@boyingliu01/xp-gate 0.14.31 → 0.15.0

package/lib/sprint-audit.js

@@ -1,235 +1,235 @@
-/**
- * xp-gate sprint-audit — Layer 2: Final sprint completeness audit.
- *
- * Checks phase_history coverage, time records, artifact records,
- * and state consistency at Phase 6 CLOSE.
- *
- * Usage:
- *   xp-gate sprint-audit [--dir <path>] [--json]
- *
- * Verdict rules:
- *   6/6 completed + 0 errors       → PASS (exit 0)
- *   >= 4/6 completed + 0 errors    → PASS_WITH_WARNINGS (exit 0)
- *   < 4/6 completed or any errors  → FAIL (exit 1)
- *   No sprint-state.json           → SKIP (exit 0)
- *
- * @module sprint-audit
- */
-
-'use strict';
-
-const fs = require('fs');
-const path = require('path');
-const { PHASE_NAMES } = require('./phase-transition');
-
-/**
- * Run the sprint audit.
- * @param {string[]} args - CLI arguments
- * @returns {Promise<number>} Exit code
- */
-async function handleSprintAudit(args = []) {
-  if (args.includes('--help')) {
-    console.log('Usage: xp-gate sprint-audit [options]');
-    console.log('');
-    console.log('Options:');
-    console.log('  --dir <path>   Project directory (default: cwd)');
-    console.log('  --json         Output as JSON instead of human-readable');
-    console.log('');
-    console.log('Runs final sprint completeness audit at Phase 6 CLOSE.');
-    console.log('Checks phase coverage, time records, artifact records,');
-    console.log('and state consistency.');
-    return 0;
-  }
-
-  const dirIdx = args.indexOf('--dir');
-  const projectDir = dirIdx >= 0 ? args[dirIdx + 1] : process.cwd();
-  const jsonFlag = args.includes('--json');
-
-  const stateFile = path.join(projectDir, '.sprint-state', 'sprint-state.json');
-
-  // No sprint-state.json → SKIP
-  if (!fs.existsSync(stateFile)) {
-    if (jsonFlag) {
-      console.log(JSON.stringify({ verdict: 'SKIP', reason: 'No sprint-state.json found' }));
-    } else {
-      console.log('⏭️  No sprint-state.json found — skipping audit.');
-    }
-    return 0;
-  }
-
-  let state;
-  try {
-    state = JSON.parse(fs.readFileSync(stateFile, 'utf8'));
-  } catch (err) {
-    const result = {
-      verdict: 'FAIL',
-      errors: [`Failed to parse sprint-state.json: ${err.message}`],
-    };
-    if (jsonFlag) {
-      console.log(JSON.stringify(result, null, 2));
-    } else {
-      console.error(`❌ ${result.errors[0]}`);
-    }
-    return 1;
-  }
-
-  // ── Run checks ──
-  const warnings = [];
-  const errors = [];
-  const phaseHistory = Array.isArray(state.phase_history) ? state.phase_history : [];
-
-  // Build lookup
-  const historyLookup = {};
-  for (const entry of phaseHistory) {
-    historyLookup[entry.phase] = entry;
-  }
-
-  // Check 1: Phase coverage
-  const completedPhases = [];
-  const missingPhases = [];
-  const incompletePhases = [];
-
-  for (let i = 1; i <= 6; i++) {
-    const entry = historyLookup[i];
-    if (!entry) {
-      missingPhases.push(i);
-    } else if (entry.status === 'completed' || entry.status === 'skipped') {
-      completedPhases.push(i);
-    } else {
-      incompletePhases.push({ phase: i, name: PHASE_NAMES[i] || `Phase ${i}`, status: entry.status });
-    }
-  }
-
-  // Check 2: Time records for completed phases
-  for (const phaseNum of completedPhases) {
-    const entry = historyLookup[phaseNum];
-    if (entry.status === 'completed' && (entry.duration_seconds == null || entry.duration_seconds === 0)) {
-      warnings.push(`Phase ${phaseNum} (${PHASE_NAMES[phaseNum]}) completed but has no duration recorded`);
-    }
-  }
-
-  // Check 3: Artifact records (phase-{N}-summary.md)
-  const outputsDir = path.join(projectDir, '.sprint-state', 'phase-outputs');
-  for (const phaseNum of completedPhases) {
-    if (historyLookup[phaseNum].status === 'completed') {
-      const summaryFile = path.join(outputsDir, `phase-${phaseNum}-summary.md`);
-      if (!fs.existsSync(summaryFile)) {
-        warnings.push(`Phase ${phaseNum} summary missing: .sprint-state/phase-outputs/phase-${phaseNum}-summary.md`);
-      }
-    }
-  }
-
-  // Check 4: State consistency — phase field vs phase_history last entry
-  if (phaseHistory.length > 0) {
-    const lastEntry = phaseHistory[phaseHistory.length - 1];
-    if (state.phase !== undefined && state.phase !== lastEntry.phase) {
-      errors.push(
-        `State inconsistency: sprint-state.phase=${state.phase} but phase_history last entry is phase ${lastEntry.phase}`
-      );
-    }
-  }
-
-  // ── Determine verdict ──
-  const completedCount = completedPhases.length;
-  let verdict;
-  if (errors.length > 0 || completedCount < 4) {
-    verdict = 'FAIL';
-  } else if (completedCount >= 6 && errors.length === 0) {
-    verdict = 'PASS';
-  } else {
-    verdict = 'PASS_WITH_WARNINGS';
-  }
-
-  // ── Build result ──
-  const result = {
-    sprint_id: state.id || 'unknown',
-    branch: state.isolation?.branch || 'unknown',
-    coverage: {
-      completed: completedCount,
-      total: 6,
-      pct: Math.round((completedCount / 6) * 100),
-    },
-    missing_phases: missingPhases.map(p => ({ phase: p, name: PHASE_NAMES[p] || `Phase ${p}` })),
-    incomplete_phases: incompletePhases,
-    warnings,
-    errors,
-    verdict,
-  };
-
-  // ── Persist report (latest overwrites — expected behavior) ──
-  const reportPath = path.join(projectDir, '.sprint-state', 'audit-report.json');
-  try {
-    fs.writeFileSync(reportPath, JSON.stringify(result, null, 2), 'utf8');
-  } catch (err) {
-    // Report write failure is WARNING, not BLOCK
-    warnings.push(`Failed to write audit report: ${err.message}`);
-  }
-
-  // ── Output ──
-  if (jsonFlag) {
-    console.log(JSON.stringify(result, null, 2));
-  } else {
-    printHumanReadable(result, state);
-  }
-
-  // Exit code: FAIL → 1, others → 0
-  return verdict === 'FAIL' ? 1 : 0;
-}
-
-/**
- * Print human-readable audit report.
- * @param {object} result - Audit result object
- * @param {object} state - Sprint state object
- */
-function printHumanReadable(result, state) {
-  const lines = [];
-  lines.push('');
-  lines.push('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
-  lines.push(`  Sprint Audit Report — ${result.sprint_id}`);
-  lines.push('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
-  lines.push('');
-  lines.push(`  Branch: ${result.branch}`);
-  lines.push(`  Phase Coverage: ${result.coverage.completed}/${result.coverage.total} (${result.coverage.pct}%)`);
-  lines.push('');
-  lines.push('  Phase History:');
-
-  for (let i = 1; i <= 6; i++) {
-    const entry = result.incomplete_phases.find(p => p.phase === i);
-    const missing = result.missing_phases.find(p => p.phase === i);
-    const name = (PHASE_NAMES[i] || `Phase ${i}`).padEnd(10);
-
-    if (missing) {
-      lines.push(`  ❌ Phase ${i}/6  ${name} — not recorded`);
-    } else if (entry) {
-      lines.push(`  ⚠️  Phase ${i}/6  ${name} ${entry.status}  ← not yet completed`);
-    } else {
-      lines.push(`  ✅ Phase ${i}/6  ${name} completed`);
-    }
-  }
-
-  if (result.warnings.length > 0) {
-    lines.push('');
-    lines.push('  Warnings:');
-    for (const w of result.warnings) {
-      lines.push(`  ⚠️  ${w}`);
-    }
-  }
-
-  if (result.errors.length > 0) {
-    lines.push('');
-    lines.push('  Errors:');
-    for (const e of result.errors) {
-      lines.push(`  ❌ ${e}`);
-    }
-  }
-
-  lines.push('');
-  const issueCount = result.warnings.length + result.errors.length;
-  lines.push(`  Overall: ${result.warnings.length} warning(s), ${result.errors.length} error(s)`);
-  lines.push(`  Verdict: ${result.verdict}`);
-  lines.push('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
-
-  console.log(lines.join('\n'));
-}
-
-module.exports = { handleSprintAudit };
+/**
+ * xp-gate sprint-audit — Layer 2: Final sprint completeness audit.
+ *
+ * Checks phase_history coverage, time records, artifact records,
+ * and state consistency at Phase 6 CLOSE.
+ *
+ * Usage:
+ *   xp-gate sprint-audit [--dir <path>] [--json]
+ *
+ * Verdict rules:
+ *   6/6 completed + 0 errors       → PASS (exit 0)
+ *   >= 4/6 completed + 0 errors    → PASS_WITH_WARNINGS (exit 0)
+ *   < 4/6 completed or any errors  → FAIL (exit 1)
+ *   No sprint-state.json           → SKIP (exit 0)
+ *
+ * @module sprint-audit
+ */
+
+'use strict';
+
+const fs = require('fs');
+const path = require('path');
+const { PHASE_NAMES } = require('./phase-transition');
+
+/**
+ * Run the sprint audit.
+ * @param {string[]} args - CLI arguments
+ * @returns {Promise<number>} Exit code
+ */
+async function handleSprintAudit(args = []) {
+  if (args.includes('--help')) {
+    console.log('Usage: xp-gate sprint-audit [options]');
+    console.log('');
+    console.log('Options:');
+    console.log('  --dir <path>   Project directory (default: cwd)');
+    console.log('  --json         Output as JSON instead of human-readable');
+    console.log('');
+    console.log('Runs final sprint completeness audit at Phase 6 CLOSE.');
+    console.log('Checks phase coverage, time records, artifact records,');
+    console.log('and state consistency.');
+    return 0;
+  }
+
+  const dirIdx = args.indexOf('--dir');
+  const projectDir = dirIdx >= 0 ? args[dirIdx + 1] : process.cwd();
+  const jsonFlag = args.includes('--json');
+
+  const stateFile = path.join(projectDir, '.sprint-state', 'sprint-state.json');
+
+  // No sprint-state.json → SKIP
+  if (!fs.existsSync(stateFile)) {
+    if (jsonFlag) {
+      console.log(JSON.stringify({ verdict: 'SKIP', reason: 'No sprint-state.json found' }));
+    } else {
+      console.log('⏭️  No sprint-state.json found — skipping audit.');
+    }
+    return 0;
+  }
+
+  let state;
+  try {
+    state = JSON.parse(fs.readFileSync(stateFile, 'utf8'));
+  } catch (err) {
+    const result = {
+      verdict: 'FAIL',
+      errors: [`Failed to parse sprint-state.json: ${err.message}`],
+    };
+    if (jsonFlag) {
+      console.log(JSON.stringify(result, null, 2));
+    } else {
+      console.error(`❌ ${result.errors[0]}`);
+    }
+    return 1;
+  }
+
+  // ── Run checks ──
+  const warnings = [];
+  const errors = [];
+  const phaseHistory = Array.isArray(state.phase_history) ? state.phase_history : [];
+
+  // Build lookup
+  const historyLookup = {};
+  for (const entry of phaseHistory) {
+    historyLookup[entry.phase] = entry;
+  }
+
+  // Check 1: Phase coverage
+  const completedPhases = [];
+  const missingPhases = [];
+  const incompletePhases = [];
+
+  for (let i = 1; i <= 6; i++) {
+    const entry = historyLookup[i];
+    if (!entry) {
+      missingPhases.push(i);
+    } else if (entry.status === 'completed' || entry.status === 'skipped') {
+      completedPhases.push(i);
+    } else {
+      incompletePhases.push({ phase: i, name: PHASE_NAMES[i] || `Phase ${i}`, status: entry.status });
+    }
+  }
+
+  // Check 2: Time records for completed phases
+  for (const phaseNum of completedPhases) {
+    const entry = historyLookup[phaseNum];
+    if (entry.status === 'completed' && (entry.duration_seconds == null || entry.duration_seconds === 0)) {
+      warnings.push(`Phase ${phaseNum} (${PHASE_NAMES[phaseNum]}) completed but has no duration recorded`);
+    }
+  }
+
+  // Check 3: Artifact records (phase-{N}-summary.md)
+  const outputsDir = path.join(projectDir, '.sprint-state', 'phase-outputs');
+  for (const phaseNum of completedPhases) {
+    if (historyLookup[phaseNum].status === 'completed') {
+      const summaryFile = path.join(outputsDir, `phase-${phaseNum}-summary.md`);
+      if (!fs.existsSync(summaryFile)) {
+        warnings.push(`Phase ${phaseNum} summary missing: .sprint-state/phase-outputs/phase-${phaseNum}-summary.md`);
+      }
+    }
+  }
+
+  // Check 4: State consistency — phase field vs phase_history last entry
+  if (phaseHistory.length > 0) {
+    const lastEntry = phaseHistory[phaseHistory.length - 1];
+    if (state.phase !== undefined && state.phase !== lastEntry.phase) {
+      errors.push(
+        `State inconsistency: sprint-state.phase=${state.phase} but phase_history last entry is phase ${lastEntry.phase}`
+      );
+    }
+  }
+
+  // ── Determine verdict ──
+  const completedCount = completedPhases.length;
+  let verdict;
+  if (errors.length > 0 || completedCount < 4) {
+    verdict = 'FAIL';
+  } else if (completedCount >= 6 && errors.length === 0) {
+    verdict = 'PASS';
+  } else {
+    verdict = 'PASS_WITH_WARNINGS';
+  }
+
+  // ── Build result ──
+  const result = {
+    sprint_id: state.id || 'unknown',
+    branch: state.isolation?.branch || 'unknown',
+    coverage: {
+      completed: completedCount,
+      total: 6,
+      pct: Math.round((completedCount / 6) * 100),
+    },
+    missing_phases: missingPhases.map(p => ({ phase: p, name: PHASE_NAMES[p] || `Phase ${p}` })),
+    incomplete_phases: incompletePhases,
+    warnings,
+    errors,
+    verdict,
+  };
+
+  // ── Persist report (latest overwrites — expected behavior) ──
+  const reportPath = path.join(projectDir, '.sprint-state', 'audit-report.json');
+  try {
+    fs.writeFileSync(reportPath, JSON.stringify(result, null, 2), 'utf8');
+  } catch (err) {
+    // Report write failure is WARNING, not BLOCK
+    warnings.push(`Failed to write audit report: ${err.message}`);
+  }
+
+  // ── Output ──
+  if (jsonFlag) {
+    console.log(JSON.stringify(result, null, 2));
+  } else {
+    printHumanReadable(result, state);
+  }
+
+  // Exit code: FAIL → 1, others → 0
+  return verdict === 'FAIL' ? 1 : 0;
+}
+
+/**
+ * Print human-readable audit report.
+ * @param {object} result - Audit result object
+ * @param {object} state - Sprint state object
+ */
+function printHumanReadable(result, state) {
+  const lines = [];
+  lines.push('');
+  lines.push('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
+  lines.push(`  Sprint Audit Report — ${result.sprint_id}`);
+  lines.push('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
+  lines.push('');
+  lines.push(`  Branch: ${result.branch}`);
+  lines.push(`  Phase Coverage: ${result.coverage.completed}/${result.coverage.total} (${result.coverage.pct}%)`);
+  lines.push('');
+  lines.push('  Phase History:');
+
+  for (let i = 1; i <= 6; i++) {
+    const entry = result.incomplete_phases.find(p => p.phase === i);
+    const missing = result.missing_phases.find(p => p.phase === i);
+    const name = (PHASE_NAMES[i] || `Phase ${i}`).padEnd(10);
+
+    if (missing) {
+      lines.push(`  ❌ Phase ${i}/6  ${name} — not recorded`);
+    } else if (entry) {
+      lines.push(`  ⚠️  Phase ${i}/6  ${name} ${entry.status}  ← not yet completed`);
+    } else {
+      lines.push(`  ✅ Phase ${i}/6  ${name} completed`);
+    }
+  }
+
+  if (result.warnings.length > 0) {
+    lines.push('');
+    lines.push('  Warnings:');
+    for (const w of result.warnings) {
+      lines.push(`  ⚠️  ${w}`);
+    }
+  }
+
+  if (result.errors.length > 0) {
+    lines.push('');
+    lines.push('  Errors:');
+    for (const e of result.errors) {
+      lines.push(`  ❌ ${e}`);
+    }
+  }
+
+  lines.push('');
+  const issueCount = result.warnings.length + result.errors.length;
+  lines.push(`  Overall: ${result.warnings.length} warning(s), ${result.errors.length} error(s)`);
+  lines.push(`  Verdict: ${result.verdict}`);
+  lines.push('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
+
+  console.log(lines.join('\n'));
+}
+
+module.exports = { handleSprintAudit };

package/mock-policy/AGENTS.md

@@ -1,9 +1,9 @@
 # SRC/MOCK-POLICY KNOWLEDGE BASE
 
-**Generated:** 2026-07-22
-**Commit:** 18b636a
+**Generated:** 2026-07-23
+**Commit:** 1d581aa
 **Branch:** main
-**Version:** 0.14.31.0
+**Version:** 0.15.0.0
 
 ## OVERVIEW
 Mock layering policy enforcement — Gate M3 of pre-push hook. Ensures integration tests use real implementations for internal dependencies, mock external dependencies, and annotate pending mocks with removal plans. Combines project scope scanning, mock decision engine, and per-file validation into a single pipeline.

package/mutation/AGENTS.md

@@ -1,9 +1,9 @@
 # SRC/MUTATION KNOWLEDGE BASE
 
-**Generated:** 2026-07-22
-**Commit:** 18b636a
+**Generated:** 2026-07-23
+**Commit:** 1d581aa
 **Branch:** main
-**Version:** 0.14.31.0
+**Version:** 0.15.0.0
 
 ## OVERVIEW
 **Gate M** (incremental mutation testing) + **Gate M2** helpers (test-layer detection used by `src/mock-policy/`). Pre-push quality gate. TypeScript-only; uses Stryker.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@boyingliu01/xp-gate",
-  "version": "0.14.31",
+  "version": "0.15.0",
   "description": "AI-driven development workflow: 6 quality gates + Delphi review + Sprint Flow",
   "bin": {
     "xp-gate": "./bin/xp-gate.js"

package/plugins/claude-code/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "xp-gate",
-  "version": "0.14.31",
+  "version": "0.15.0",
   "displayName": "XP-Gate",
   "description": "Extreme Programming quality gates + AI workflow skills for Claude Code. Includes 10 quality gates (Gate 0-9), Sprint Flow (11 phases), and Delphi multi-expert review (>=90% consensus).",
   "author": {

package/plugins/claude-code/skills/delphi-review/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
 
-**Generated:** 2026-07-22
-**Commit:** 18b636a
+**Generated:** 2026-07-23
+**Commit:** 1d581aa
 **Branch:** main
-**Version:** 0.14.31.0
+**Version:** 0.15.0.0
 
 ## OVERVIEW
 Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, 3 experts from ≥2 providers, domestic models only). Supports design + code-walkthrough modes.

package/plugins/claude-code/skills/sprint-flow/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/SPRINT-FLOW KNOWLEDGE BASE
 
-**Generated:** 2026-07-22
-**Commit:** 18b636a
+**Generated:** 2026-07-23
+**Commit:** 1d581aa
 **Branch:** main
-**Version:** 0.14.31.0
+**Version:** 0.15.0.0
 
 ## OVERVIEW
 **6-phase** development pipeline (v2.0 compact redesign, Issue #290): PREP → DESIGN → BUILD → VERIFY → SHIP → CLOSE. Phase 3/6 BUILD default build mode is **ralph-loop** (REQ-level iteration, 40-67% token savings vs parallel). HARD-GATE between DESIGN (2/6) and BUILD (3/6): design must pass Delphi review (≥90% consensus) before any coding.

package/plugins/claude-code/skills/sprint-flow/SKILL.md

@@ -269,6 +269,7 @@ next_phase_context: [key info for next phase]
 | Clean up CLOSE without backing up sprint-state first | `.sprint-state/` is inside worktree; it's lost on worktree removal. CLOSE step 1 MUST back up to repo-tracked path first |
 | Keep adding random changes after verification failures | Max 3 fix cycles; if still failing, BLOCK and request user decision |
 | Enter next phase without generating Phase Summary | Every phase MUST write `.sprint-state/phase-outputs/phase-{N}-summary.md` and pass transition gate |
+| Complete implementation change without running verification | After every file edit/refactor/feature, MUST run `npm test` + `npm run lint` + `npx tsc --noEmit` and record the structured verification event (see `phase-3-build.md` §In-Session Verification) |
 
 ---
 

package/plugins/claude-code/skills/sprint-flow/references/phase-3-build.md

@@ -144,6 +144,77 @@ This enforcement is instructional (LLM follows SKILL.md instructions), not progr
 
 ---
 
+## In-Session Verification (MANDATORY — v0.14.31+)
+
+**Purpose**: Ensure every implementation change is immediately verified and recorded, enabling Better Loop Harness (and other observability tools) to capture normalized change→validation event pairs.
+
+**Problem it solves**: Without explicit in-session verification, Agents may edit files and move on without running tests or linters. This creates unverified changes that are invisible to post-hoc review tools, breaking the traceability chain between "what changed" and "was it validated".
+
+### Mandatory Verification Protocol
+
+After **every** implementation change (file edit, refactor, new feature, bug fix), the Agent MUST execute the following sequence BEFORE claiming the change is complete:
+
+1. **Run tests**: `npm test` or `npx vitest run` (or project-specific test command)
+2. **Run linter**: `npm run lint` or `npx eslint .` (or project-specific lint command)
+3. **Type-check** (TypeScript projects): `npx tsc --noEmit`
+4. **Record the result**: Append a structured verification event (see format below)
+
+### Verification Event Format
+
+Each verification event MUST be recorded as a structured JSON object. Agents should output this to stdout or append to `.sprint-state/phase-outputs/verification-events.jsonl`:
+
+```json
+{
+  "timestamp": "2026-07-22T10:30:00Z",
+  "change": {
+    "type": "edit|refactor|feature|bugfix",
+    "files": ["src/lib/auth.ts", "src/lib/auth.test.ts"],
+    "description": "Implement validateToken() for expired token handling"
+  },
+  "verification": {
+    "tests": { "command": "npx vitest run src/lib/auth.test.ts", "status": "pass|fail", "summary": "4 passed, 0 failed" },
+    "lint": { "command": "npm run lint", "status": "pass|fail|warn", "summary": "0 errors, 2 warnings" },
+    "typecheck": { "command": "npx tsc --noEmit", "status": "pass|fail|skip", "summary": "No type errors" }
+  },
+  "outcome": "verified|failed|partial",
+  "req": "REQ-003"
+}
+```
+
+### Integration with ralph-loop
+
+When using ralph-loop mode (default BUILD strategy), each REQ iteration MUST include verification as the final step before marking the REQ complete:
+
+```
+ralph-loop iteration:
+  1. [TDD-RED] Write failing test
+  2. [TDD-GREEN] Implement minimal code to pass
+  3. [TDD-REFACTOR] Clean up while keeping tests green
+  4. [VERIFY] Run tests + lint + typecheck ← MANDATORY
+  5. [RECORD] Append verification event ← MANDATORY
+  6. Mark REQ complete and continue to next
+```
+
+### Anti-Patterns
+
+| ❌ Error | ✅ Correct |
+|----------|----------|
+| Edit file → claim done → move to next task | Edit file → run tests + lint → record result → claim done |
+| "Tests should pass" (assertion without evidence) | "Tests passed: 4 passed, 0 failed (npx vitest run)" |
+| Run tests only at end of entire BUILD phase | Run tests after every individual change/REQ |
+| Skip type-check because "I didn't touch types" | Always run `tsc --noEmit` on TypeScript projects |
+
+### Harness Integration
+
+Better Loop Harness captures change and verification events by inspecting session history. The structured verification events above serve as the canonical signal that:
+- A change occurred (the `change` field)
+- The change was validated (the `verification` field)
+- The outcome is attributable (the `outcome` field ties result to specific change)
+
+Without these events, the Harness can only infer changes from file diffs and has no verification signal, resulting in lower "改动验证" (Change Verification) dimension scores.
+
+---
+
 ## TDD 强制执行
 
 ### Gate 5a-BLOCK: 新增文件测试强制

package/plugins/claude-code/skills/test-specification-alignment/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
 
-**Generated:** 2026-07-22
-**Commit:** 18b636a
+**Generated:** 2026-07-23
+**Commit:** 1d581aa
 **Branch:** main
-**Version:** 0.14.31.0
+**Version:** 0.15.0.0
 
 ## OVERVIEW
 Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.

package/plugins/opencode/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@boyingliu01/opencode-plugin",
-  "version": "0.14.31",
+  "version": "0.15.0",
   "type": "module",
   "main": "index.ts",
   "description": "XP-Gate quality gates + AI workflow skills + Sprint Flow TUI sidebar for OpenCode",