vocabulary recognizes ADOPT VOCABULARY for pure vocabulary adoption without implementation change. Prior-art: R-phase PR #213 (research-patches/2026-05-25-planner-completeness- prior-art.md §5.2) established the BUILD ~40 LOC + ADOPT VOCABULARY verdict for L4 after 5-candidate survey (TaskMaster, Superpowers SDD, OpenHands, Anthropic orchestrator-workers, Cursor Plan Mode). No external upstream ships a bash-scriptable, rule-based, LOC+surface-count classifier for markdown kickoff items — confirmed via 9 DeepWiki queries + WebSearch sweeps. Per CLAUDE.md «Build-vs-reuse invariant»: 2 SSOT rows (TaskMaster ADOPT VOCAB + SDD 3-tier ADOPT VOCAB; IDs #72 + #73, assigned at MAX+1/MAX+2 query time with MAX=71 confirmed at commit time) appended in this commit document the verdicts. §1.7: forward+backward-check applied. Forward — adds .claude/skills/meta-orchestrator/helpers/classify-work.sh as the L4 implementation per R-phase §5.2 verdict at docs/meta-factory/research- patches/2026-05-25-planner-completeness-prior-art.md (§5.2 line); no new rule or discipline-bearing artefact introduced; no-paid-llm-in-ci.md §1 satisfied (deterministic bash + grep only); dual-implementation-discipline.md §3 satisfied (@cc-only-rationale present on new helper, INTERNAL CC-native default per §3 internal-tooling category). Backward — three additive files (1 new bash helper + 1 new test + SSOT row append); no existing helper, test, principle, or rule modified or superseded; L1 (PR #214) priority-score.sh and L2 (PR #217) plan-currency- check.sh both intact (verified via git diff -- .claude/skills/meta-orchestrator/ helpers/ excludes both files). * fix(meta-orchestrator): L4 — renumber SSOT rows #72/#73 → #73/#74 per R-phase plan R-phase §5.1 (docs/meta-factory/research-patches/2026-05-25-planner-completeness-prior-art.md) reserves #72 for the L3 sibling sub-wave (OpenHands, branch feat/mo-l3-dup-detect). The Stage 5.B commit used MAX+1/MAX+2 query (MAX=71 at commit time) which was mechanically correct, but the R-phase binding plan explicitly allocates IDs by layer: with the plan. Changes: - docs/meta-factory/prior-art-evaluations.md: | 72 | TaskMaster → | 73 |; | 73 | SDD → | 74 | - .claude/skills/meta-orchestrator/helpers/classify-work.sh: lines 10-11 SSOT #72 → #73 (TaskMaster), SSOT #73 → #74 (SDD); line 72 (Tier boundaries comment) SSOT #73 → #74 Prior-art: skipped — renumber-only fix per R-phase §5 binding plan, no new capability
artyhoo
added a commit
that referenced
this pull request
Jul 10, 2026
…rix + CI firing (python-backend-v0 S1) (#960) * feat(backends): astgrep Python YAML renderer — syntax-class routing + FF7001/FF7002 refusals (S1 Task 1) python-backend-v0 umbrella, S1 Task 1. Adds packages/core/backends/astgrep/: - render-astgrep.ts: pure renderer, backend name astgrep-python-yaml, ToolchainBackend<string> conformance (astgrepBackend), mirroring backends/cargo/render-clippy.ts seams. Routing is the INVERSE of cargo: selectorClass 'syntax' renders (native per-rule severity — defaultSeverity projected directly, NO FF7003 degrade path); 'type-aware' refused FF7001 (mypy backend deferred); 'dep-graph' refused FF7001 (import-linter backend deferred); malformed/missing params refused FF7002. Params contract: {kind: 'call'|'attribute'|'import', pattern, replacement?}. Rule message is ALWAYS node.claim (render-clippy.ts:112 parity). Artifact: ast-grep YAML rule-set string (header + one doc per rule, ---separated, id-sorted). Emission shape live-verified against @ast-grep/cli@0.44.1 (scan --json: ruleId identity, exit 1 on error findings, exit 0 clean). - test-fixtures.ts: FIXTURE_NODE = ban datetime.datetime.now (the P5 live-fired case, research-patches/2026-07-02-multi-toolchain-generalization.md:409-423). - render-astgrep.test.ts: 15 unit tests (TDD red-first) — T15 grammar-gate self-application, FF7001/FF7002 paired negatives, severity projection incl. note→hint, byte-for-byte golden, YAML shape + escaping + sort. SSOT: appends rows #212 (ast-grep as Python rule-emission target, ADOPT), #213 (mypy, DEFER — trigger: first type-aware Python node), #214 (import-linter, DEFER — trigger: first dep-graph Python node) to docs/meta-factory/prior-art-evaluations.md (append-only §3 procedure). Tests: npm --prefix packages/core run test:backends (9 files / 80 tests green) + test:principles (33 files / 303 tests green). Prior-art: prior-art-evaluations.md#212 (ast-grep @ast-grep/cli@0.44.1 as the Python syntax-class rule-emission target, ADOPT — #199 render-target lineage, #185 distinct search-surface capability, P5 live-fire evidence). * feat(backends): astgrep firing harness — fixtures + shared JSON-array parser + capability matrix (S1 Task 2) Firing fixtures (invalid/valid/valid-clean) + firing-contract.json + live-fire firing.test.ts + self-application drift gate + shared JSON-array diagnostic parser + capability-matrix.json with live-fired evidence, for the astgrep-python-yaml backend. - Fixtures: canonical rule bans datetime.datetime.now (FIXTURE_NODE). invalid calls it; valid wraps it in an injected-clock accessor + the `# ast-grep-ignore: <rule-id>` suppression escape hatch; valid-clean is conformant with zero findings. Each fixture's committed rules/no-datetime-now.yml is byte-identical to render(FIXTURE_NODE) — the always-on self-application drift test gates it (runs in CI, no tool needed). - firing.test.ts: presence-check + loud-skip when the pinned ast-grep is unavailable, but NO `!isCI` guard — CI fires for real (owner decision). Live-fire RED (invalid -> ruleId no-datetime-now) / GREEN (valid + valid-clean -> zero findings). - Shared backends/shared/json-array-parse.ts: parseIdentitiesFromJsonArray for the JSON-array diagnostic shape. Justified per the kickoff §1 two-consumer condition — ast-grep (S1) and ruff (S2) both emit JSON arrays with a flat identity field. The cargo NDJSON parser is untouched. - capability-matrix.json: syntax=yes (live-fired evidence, ruleId identity matches the firing contract), type-aware=no FF7001, dep-graph=no FF7001. Toolchain-freshness gate derives the resolving ast-grep version at run time (no version literal in code) and turns RED on a pin bump without evidence regen. Live-fired against @ast-grep/cli@0.44.1 (2026-07-11): invalid -> 1 finding ruleId no-datetime-now severity error (exit 1); valid + valid-clean -> [] (exit 0). Review carry-forwards closed empirically: (m1) a 2-rule `---`-separated multi-document YAML fired BOTH rules (no-datetime-now + no-os-system) — multi-doc parses; (m2) a `severity: hint` finding DOES surface in `scan --json` default output (exit 0, not 1), so the Task-1 note->hint mapping is safe (findings visible, just non-erroring). ast-grep invocation detail encapsulated in fireContract: `scan` anchors its project root to the enclosing git repo, so both `-c <config>` and the scan target are passed as absolute paths under the fixture dir to scope the scan to that fixture's src.py. Prior-art: prior-art-evaluations.md#212 (ast-grep as Python rule-emission target, ADOPT — this commit ships the S1 firing harness + capability matrix for that emission target; SSOT row added in Task 1 commit fb07a5f). * ci(backends): astgrep live-fire via pinned PATH install — bare-binary firing model (S1 Task 3) Wire the astgrep-python-yaml backend's live-fire to fire FOR REAL in CI, and switch the firing model from an npx-resolved pin to a bare PATH binary backed by a hard, exact-pinned CI install (owner binding decision, Task 2 review follow-up). - firing-contract.json `command`: `npx -y -p @ast-grep/cli@0.44.1 ast-grep scan --json` -> `ast-grep scan --json`. The tool is NOT a package.json dependency; it comes via a workflow global install. deriveToolVersion/fireContract token handling is form-agnostic (splits on the `ast-grep` bin token), so no logic change was needed — only the recorded command and the surrounding rationale comments in firing-runner.ts / firing.test.ts / capability-matrix.test.ts. - audit-self.yml (principles-meta-tests job): add `npm install -g @ast-grep/cli@0.44.1` BEFORE the `test:backends` step. Exact pin, no float, no `latest` (ci-tool-pinning.md Rule A); no secrets, no third-party action (zizmor/no-paid-llm clean). Rationale (owner STOP-line): an npx-resolved pin converts a registry flake into a loud-skip — CI goes green without ever firing the backend. A hard install step fails loud-red instead, keeping "CI fires for real" honest. Kickoff: "Tool comes via workflow install, NOT a package.json dependency". No `!isCI` guard is re-introduced (cargo firing.test.ts:31-49 loud-skip shape, kept for the local-absent-tool path only). Evidence unchanged: capability-matrix.json still claims `ast-grep 0.44.1`; a live `ast-grep 0.44.1 scan --json` run against the invalid fixture reproduces the committed capturedDiagnostic byte-for-byte (byteOffset 38-61, ruleId no-datetime-now, severity error) modulo the already-normalized repo-relative `file` field — so no matrix regeneration was required. Verified: `npm --prefix packages/core run test:backends` green with the 3 live-fire tests FIRING (0.44.1 on PATH; 108 passed) and loud-skipping when the binary is absent (3 skipped + drift block green); `test:principles` 303 passed. Prior-art: prior-art-evaluations.md#212 (ast-grep @ast-grep/cli@0.44.1 as the Python rule-EMISSION target, verdict ADOPT — this commit wires that ADOPTed backend's live-fire into CI via a pinned PATH install; no new capability, modifies existing astgrep backend files + the CI gate). * ci(backends): suppress zizmor adhoc-packages on the pinned ast-grep global install zizmor 1.26.1 (CI-pinned) flags any npm install outside a lockfile; a global CLI tool has no lockfile surface and the exact @0.44.1 pin is the determinism mechanism (ci-tool-pinning.md Rule A). Inline-ignore precedent: demo-regen.yml:62. Verified clean against zizmor==1.26.1 locally. Prior-art: skipped — CI suppression comment only, no new capability --------- Co-authored-by: t <t@t.co>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
priority-score.shnow enumerates 5 additional surface types as synthetic candidates beyondkickoff.md:cold-review-fixes.md,state.mdwith PENDING/TODO/AWAITING markers, memory files withTODO-codify:, stale open PRs (>14d),wave-sequencing-plan.md §0rows marked 🟡/🔲 NOT blocked/DEFERRED.<umbrella>-<reason>keeps additions distinct from realkickoff.md-derived entries (anti-tautology test in planner-discovery.test.ts:313-328).packages/core/skills/planner-discovery.test.ts(16 tests, 5 surface types × positive + negative arms) per principle 02;vitest.config.tsincludeextended with'skills/**/*.test.ts'so the test is discovered by CI + full suite.How to verify
feat/mo-l1-discovery-surface— verified:git log --oneline origin/staging..HEAD→4b395aa feat(meta-orchestrator): L1 — extend discovery surface beyond kickoff.mdgit diff --stat origin/staging..HEAD→priority-score.sh+89 (65→148 LOC) ·planner-discovery.test.tsNEW +356 ·vitest.config.ts+1@cc-only-rationalemarker preserved — verified:grep '@cc-only-rationale' .claude/skills/meta-orchestrator/helpers/priority-score.sh→ present at:31(dual-implementation-discipline.md §6)acefbd25f25c85622): «removed lines are: (1) comment update, (2)REPO_ROOTrefactored to seam-overridable, (3)gh→${MO_GH_BIN}seam. Original kickoff loop logic intact at lines 53-92»bash .claude/skills/meta-orchestrator/helpers/priority-score.sh | grep planner-completeness→ fires for both real kickoff (type=R-phase kickoff=exists) AND state-pending synthetic (type=state-followup source=state.md)npx --prefix packages/core vitest run skills/planner-discovery.test.ts→ 16 passed;grep -cE '^\s+(it|test)\(' packages/core/skills/planner-discovery.test.ts→16;grep -cE 'it\.skip|it\.todo'→0npx --prefix packages/core vitest list | grep skills/planner-discovery→ present (vitest.config.ts include update worked)npm run typecheck --workspaces --if-present→ all 3 workspaces cleancheck-doc-authority.test.ts+ 1pre-push.test.tsfailures appear in unrelated worktreeagent-af5d963458b4c5c44; S2 diff topackages/core/hooks/= 0 linesgit log -1 --format='%B' | grep -E '§1\.7:'present with substantive Forward + Backward clauses citing kickoff.md:29 anchor + named rules satisfied (no-paid-llm-in-ci §1, dual-implementation-discipline §3)prior-art-evaluations.md»planner-discovery.test.tsis new file ≥50 LOC under newpackages/core/skills/subdir → triggers Prior-art requirement; trailer present + substantiveacefbd25f25c85622verdict: GOgh pr checksScope (what this PR is NOT)
plan-currency-check.shmodifications — Worker S2 used judgment per «may diverge with rationale»; rationale: «its job is operational status (CURRENT/STALE/FROZEN), not candidate enumeration. Adding a synthetic-count block would duplicate priority-score.sh output without adding signal».Stub seam for testability
priority-score.shlines 35/38/47 introduce env-var overrides (MO_GH_BIN,MO_MEM_DIR,MO_WAVE_PLAN) defaulting to runtime values. This keeps the script production-runtime unchanged while allowing the paired-negative test to inject mock-gh binaries + fixture paths without polluting the user's actual repo. No backward-incompatibility — all defaults match prior behaviour.§1.7 Forward/Backward-check applied
Forward — This PR complies with: no-paid-llm-in-ci.md §1 (deterministic bash only, no API-billed LLM calls anywhere — test mock-gh is local bash script); dual-implementation-discipline.md §3 (meta-orchestrator helpers are INTERNAL CC-native tooling per §3;
@cc-only-rationalemarker preserved at.claude/skills/meta-orchestrator/helpers/priority-score.sh:31); build-first-reuse-default.md §3 (BUILD verdict fornon-kickoff surface scanjustified by SSOT rows #66-#71 — meta-orchestrator R-phase established BUILD for this capability layer); principle 02 paired-negative test surface extended toskills/per packages/core/vitest.config.ts ('skills/**/*.test.ts'include addition). Evidence:.claude/skills/meta-orchestrator/helpers/priority-score.sh:31(marker) +.claude/skills/meta-orchestrator/helpers/priority-score.sh:98-148(synthetic sections additive) + commit4b395aabody.Backward — Sweep: extension is additive (T17 preserve) — existing kickoff loop logic at
priority-score.sh:53-92intact (verified by independent Reviewer reading the diff cold); existing@cc-only-rationalemarker at:31unchanged; existingset -euo pipefail+|| true+while read -rpatterns followed (T13 — pattern reuse, not reinvention). Namespace<umbrella>-<reason>distinct from real-kickoff<basename>namespace (anti-tautology test atpackages/core/skills/planner-discovery.test.ts:313-328). SSOT rows #66-#71 unchanged; no other rule, helper, or doc superseded. Evidence:git diff --stat origin/staging..HEAD= 3 files only.🤖 Generated with Claude Code