@dzhechkov/skills-feature-adr 1.3.46 → 1.3.47

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@dzhechkov/skills-feature-adr",
-  "version": "1.3.46",
+  "version": "1.3.47",
   "description": "Adaptive Feature Development skill pack for Claude Code — 11-step pipeline with Complexity Router (S/M/L/XL), ADR-driven architecture, 15 agentic-qe skills, multi-agent fleet QE. Supports --full-qe, --full-qe-extended, --with-learning, and --knowledge-extractor modes.",
   "bin": {
     "skills-feature-adr": "./bin/cli.js"

package/templates/.claude/workflows/feature-adr.js

@@ -261,6 +261,15 @@ function needsCodeLandedBarrier(coderUsed) {
   return coderUsed === 'codex' || coderUsed === 'codex-fallback'
 }
 
+// Step-8 claim-gate (inlined byte-equivalent of harness-core/src/feature-adr-claim-gate.ts:step8ClaimGate;
+// the drift test asserts this body matches the module). Folds the claim-check counts the QE agent
+// reported into an ADDITIVE result field + a note. Advisory only — never changes the grade. Absent
+// counts yield an honest not-run note, never a fabricated zero-findings pass.
+function step8ClaimGate(counts) {
+  if (!counts) return { claimCheck: null, note: 'claim-check: not run (no counts reported)' }
+  return { claimCheck: counts, note: counts.findings + ' finding(s) (' + counts.high + ' high) in 08_qe_report.md' }
+}
+
 function normalizeCodeLandingPath(path) {
   let p = String(path || '').trim().replace(/\\/g, '/')
   while (p.indexOf('./') === 0) p = p.slice(2)
@@ -385,7 +394,7 @@ async function designStage(promptText, opts, artifactPath, baseLabel) {
 
 const ROUTER = { type: 'object', additionalProperties: false, required: ['tier', 'activeSteps', 'rationale'], properties: { tier: { type: 'string', enum: ['S', 'M', 'L', 'XL'] }, activeSteps: { type: 'array', items: { type: 'number' } }, rationale: { type: 'string' } } }
 const ARTIFACT = { type: 'object', additionalProperties: false, required: ['wrote', 'summary'], properties: { wrote: { type: 'array', items: { type: 'string' } }, summary: { type: 'string' } } }
-const QE = { type: 'object', additionalProperties: false, required: ['grade', 'gaps', 'codeTestsAdequate', 'docTestsPresent'], properties: { grade: { type: 'string' }, codeTestsAdequate: { type: 'boolean' }, docTestsPresent: { type: 'boolean' }, gaps: { type: 'array', items: { type: 'object', additionalProperties: false, required: ['sev', 'what'], properties: { sev: { type: 'string' }, what: { type: 'string' } } } } } }
+const QE = { type: 'object', additionalProperties: false, required: ['grade', 'gaps', 'codeTestsAdequate', 'docTestsPresent'], properties: { grade: { type: 'string' }, codeTestsAdequate: { type: 'boolean' }, docTestsPresent: { type: 'boolean' }, gaps: { type: 'array', items: { type: 'object', additionalProperties: false, required: ['sev', 'what'], properties: { sev: { type: 'string' }, what: { type: 'string' } } } }, claimCheck: { type: 'object', additionalProperties: false, properties: { findings: { type: 'number' }, high: { type: 'number' }, medium: { type: 'number' } } } } }
 const ADR_TEMPLATE_GUIDE = 'ADR best-practices for Step 3: emit exactly one decision per ADR with the invariant core Title, Status, Context, Decision, Consequences. Template weight is tier-routed: S/M use Nygard/ITD-lightweight form but still include decision drivers, considered options, rationale, consequences, and Confirmation; L/XL use MADR structure plus an NHS Wales Confirmation stanza. Confirmation MUST name verification method, monitoring, success metric, and owner, and its load-bearing safety property MUST be tied to a Step-8 automated test/fitness function. Use status vocabulary proposed/accepted/rejected/deprecated/superseded plus a reversibility clause. Context must be neutral and appear before Decision. Considered Options must include rejected options with symmetric pros/cons. Rationale points must map to stated drivers and explain why losers were rejected. Consequences must include positive and negative outcomes/accepted downsides, follow-up ADR links, an after-action review schedule, and supersession discipline: supersession mints a new ADR and never edits accepted/rejected ADR content in place. Decision must be concrete/testable with exact names, versions, formats, paths, commands, or APIs. Reject explainer-masquerading-as-ADR: a domain overview with no concrete Decision is not an ADR. File names under 03_adr MUST be sequential NNN-{decision-slug}.md with lowercase kebab-case, dateless, ticketless slugs (the auto-001 ADR tracks the feature slug, so the present-tense imperative signal lives in the ADR Title; model-named additional ADRs use imperative slugs). Add a ## Links traceability block (requirements, driving use case, related ADRs) and a one-line provenance note (model-generated, edited for clarity); for a long ADR include a top-of-file table of contents.'
 const ADR_FITNESS_CHECKLIST = 'ADR fitness checklist for Step 8: read every ' + FDIR + '/03_adr/NNN-*.md ADR and fail the QE gate for any miss. Required checks: (1) filename is 03_adr/NNN-{decision-slug}.md where the slug is lowercase kebab-case, imperative, dateless, and ticketless; (2) title is decision-shaped and the ADR records one decision only; (3) Status is non-empty controlled vocabulary proposed/accepted/rejected/deprecated/superseded and includes a reversibility/revisit clause; (4) Context is neutral, problem-first, and appears before Decision; (5) Decision Drivers are stated and ranked/weighted; (6) Considered Options include the chosen and rejected options, each with symmetric pros and cons; (7) Rationale maps each point back to a driver and explains why rejected options lost; (8) Decision is concrete/testable with exact names, versions, formats, paths, commands, or APIs; (9) Consequences include positive and negative outcomes/accepted downsides, follow-up ADR links, and an after-action review schedule; (10) Confirmation names verification method, monitoring, success metric, and owner, then links the load-bearing safety property to an automated test/fitness function; (11) no placeholder text, template hints, raw generation scaffolding, or fake Markdown structure; (12) reject explainer-masquerading-as-ADR: describing a space with no concrete Decision is a blocker; (13) a Related/Links traceability block maps the ADR to its requirements, driving use case, and related ADRs. The ADR Confirmation check is load-bearing: assert the named safety property has a real test by file/name; if absent, grade no better than C and record a blocker gap.'
 
@@ -532,7 +541,7 @@ if (needsCodeLandedBarrier(coderUsed)) {
 // Step 8: QE (brutal-honesty, agentic-qe) + MANDATORY teach
 phase('QE')
 await usageProbe('QE')
-const qePrompt = 'Step 8 (QE - brutal-honesty review, agentic-qe) of /feature-adr for "' + DESC + '" (' + SLUG + '). Adversarially review the SHIPPED code (read it): correctness, edge cases, error handling, and the LOAD-BEARING property the ADR named (ASSERT it has a test - the recurring lesson). Run this ADR gate before final grading: ' + ADR_FITNESS_CHECKLIST + ' Grade A/B/C/D honestly. Assess code-test adequacy + doc-test presence. List CONFIRMED gaps with severity. Write ' + FDIR + '/08_qe_report.md with an ADR Fitness Checklist section showing PASS/FAIL per ADR and evidence for the Confirmation-linked test. MANDATORY SELF-LEARNING STORE (close the loop, never skip): compare every candidate lesson against the Step-0 recalled LEARNED patterns above. Teach ONLY lessons NOT covered by Step-0 recall. On overlap, run `dz teach --reinforce "<recalled pattern id or exact text>" --project ' + BRAIN + '` instead of minting a near-duplicate; if --reinforce is unavailable, skip the duplicate teach and report `reinforced existing pattern <id>` in the QE report. Store every genuinely new lesson in the CANONICAL BRAIN store at `' + BRAIN + '` so it is NOT lost to a target repo you may have cd`d into. Via Bash run EXACTLY `' + DZ_TEACH('<a durable reusable lesson from this feature - a rule/pattern/pitfall, NOT a checkpoint echo>', '<0.7-0.95>', '<area>') + '` for each genuine NEW lesson (1-3 max, high-signal) — the `cd ' + BRAIN + ' &&` prefix + `--project ' + BRAIN + '` pin guarantee the lesson lands in the brain regardless of your CWD. Then run `' + DZ + ' statusline --fa-record --slug ' + SLUG + ' --step "Step 8 QE" --recalled 3 --stored <count taught> --reinforced <count reinforced> --mode ' + MODE + ' --project ' + REPO + '` (run it verbatim via Bash, do not skip). Do NOT teach trivia or invent gaps. Return {grade, gaps, codeTestsAdequate, docTestsPresent}.' + landedNote
+const qePrompt = 'Step 8 (QE - brutal-honesty review, agentic-qe) of /feature-adr for "' + DESC + '" (' + SLUG + '). Adversarially review the SHIPPED code (read it): correctness, edge cases, error handling, and the LOAD-BEARING property the ADR named (ASSERT it has a test - the recurring lesson). Run this ADR gate before final grading: ' + ADR_FITNESS_CHECKLIST + ' Grade A/B/C/D honestly. Assess code-test adequacy + doc-test presence. List CONFIRMED gaps with severity. Write ' + FDIR + '/08_qe_report.md with an ADR Fitness Checklist section showing PASS/FAIL per ADR and evidence for the Confirmation-linked test. MANDATORY SELF-LEARNING STORE (close the loop, never skip): compare every candidate lesson against the Step-0 recalled LEARNED patterns above. Teach ONLY lessons NOT covered by Step-0 recall. On overlap, run `dz teach --reinforce "<recalled pattern id or exact text>" --project ' + BRAIN + '` instead of minting a near-duplicate; if --reinforce is unavailable, skip the duplicate teach and report `reinforced existing pattern <id>` in the QE report. Store every genuinely new lesson in the CANONICAL BRAIN store at `' + BRAIN + '` so it is NOT lost to a target repo you may have cd`d into. Via Bash run EXACTLY `' + DZ_TEACH('<a durable reusable lesson from this feature - a rule/pattern/pitfall, NOT a checkpoint echo>', '<0.7-0.95>', '<area>') + '` for each genuine NEW lesson (1-3 max, high-signal) — the `cd ' + BRAIN + ' &&` prefix + `--project ' + BRAIN + '` pin guarantee the lesson lands in the brain regardless of your CWD. Then run `' + DZ + ' statusline --fa-record --slug ' + SLUG + ' --step "Step 8 QE" --recalled 3 --stored <count taught> --reinforced <count reinforced> --mode ' + MODE + ' --project ' + REPO + '` (run it verbatim via Bash, do not skip). Do NOT teach trivia or invent gaps. AUTHORING-TIME CLAIM-CHECK (Deliverable of claim-check-authoring-time): after writing ' + FDIR + '/08_qe_report.md, run EXACTLY `dz claim-check ' + FDIR + '/08_qe_report.md --json --fail-on none` via Bash, parse the {ok, findings, scanned} JSON, and report claimCheck: {findings: N, high: N, medium: N} (counts by severity) in your return object. TAG EVERY QUANTITATIVE CLAIM you write in the report using the convention the checker recognizes as honest — write "1131 tests pass (MEASURED — `npx vitest run`)", never a bare "1131 tests pass" — and where you QUOTE a forbidden phrase as an example (e.g. the retracted "100% passing" framing), backtick the literal so it reads as code, not an assertion, so your own compliant report scans clean. Return {grade, gaps, codeTestsAdequate, docTestsPresent, claimCheck}.' + landedNote
 // CROSS-MODEL QE (load-bearing): resolveStageModel('qe') derives the OTHER family than the resolved
 // coder when args.models.qe is unset (coder-codex ⇒ opus; coder-Claude ⇒ codex, or opus if codex absent).
 // An explicit args.models.qe wins. A Claude qe spec is merged onto the qe-code-reviewer base (role
@@ -568,6 +577,10 @@ if (qe === null && qeIsCodex) {
   if (qe) { qeReviewerUsed = 'claude'; modelsUsed.qe = modelLabel(qeBeltOpts) }
 }
 
+// Step 8 claim-gate: fold the QE agent's reported claim-check counts into an additive result field.
+const claimGate = step8ClaimGate(qe && qe.claimCheck ? qe.claimCheck : null)
+log(claimGate.note)
+
 // Step 9: Fleet QE (L/XL)
 let fleet = 'skipped (S/M)'
 if (isLplus) {
@@ -605,5 +618,6 @@ return {
   usageThreshold: USAGE_THRESHOLD,
   selfLearning: 'recall@Step0 + teach@Step8 (mandatory)',
   brain: BRAIN,
+  claimGate: claimGate,
   promiseTags: tags,
 }