@boyingliu01/xp-gate 0.34.1 → 0.35.1

package/lib/doctor.js

@@ -80,6 +80,38 @@ const EXEC_TIMEOUT_MS = 1500;
  */
 const GLOBAL_DIAGNOSIS_TIMEOUT_MS = 10000;
 
+/**
+ * Merge a timed-out partial diagnosis into one honest verdict (#629).
+ *
+ * `doctor`'s global timeout (#348) exists so the command never hangs, but the
+ * original handler threw away the entire `diagnoseAsync()` result and substituted
+ * a single placeholder check. Against an identical healthy install that made the
+ * SAME command print "All checks passed" or "Timed out after 10s" depending on
+ * machine load, and a timed-out run reported 0 installed skills — doctor giving
+ * LESS information the LONGER it runs is the opposite of a diagnostic.
+ *
+ * Keeps every completed check, adds ONE Diagnosis notice naming what did not
+ * report, and never lets a partial run read as clean (#495).
+ *
+ * @param {{checks?: Array, issues?: number}} partial checks finished before the deadline
+ * @param {string[]} pending names of surfaces that did not report in time
+ */
+function mergeTimedOutDiagnosis(partial, pending) {
+  const completed = (partial && Array.isArray(partial.checks)) ? partial.checks : [];
+  const inherited = (partial && Number.isFinite(partial.issues)) ? partial.issues : 0;
+  const pendingNames = Array.isArray(pending) ? pending.filter(Boolean) : [];
+  const detail = pendingNames.length > 0
+    ? `Timed out after ${GLOBAL_DIAGNOSIS_TIMEOUT_MS / 1000}s — did not report in time: ${pendingNames.join(', ')}`
+    : `Timed out after ${GLOBAL_DIAGNOSIS_TIMEOUT_MS / 1000}s — some checks incomplete`;
+  return {
+    checks: [...completed, { name: 'Diagnosis', status: 'WARN', detail }],
+    // A partial run is never clean, and a real issue count is never reset.
+    issues: Math.max(inherited, 1),
+    timedOut: true,
+    completedCheckCount: completed.length,
+  };
+}
+
 /**
  * Fixed attribution text for the WorkBuddy-desktop sandbox restriction (#525).
  *
@@ -1605,9 +1637,17 @@ async function checkAdapters(checks, mode, gitDirPromise) {
  *   D) Env + CLI tools — fully independent, run IN PARALLEL
  *   E) TUI + Skills — independent, run IN PARALLEL
  */
-async function diagnoseAsync(refreshEnv = false) {
+async function diagnoseAsync(refreshEnv = false, progress = null) {
+  // #629: `progress` is a live view of the checks completed so far. The global
+  // timeout used to discard everything diagnoseAsync had already produced; with a
+  // shared sink, a deadline can report "these finished, those did not" instead of
+  // replacing the whole diagnosis with a placeholder.
   const checks = [];
   let issues = 0;
+  if (progress) {
+    progress.checks = checks;
+    progress.getIssues = () => issues;
+  }
 
   // Spawn capability probe FIRST (sync, no config dependency) — #525: it must
   // report even when the config early-exits below, and its WARN (environmental,
@@ -2869,10 +2909,26 @@ async function doctor(args) {
 
   // Global timeout wrapper — ensures doctor completes within GLOBAL_DIAGNOSIS_TIMEOUT_MS
   // even if network/subprocess checks stack up (fix #348: 43s on Windows).
-  const diagnosisPromise = diagnoseAsync(refreshEnv);
+  // #629: give diagnoseAsync a live sink so a deadline can keep what finished.
+  // Without it, `Promise.race` discarded the entire diagnosis -- so the SAME
+  // healthy install reported different results run to run, and a timed-out run
+  // lost the skills section entirely (scrapers read 0/12 installed skills).
+  const progress = { checks: [], getIssues: () => 0 };
+  const diagnosisPromise = diagnoseAsync(refreshEnv, progress);
   let diagnosisTimer = null;
   const timeoutPromise = new Promise((resolve) => {
-    diagnosisTimer = setTimeout(() => resolve({ checks: [{ name: 'Diagnosis', status: 'WARN', detail: `Timed out after ${GLOBAL_DIAGNOSIS_TIMEOUT_MS / 1000}s — some checks incomplete` }], issues: 0, timedOut: true }), GLOBAL_DIAGNOSIS_TIMEOUT_MS);
+    diagnosisTimer = setTimeout(() => {
+      const completed = Array.isArray(progress.checks) ? progress.checks : [];
+      const reported = new Set(completed.map((c) => c && c.name));
+      // Name the surfaces that did NOT report, so the reader knows exactly which
+      // conclusions are missing rather than just "something timed out".
+      const pending = ['Hooks', 'Adapters', 'Skills', 'Gate env', 'OpenCode TUI']
+        .filter((name) => !reported.has(name));
+      resolve(mergeTimedOutDiagnosis(
+        { checks: completed, issues: progress.getIssues() },
+        pending,
+      ));
+    }, GLOBAL_DIAGNOSIS_TIMEOUT_MS);
   });
   const { checks, issues: diagnosedIssues, timedOut } = await Promise.race([
     diagnosisPromise.then(r => ({ ...r, timedOut: false })),
@@ -3349,6 +3405,7 @@ module.exports = {
   readTuiJson,
   formatDoctorJson,
   diagnoseHookDrift,
+  mergeTimedOutDiagnosis,
   classifyHooksDir,
   syncGlobalHooksFromRepo,
   diagnoseModuleDrift,

package/lib/gate-audit.ts

@@ -41,6 +41,12 @@ export interface GateAuditEntry {
   duration_anomaly?: boolean; // Issue #370: set when duration_ms > max_duration_ms
   duration_reason?: 'poisoned_start_ms' | 'clock_skew'; // REQ-B: why duration_ms is null
   detail?: string; // #507: optional gate-specific payload (e.g. effective CCN threshold)
+  /**
+   * #651: WHY the gate blocked. Without this the journal can only answer "how
+   * many failed", never "which rule fails most" — and the second question is the
+   * one that drives fixes. Only meaningful when passed=false.
+   */
+  failure_reason?: string;
 }
 
 // ── Public API ───────────────────────────────────────────────────────────────
@@ -415,6 +421,8 @@ function runCli(): void {
       ...(durationReason ? { duration_reason: durationReason as 'poisoned_start_ms' | 'clock_skew' } : {}),
       // #507: only set when provided (omit field otherwise)
       ...(opts['detail'] ? { detail: opts['detail'] } : {}),
+      // #651: only set when provided, so successful records stay byte-identical.
+      ...(opts['failure-reason'] ? { failure_reason: String(opts['failure-reason']).slice(0, 300) } : {}),
     };
     // Pre-commit (trigger=commit) is staging for a commit that does not exist
     // yet: park it in the pending sidecar so post-commit can stamp the real

package/lib/mattpocock-license-verdict.json

@@ -2,6 +2,6 @@
   "verdict": "PASS",
   "license_type": "MIT",
   "sha256": "0e7ac423bf2c6e223b7c5b156f8cf72da49d748e56a1641402c31f22ad07dbb5",
-  "checked_at": "2026-10-30T14:53:53.917Z",
+  "checked_at": "2026-10-30T15:51:17.008Z",
   "source": "network"
 }

package/lib/rework.js

@@ -0,0 +1,262 @@
+/**
+ * `xp-gate rework` — what the gate journal says about rework (#651).
+ *
+ * `xp-gate retro` already answers "how much did we ship". This answers the
+ * narrower and more actionable question: how often does a round of work clear
+ * the gates on the first attempt, and which rule stops it most.
+ *
+ * The reason this needs a dedicated command rather than a `retro` line: before
+ * #651 the journal contained NO failure records at all, so a naive rework rate
+ * computed from it returned 100% every time. A metric that reads "perfect" when
+ * it is actually unmeasured is worse than no metric -- it manufactures
+ * confidence. So `measurable: false` is a first-class outcome here.
+ *
+ * No runtime dependencies: this ships inside the zero-install package.
+ */
+'use strict';
+
+const fs = require('node:fs');
+const path = require('node:path');
+
+const AUDIT_DIR = '.xp-gate';
+const AUDIT_FILE = 'audit.jsonl';
+const PENDING_FILE = 'audit.pending.jsonl';
+
+/** Bucket name for failures the journal cannot attribute to a rule. */
+const UNATTRIBUTED = 'unattributed';
+
+/**
+ * Read every journal record under `repoRoot`, oldest first.
+ *
+ * Malformed lines are skipped rather than thrown on: the journal is append-only
+ * and a single truncated write must not take the whole report down.
+ *
+ * @param {string} [repoRoot]
+ * @returns {Array<object>}
+ */
+function readJournal(repoRoot = process.cwd()) {
+  const dir = path.join(repoRoot, AUDIT_DIR);
+  const entries = [];
+  for (const file of [AUDIT_FILE, PENDING_FILE]) {
+    const full = path.join(dir, file);
+    let raw;
+    try {
+      raw = fs.readFileSync(full, 'utf8');
+    } catch {
+      continue;
+    }
+    for (const line of raw.split('\n')) {
+      if (!line.trim()) continue;
+      try {
+        const parsed = JSON.parse(line);
+        if (parsed && typeof parsed === 'object') entries.push(parsed);
+      } catch {
+        /* truncated/garbled line -- skip, do not fail the report */
+      }
+    }
+  }
+  return entries;
+}
+
+/** Median of a numeric array (0 for an empty array). */
+function median(values) {
+  if (values.length === 0) return 0;
+  const sorted = [...values].sort((a, b) => a - b);
+  const mid = Math.floor(sorted.length / 2);
+  return sorted.length % 2 === 0 ? (sorted[mid - 1] + sorted[mid]) / 2 : sorted[mid];
+}
+
+/** Mean of a numeric array (0 for an empty array). */
+function mean(values) {
+  if (values.length === 0) return 0;
+  return values.reduce((a, b) => a + b, 0) / values.length;
+}
+
+/**
+ * Group a flat record list into rework rounds.
+ *
+ * The journal is a flat stream of gate executions with no round identifier, so a
+ * round is reconstructed the only way the data allows: a run of FAIL records
+ * terminated by the next PASS. That is exactly "how many attempts before this
+ * landed", which is the definition rework needs. A trailing run of failures with
+ * no resolving pass is a round that has not landed yet, and is counted as
+ * `unresolved` rather than being dropped.
+ *
+ * @param {Array<object>} entries
+ */
+function groupRounds(entries) {
+  const rounds = [];
+  let current = 0;
+  for (const entry of entries) {
+    if (entry.passed) {
+      if (current > 0) rounds.push(current);
+      current = 0;
+      continue;
+    }
+    current += 1;
+  }
+  return { resolved: rounds, unresolved: current };
+}
+
+/**
+ * Aggregate the journal into rework metrics.
+ *
+ * @param {Array<object>} entries journal records
+ * @returns {object} see AC-670-59..62
+ */
+function computeReworkStats(entries) {
+  const list = Array.isArray(entries) ? entries : [];
+  const totals = list.length;
+  const failures = list.filter((e) => e.passed === false).length;
+  const passes = totals - failures;
+
+  // ── Failures by reason ────────────────────────────────────────────────────
+  // Unlabelled failures are bucketed, never dropped: dropping them would lower
+  // the failure count and push the first-pass rate UP, which is the optimistic
+  // direction and therefore the dangerous one.
+  const byReason = new Map();
+  for (const entry of list) {
+    if (entry.passed !== false) continue;
+    const raw = typeof entry.failure_reason === 'string' ? entry.failure_reason.trim() : '';
+    const key = raw === '' ? UNATTRIBUTED : raw;
+    byReason.set(key, (byReason.get(key) || 0) + 1);
+  }
+  const topFailures = [...byReason.entries()]
+    .map(([reason, count]) => ({ reason, count }))
+    .sort((a, b) => b.count - a.count || a.reason.localeCompare(b.reason));
+
+  // ── Durations ─────────────────────────────────────────────────────────────
+  // Two independent guards, because the flag alone is not enough:
+  //
+  //  1. honour `duration_anomaly` -- the writer's own verdict;
+  //  2. reject implausible magnitudes. Measured on the real journal: 391 records
+  //     carry the flag, but 6 MORE epoch-sized values (up to 1.78e12) do not,
+  //     so trusting the flag alone left the mean at 1.3e9 ms -- the very
+  //     "average 430 million seconds" artifact this is supposed to kill.
+  //
+  // The ceiling is deliberately generous (1 hour): a real gate run that long is
+  // pathological but conceivable, while an epoch stamp is ~1.78e12 and cannot be
+  // mistaken for anything else.
+  const MAX_PLAUSIBLE_DURATION_MS = 60 * 60 * 1000;
+  const isPlausible = (e) => typeof e.duration_ms === 'number'
+    && Number.isFinite(e.duration_ms)
+    && e.duration_ms >= 0
+    && e.duration_ms <= MAX_PLAUSIBLE_DURATION_MS
+    && e.duration_anomaly !== true;
+  const sane = list.filter(isPlausible);
+  const duration = sane.length > 0
+    ? {
+      medianMs: median(sane.map((e) => e.duration_ms)),
+      meanMs: Math.round(mean(sane.map((e) => e.duration_ms))),
+      samples: sane.length,
+      // Every record that did NOT contribute -- flagged or implausible. Reporting
+      // only the flagged count would understate the exclusion and make the
+      // sample size look closer to the record count than it is.
+      excludedAnomalies: list.filter((e) => typeof e.duration_ms === 'number' && !isPlausible(e)).length,
+    }
+    : null;
+
+  // ── Rounds ────────────────────────────────────────────────────────────────
+  const rounds = groupRounds(list);
+  const reworkRounds = rounds.resolved;
+
+  // ── First-pass rate ───────────────────────────────────────────────────────
+  // Undefined without failures. A rate over an empty failure set is not 100%.
+  const measurable = failures > 0;
+  const firstPassRate = measurable ? Math.round((passes / totals) * 1000) / 10 : null;
+
+  return {
+    measurable,
+    reason: measurable ? null : 'no failure records in the journal -- first-pass rate is not measurable (pre-#651 journals only recorded passes)',
+    totalRecords: totals,
+    passes,
+    failures,
+    firstPassRate,
+    rounds: {
+      resolved: reworkRounds.length,
+      unresolved: rounds.unresolved > 0,
+      medianRework: median(reworkRounds),
+      meanRework: Math.round(mean(reworkRounds) * 100) / 100,
+      worstRework: reworkRounds.length > 0 ? Math.max(...reworkRounds) : 0,
+    },
+    topFailures,
+    duration,
+  };
+}
+
+/** Render a stats object for the terminal. */
+function formatReworkReport(stats, { limit = 10 } = {}) {
+  const lines = [];
+  lines.push('');
+  lines.push('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
+  lines.push('   REWORK REPORT');
+  lines.push('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
+  lines.push('');
+  lines.push(`  Journal records: ${stats.totalRecords}  (${stats.passes} pass, ${stats.failures} fail)`);
+
+  if (!stats.measurable) {
+    // Say WHY, and say it loudly: a silent 100% would be a lie.
+    lines.push('');
+    lines.push('  ⚠️  First-pass rate: NOT MEASURABLE');
+    lines.push(`     ${stats.reason}`);
+  } else {
+    lines.push(`  First-pass rate: ${stats.firstPassRate}%`);
+  }
+
+  if (stats.rounds.resolved > 0) {
+    lines.push('');
+    lines.push(`  Rework rounds (failures before a landing): ${stats.rounds.resolved}`);
+    lines.push(`     median ${stats.rounds.medianRework} / mean ${stats.rounds.meanRework} / worst ${stats.rounds.worstRework}`);
+    if (stats.rounds.unresolved) {
+      lines.push('     (a trailing run of failures has not landed yet)');
+    }
+  }
+
+  if (stats.topFailures.length > 0) {
+    lines.push('');
+    lines.push(`  Top ${limit} blocking reasons:`);
+    for (const { reason, count } of stats.topFailures.slice(0, limit)) {
+      lines.push(`     ${String(count).padStart(5)}  ${reason}`);
+    }
+  }
+
+  if (stats.duration) {
+    lines.push('');
+    lines.push(`  Gate duration: median ${stats.duration.medianMs} ms / mean ${stats.duration.meanMs} ms (${stats.duration.samples} samples`);
+    lines.push(`                 ${stats.duration.excludedAnomalies} anomaly record(s) excluded)`);
+  }
+
+  lines.push('');
+  return lines.join('\n');
+}
+
+/**
+ * CLI entry.
+ * @param {string[]} argv args after `rework`
+ */
+function main(argv = []) {
+  const repoRootIdx = argv.indexOf('--dir');
+  const repoRoot = repoRootIdx !== -1 && argv[repoRootIdx + 1] ? argv[repoRootIdx + 1] : process.cwd();
+  const limitIdx = argv.indexOf('--top');
+  const limit = limitIdx !== -1 && argv[limitIdx + 1] ? parseInt(argv[limitIdx + 1], 10) : 10;
+
+  const stats = computeReworkStats(readJournal(repoRoot));
+  if (argv.includes('--json')) {
+    process.stdout.write(`${JSON.stringify(stats, null, 2)}\n`);
+    return 0;
+  }
+  process.stdout.write(`${formatReworkReport(stats, { limit })}\n`);
+  return 0;
+}
+
+module.exports = {
+  readJournal,
+  computeReworkStats,
+  formatReworkReport,
+  main,
+  UNATTRIBUTED,
+};
+
+if (require.main === module) {
+  process.exitCode = main(process.argv.slice(2));
+}

package/mock-policy/AGENTS.md

@@ -1,9 +1,9 @@
 # SRC/MOCK-POLICY KNOWLEDGE BASE
 
 **Generated:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## 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:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## 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": "0.34.1",
+  "version": "0.35.1",
   "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": "0.34.1",
+  "version": "0.35.1",
   "displayName": "XP-Gate",
   "description": "Extreme Programming quality gates + AI workflow skills for Claude Code. Includes 12 pre-commit gates (Gate 0-11), 8 pre-push gates, Sprint Flow (6 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:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## OVERVIEW
 Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, exactly 3 experts with distinct executable model IDs). Supports design, requirements, and code-walkthrough modes.

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

@@ -1,9 +1,9 @@
 # SKILLS/SPRINT-FLOW KNOWLEDGE BASE
 
 **Generated:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## 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/test-specification-alignment/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
 
 **Generated:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## OVERVIEW
 Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.

package/plugins/dsh/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@boyingliu01/dsh-plugin-xp-gate",
-  "version": "0.34.1",
+  "version": "0.35.1",
   "description": "XP-Gate deterministic quality gates + AI workflow skills as a DeepSeek Harness (DSH) native plugin: gate-check / gate-principles / gate-arch tools + 12 SKILL.md skills",
   "type": "module",
   "main": "./lib/index.js",

package/plugins/dsh/skills/delphi-review/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
 
 **Generated:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## OVERVIEW
 Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, exactly 3 experts with distinct executable model IDs). Supports design, requirements, and code-walkthrough modes.

package/plugins/dsh/skills/sprint-flow/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/SPRINT-FLOW KNOWLEDGE BASE
 
 **Generated:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## 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/dsh/skills/test-specification-alignment/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
 
 **Generated:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## 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": "0.34.1",
+  "version": "0.35.1",
   "type": "module",
   "main": "index.ts",
   "description": "XP-Gate quality gates + AI workflow skills + Sprint Flow TUI sidebar for OpenCode",

package/plugins/opencode/skills/delphi-review/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
 
 **Generated:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## OVERVIEW
 Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, exactly 3 experts with distinct executable model IDs). Supports design, requirements, and code-walkthrough modes.

package/plugins/opencode/skills/sprint-flow/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/SPRINT-FLOW KNOWLEDGE BASE
 
 **Generated:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## 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/opencode/skills/test-specification-alignment/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
 
 **Generated:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## OVERVIEW
 Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.

package/plugins/qoder/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "xp-gate",
-  "version": "0.34.1",
+  "version": "0.35.1",
   "displayName": "XP-Gate",
   "description": "Extreme Programming quality gates + AI workflow skills for Qoder. Includes 12 pre-commit gates (Gate 0-11), 8 pre-push gates, Sprint Flow (6 phases), and Delphi multi-expert review (>=90% consensus).",
   "author": {

package/plugins/qoder/skills/delphi-review/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
 
 **Generated:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## OVERVIEW
 Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, exactly 3 experts with distinct executable model IDs). Supports design, requirements, and code-walkthrough modes.

package/plugins/qoder/skills/sprint-flow/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/SPRINT-FLOW KNOWLEDGE BASE
 
 **Generated:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## 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/qoder/skills/test-specification-alignment/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
 
 **Generated:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## OVERVIEW
 Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.

package/principles/AGENTS.md

@@ -1,9 +1,9 @@
 # PRINCIPLES CHECKER MODULE
 
 **Generated:** 2026-10-30
-**Commit:** e583bcfb
+**Commit:** 2ce96f13
 **Branch:** main
-**Version:** 0.34.1.0
+**Version:** 0.35.1.0
 
 ## OVERVIEW
 Clean Code & SOLID principles checker — **Gate 4** of pre-commit. 14 rules × 9 language adapters, SARIF 2.1.0 output. Houses the **Boy Scout Rule** enforcement engine (Gate 6) and warning-baseline storage.