agentic-sdlc-wizard 1.70.0 → 1.72.0

package/.claude-plugin/marketplace.json

@@ -13,7 +13,7 @@
       "name": "sdlc-wizard",
       "source": ".",
       "description": "SDLC enforcement for AI agents — TDD, planning, self-review, CI shepherd",
-      "version": "1.70.0",
+      "version": "1.72.0",
       "author": {
         "name": "Stefan Ayala"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "sdlc-wizard",
-  "version": "1.70.0",
+  "version": "1.72.0",
   "description": "SDLC enforcement for AI agents — TDD, planning, self-review, CI shepherd",
   "author": {
     "name": "Stefan Ayala",

package/CHANGELOG.md

@@ -4,6 +4,93 @@ All notable changes to the SDLC Wizard.
 
 > **Note:** This changelog is for humans to read. Don't manually apply these changes - just run the wizard ("Check for SDLC wizard updates") and it handles everything automatically.
 
+## [1.72.0] - 2026-05-05
+
+### Closes #323: `init --force` no longer silently overwrites CUSTOMIZED files
+
+User report 2026-05-05 — `npx agentic-sdlc-wizard check` flags 6 files as CUSTOMIZED then recommends `init --force`, which silently clobbers all 6. Reporter: "the wizard correctly **detected** 6 CUSTOMIZED files and then **recommended a command that would overwrite all 6**." Fully closed in two parts:
+
+#### Part 1 — customization-aware recommendation in `check` (PR #325)
+
+When `check` finds CUSTOMIZED files alongside an available update, the suggested command now warns and points at `init --dry-run` first instead of silently recommending `init --force`. Pure function `buildUpdateRecommendation(updateInfo, customizedCount)` exported from `cli/init.js`. Backward compat: zero-customized recommendation byte-for-byte unchanged.
+
+#### Part 2 — new `init --preserve-customized` flag (PR #328)
+
+Composes existing `--force` semantics — when both flags are set:
+
+- **CUSTOMIZED** files (sha256 mismatch with template) → action `PRESERVE`, skipped during write, reported in summary footer
+- **MATCH** files → `OVERWRITE` (refresh; effectively no-op since hashes already match)
+- **MISSING** files → `CREATE` (new files added in latest version still get installed)
+
+Without `--force`, the flag is a no-op (all existing files SKIP regardless). Updated `check` recommendation now suggests `init --force --preserve-customized` as the "upgrade safely" path when CUSTOMIZED files exist.
+
+#### Sample output
+
+```
+PRESERVE  .claude/hooks/sdlc-prompt-check.sh
+PRESERVE  .claude/skills/sdlc/SKILL.md
+OVERWRITE .claude/hooks/tdd-pretool-check.sh
+CREATE    .claude/skills/feedback/SKILL.md
+
+PRESERVED 2 customized file(s) — review with `init --dry-run` to see what differs from the latest template.
+```
+
+#### Test coverage
+
+10 new tests in `tests/test-cli.sh` across 3 PRs (78 → 88 green): customization-aware recommendation (2 from #325), null/undefined edge cases (2 from #326 P2 follow-up), preserve-customized core behavior (3 from #328 round 1), no-force-no-op + settings.json MERGE precedence + WIZARD_DOC parity (3 from #328 round-2).
+
+#### Deferred
+
+Option 3 from #323 (real `update` subcommand with backup directory + per-file diff prompt) — options 1 + 2 close the immediate footgun without a new subcommand and backup-storage convention.
+
+#### Files
+
+- `cli/init.js` — `buildUpdateRecommendation()` exported; `--preserve-customized` threaded through `init()` → `planOperations()`; `isCustomized()` hash helper; `PRESERVE` action skipped in `executeOperations()`; `printOps()` adds yellow `PRESERVE` color + summary footer
+- `cli/bin/sdlc-wizard.js` — `--preserve-customized` flag + help text
+- `tests/test-cli.sh` — 10 new tests across 3 PRs (78 → 88 green)
+- `package.json`, `.claude-plugin/plugin.json` + `marketplace.json`, `SDLC.md`, `skills/update/SKILL.md`, `CLAUDE_CODE_SDLC_WIZARD.md`, `CHANGELOG.md` (1.71.0 → 1.72.0)
+
+## [1.71.0] - 2026-05-05
+
+### Token-bloat fix: SDLC skill Cross-Model Review section trimmed
+
+`skills/sdlc/SKILL.md` Cross-Model Review section condensed from ~70 lines to ~20 lines. Saves ~427 tokens per SDLC skill auto-invoke (4995 → 4568 tokens). The skill auto-loads on virtually every productive `implement/fix/refactor` task, so this is real per-session cost.
+
+### What stayed in SKILL.md
+
+- Decision-making: when to run / skip / prerequisites / flagship-tier reviewer rule (#233)
+- 4-step protocol summary (preflight → handoff → reviewer → dialogue loop)
+- Required handoff JSON keys + `pr_number` self-heal opt-in note (#209)
+- Convergence rule (2 rounds sweet spot, 3 max)
+- Release-review verification-checklist additions
+- Sandbox flag for Codex from CC
+
+### What moved to canonical wizard doc only
+
+Full JSON example, full codex command example, anti-patterns, multi-reviewer (Claude+Codex+human) workflow, non-code-domain variants. All these live in `CLAUDE_CODE_SDLC_WIZARD.md` → "Cross-Model Review Loop" (194 lines, full canonical protocol). The trimmed SKILL.md ends with an explicit pointer to that section.
+
+### Audit method
+
+ROADMAP #236 phase 3. `scripts/audit-session-load.sh` ranked SKILL.md files at the top of the size table:
+- `skills/sdlc/SKILL.md`: 4995 tokens (sat right at 5K threshold)
+- `skills/update/SKILL.md`: 4931 tokens
+- `skills/setup/SKILL.md`: 4490 tokens
+
+SDLC skill auto-invokes most often (every implement/fix/refactor task), so it earned the cut. Verified 8 test suites that grep for SKILL.md content (mocking table, TDD prove, Memory Audit Protocol heading, opus[1m], autocompact compound, Deployment Tasks, plus `tests/test-self-update.sh` which asserts cross-model-review-specific content: `### Release Review Focus` heading, `Version parity` focus area, `"mission"`/`"success"`/`"failure"` JSON-quoted schema keys, "verification checklist" pattern, "preflight" mention). Codex round 1 caught 3 missed assertions in `test-self-update.sh`; round 2 fixes restored those constraints in tighter prose without re-bloating.
+
+### Files
+
+- `skills/sdlc/SKILL.md` — Cross-Model Review section trimmed
+- `CHANGELOG.md`, `SDLC.md`, `skills/update/SKILL.md` (Latest:), `package.json`, `.claude-plugin/plugin.json` + `marketplace.json`, `CLAUDE_CODE_SDLC_WIZARD.md` (1.70.0 → 1.71.0)
+
+### Combined savings ROADMAP #236 phases 1-3
+
+- v1.69.0: ~12K tokens/session (BASELINE block fires once)
+- v1.70.0: ~0.5-1.5K tokens/session (TDD CHECK fires once)
+- v1.71.0: ~573 tokens/session (SDLC skill leaner on auto-invoke)
+
+Total on a 50-prompt + 20-Edit + 1 SDLC-skill-invoke session: **~14K tokens/session**.
+
 ## [1.70.0] - 2026-05-05
 
 ### Token-bloat fix: TDD CHECK nudge fires once per CC session

package/CLAUDE_CODE_SDLC_WIZARD.md

@@ -2976,7 +2976,7 @@ If deployment fails or post-deploy verification catches issues:
 
 **SDLC.md:**
 ```markdown
-<!-- SDLC Wizard Version: 1.70.0 -->
+<!-- SDLC Wizard Version: 1.72.0 -->
 <!-- Setup Date: [DATE] -->
 <!-- Completed Steps: step-0.1, step-0.2, step-0.4, step-1, step-2, step-3, step-4, step-5, step-6, step-7, step-8, step-9 -->
 <!-- Git Workflow: [PRs or Solo] -->
@@ -3923,6 +3923,21 @@ CLI-distributed file parity (skills, hooks, settings).
 
 **This complements automated tests, not replaces them.** Tests catch exact version mismatches (e.g., `test_package_version_matches_changelog`). Cross-model review catches semantic issues tests cannot — a section silently dropped, examples using outdated but syntactically valid versions, docs describing features that no longer exist.
 
+#### Anti-patterns
+
+- **"Find at least N problems"** — incentivizes false positives. The reviewer will manufacture findings to hit the count.
+- **"Review this"** — too vague. Always pair with `verification_checklist` items that name file:line evidence to verify.
+- **1-10 score with no criteria** — every reviewer scores differently. Either define what 1, 5, 10 mean for *this* review, or drop the score and just produce CERTIFIED / NOT CERTIFIED with findings.
+- **Author reasoning visible to reviewer** — anchoring bias. The reviewer should see code + handoff, not the author's self-assessment of why it's correct.
+
+#### Multiple reviewers (Claude review + Codex + human)
+
+Run them in parallel; collect feedback via `gh api repos/OWNER/REPO/pulls/PR/comments` (single source of truth). Respond per-reviewer (different blind spots — don't merge feedback). On conflicts, pick the stronger argument with reasoning, not the louder voice. Cap iterations at 3 per reviewer to avoid infinite loops.
+
+#### Non-code domains (research, persuasion, medical content)
+
+Same handoff format. Adapt `review_instructions` (e.g. "verify each cited claim links to a primary source") and `verification_checklist` (specific claim → specific source). Add `"audience"` and `"stakes"` keys to the JSON so the reviewer knows what reading level / risk profile to apply.
+
 ---
 
 ## User Understanding and Periodic Feedback
@@ -4055,7 +4070,7 @@ Walk through updates? (y/n)
 Store wizard state in `SDLC.md` as metadata comments (invisible to readers, parseable by Claude):
 
 ```markdown
-<!-- SDLC Wizard Version: 1.70.0 -->
+<!-- SDLC Wizard Version: 1.72.0 -->
 <!-- Setup Date: 2026-01-24 -->
 <!-- Completed Steps: step-0.1, step-0.2, step-1, step-2, step-3, step-4, step-5, step-6, step-7, step-8, step-9 -->
 <!-- Git Workflow: PRs -->

package/cli/bin/sdlc-wizard.js

@@ -11,6 +11,7 @@ const flags = {
   force: args.includes('--force'),
   dryRun: args.includes('--dry-run'),
   json: args.includes('--json'),
+  preserveCustomized: args.includes('--preserve-customized'),
 };
 
 const positional = args.filter((a) => !a.startsWith('--'));
@@ -31,11 +32,12 @@ if (args.includes('--help') || args.includes('-h') || !command) {
     sdlc-wizard complexity [path]            Print mixed-mode tier heuristic (roadmap #233)
 
   Options:
-    --force       Overwrite existing files (init only)
-    --dry-run     Preview changes without writing (init only)
-    --json        Output as JSON (check / complexity)
-    --version     Show version
-    --help        Show this help
+    --force                  Overwrite existing files (init only)
+    --preserve-customized    With --force, skip files that have local edits (init only)
+    --dry-run                Preview changes without writing (init only)
+    --json                   Output as JSON (check / complexity)
+    --version                Show version
+    --help                   Show this help
   `.trim());
   process.exit(0);
 }

package/cli/init.js

@@ -130,9 +130,23 @@ function mergeSettings(existingPath, templatePath, force) {
   }
 }
 
-function planOperations(targetDir, { force }) {
+function planOperations(targetDir, { force, preserveCustomized = false }) {
   const ops = [];
 
+  // #323 option 2: preserve mode requires hashing each existing file to
+  // distinguish CUSTOMIZED from MATCH. Only meaningful with --force; without
+  // --force, existing files are SKIP regardless of hash.
+  const isCustomized = (srcPath, destPath) => {
+    if (!preserveCustomized || !force) return false;
+    try {
+      const srcHash = crypto.createHash('sha256').update(fs.readFileSync(srcPath)).digest('hex');
+      const destHash = crypto.createHash('sha256').update(fs.readFileSync(destPath)).digest('hex');
+      return srcHash !== destHash;
+    } catch (_) {
+      return false;
+    }
+  };
+
   for (const file of FILES) {
     const destPath = path.join(targetDir, file.dest);
     const srcPath = path.join(file.base || TEMPLATES_DIR, file.src);
@@ -154,11 +168,16 @@ function planOperations(targetDir, { force }) {
       // Invalid JSON — fall through to normal SKIP/OVERWRITE
     }
 
+    let action;
+    if (!exists) action = 'CREATE';
+    else if (isCustomized(srcPath, destPath)) action = 'PRESERVE';
+    else action = force ? 'OVERWRITE' : 'SKIP';
+
     ops.push({
       src: srcPath,
       dest: destPath,
       relativeDest: file.dest,
-      action: exists ? (force ? 'OVERWRITE' : 'SKIP') : 'CREATE',
+      action,
       executable: file.executable || false,
     });
   }
@@ -166,11 +185,15 @@ function planOperations(targetDir, { force }) {
   // Wizard doc
   const wizardDest = path.join(targetDir, 'CLAUDE_CODE_SDLC_WIZARD.md');
   const wizardExists = fs.existsSync(wizardDest);
+  let wizardAction;
+  if (!wizardExists) wizardAction = 'CREATE';
+  else if (isCustomized(WIZARD_DOC, wizardDest)) wizardAction = 'PRESERVE';
+  else wizardAction = force ? 'OVERWRITE' : 'SKIP';
   ops.push({
     src: WIZARD_DOC,
     dest: wizardDest,
     relativeDest: 'CLAUDE_CODE_SDLC_WIZARD.md',
-    action: wizardExists ? (force ? 'OVERWRITE' : 'SKIP') : 'CREATE',
+    action: wizardAction,
     executable: false,
   });
 
@@ -183,7 +206,7 @@ function ensureDir(filePath) {
 
 function executeOperations(ops) {
   for (const op of ops) {
-    if (op.action === 'SKIP') continue;
+    if (op.action === 'SKIP' || op.action === 'PRESERVE') continue;
     ensureDir(op.dest);
     if (op.action === 'MERGE') {
       fs.writeFileSync(op.dest, op.mergedContent);
@@ -230,12 +253,18 @@ function updateGitignore(targetDir, { dryRun }) {
 }
 
 function printOps(ops) {
+  let preserveCount = 0;
   for (const op of ops) {
     const color = op.action === 'CREATE' ? GREEN
       : op.action === 'SKIP' ? YELLOW
       : op.action === 'MERGE' ? MAGENTA
+      : op.action === 'PRESERVE' ? YELLOW
       : CYAN;
     console.log(`  ${color}${op.action}${RESET}  ${op.relativeDest}`);
+    if (op.action === 'PRESERVE') preserveCount++;
+  }
+  if (preserveCount > 0) {
+    console.log(`\n  ${YELLOW}PRESERVED ${preserveCount} customized file(s)${RESET} — review with \`init --dry-run\` to see what differs from the latest template.`);
   }
 }
 
@@ -254,7 +283,7 @@ function invalidateVersionCache({ dryRun }) {
   return true;
 }
 
-function init(targetDir, { force = false, dryRun = false } = {}) {
+function init(targetDir, { force = false, dryRun = false, preserveCustomized = false } = {}) {
   if (!dryRun && !force) {
     const pluginPaths = detectPluginInstall();
     if (pluginPaths.length > 0) {
@@ -273,7 +302,7 @@ function init(targetDir, { force = false, dryRun = false } = {}) {
     }
   }
 
-  const ops = planOperations(targetDir, { force });
+  const ops = planOperations(targetDir, { force, preserveCustomized });
 
   if (dryRun) {
     console.log('Dry run — no files will be written:\n');
@@ -396,14 +425,37 @@ function check(targetDir, { json = false } = {}) {
       }
     }
     if (updateInfo) {
-      console.log(`\n  ${YELLOW}UPDATE${RESET}  v${updateInfo.current} -> v${updateInfo.latest}`);
-      console.log('         Run: npx agentic-sdlc-wizard init --force');
+      const customizedCount = results.filter((r) => r.status === 'CUSTOMIZED').length;
+      for (const line of buildUpdateRecommendation(updateInfo, customizedCount)) {
+        console.log(line);
+      }
     }
   }
 
   return { results, updateInfo, hasDrift, marketplace };
 }
 
+// #323: when `check` finds CUSTOMIZED files alongside an available update,
+// the historical recommendation `init --force` would silently clobber them.
+// This builds an update-recommendation block that's customization-aware:
+// no-CUSTOMIZED → recommend --force as before. Has-CUSTOMIZED → warn and
+// recommend `--dry-run` first so the user can preview the diff.
+function buildUpdateRecommendation(updateInfo, customizedCount) {
+  if (!updateInfo) return [];
+  const lines = [
+    `\n  ${YELLOW}UPDATE${RESET}  v${updateInfo.current} -> v${updateInfo.latest}`,
+  ];
+  if (customizedCount > 0) {
+    lines.push(`         ${YELLOW}WARNING${RESET}: ${customizedCount} file(s) CUSTOMIZED — \`init --force\` will overwrite them`);
+    lines.push(`         Preview first:  npx agentic-sdlc-wizard init --dry-run`);
+    lines.push(`         Or upgrade safely: npx agentic-sdlc-wizard init --force --preserve-customized`);
+    lines.push(`         (\`--preserve-customized\` skips CUSTOMIZED files and updates only MATCH ones.)`);
+  } else {
+    lines.push('         Run: npx agentic-sdlc-wizard init --force');
+  }
+  return lines;
+}
+
 function checkFile(srcPath, destPath, relativeDest, shouldBeExecutable) {
   if (!fs.existsSync(destPath)) {
     return { file: relativeDest, status: 'MISSING' };
@@ -519,4 +571,4 @@ function checkMarketplacePaths() {
   return results;
 }
 
-module.exports = { init, check, planOperations, detectPluginInstall, GITIGNORE_ENTRIES };
+module.exports = { init, check, planOperations, detectPluginInstall, buildUpdateRecommendation, GITIGNORE_ENTRIES };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentic-sdlc-wizard",
-  "version": "1.70.0",
+  "version": "1.72.0",
   "description": "SDLC enforcement for Claude Code — hooks, skills, and wizard setup in one command",
   "bin": {
     "sdlc-wizard": "cli/bin/sdlc-wizard.js"

package/skills/sdlc/SKILL.md

@@ -120,76 +120,24 @@ The loop goes back to PLANNING, not TDD RED. Run `/code-review`; issues at confi
 
 ## Cross-Model Review (If Configured)
 
-**When to run:** high-stakes changes (auth, payments, data), releases/publishes, complex refactors.
-**When to skip:** trivial changes, time-sensitive hotfixes, risk < review cost.
-**Prerequisites:** Codex CLI (`npm i -g @openai/codex`) + OpenAI API key.
-
-The PROTOCOL is universal across domains; only `review_instructions` and `verification_checklist` change. **Reviewer always at flagship tier (#233):** if the project pins `model: "sonnet[1m]"` (mixed-mode), the reviewer still runs `gpt-5.5` or Opus 4.7 max — adversarial diversity is the point.
-
-### Step 0: Preflight Self-Review
-
-At `.reviews/preflight-{review_id}.md`, document what you already checked: `/code-review` passed, all tests passing, specific concerns checked, what you verified manually, known limitations. Reduces reviewer findings to 0-1 per round.
-
-### Step 1: Mission-First Handoff
-
-Write `.reviews/handoff.json`:
-```jsonc
-{
-  "review_id": "feature-xyz-001",
-  "status": "PENDING_REVIEW",
-  "round": 1,
-  "mission": "What changed and why — 2-3 sentences",
-  "success": "What 'correctly reviewed' looks like",
-  "failure": "What gets missed if reviewer is superficial",
-  "files_changed": ["src/auth.ts", "tests/auth.test.ts"],
-  "fixes_applied": [],
-  "previous_score": null,
-  "verification_checklist": [
-    "(a) Verify input validation at auth.ts:45 handles empty strings",
-    "(b) Verify test covers null-token edge case"
-  ],
-  "review_instructions": "Focus on security and edge cases. Be strict — assume bugs may be present.",
-  "preflight_path": ".reviews/preflight-feature-xyz-001.md",
-  "pr_number": 205
-}
-```
-
-`mission/success/failure` give context (without them: generic "looks good"). `verification_checklist` is specific (file:line), not "review for correctness." `pr_number` (optional) is the **PreCompact self-heal opt-in (ROADMAP #209)**: when set, `precompact-seam-check.sh` checks `gh pr view N --json state` on `/compact` and, if MERGED, treats handoff as implicit CERTIFIED. Without it, a forgotten PENDING handoff blocks every manual compact until you flip status or hit `SDLC_HANDOFF_STALE_DAYS` (default 14).
-
-### Step 2: Run the Reviewer
-
-```bash
-codex exec -c 'model_reasoning_effort="xhigh"' -s danger-full-access \
-  -o .reviews/latest-review.md \
-  "Independent code reviewer. Read .reviews/handoff.json for context. \
-   Verify each checklist item with evidence (file:line, grep, test output). \
-   Each finding: ID, severity (P0/P1/P2), evidence, certify condition. \
-   End with: score (1-10), CERTIFIED or NOT CERTIFIED."
-```
-
-Always `xhigh` — lower settings miss subtle errors. **Progress (#259):** xhigh runs take 1-5 min; for a heartbeat use `scripts/codex-review-with-progress.sh` (`SDLC_CODEX_HEARTBEAT_INTERVAL` tunes). **Sandbox:** Codex's Rust binary needs `SCDynamicStore`; CC's sandbox blocks this. From CC, use `dangerouslyDisableSandbox: true` — Codex has its own sandbox via `-s danger-full-access`. Known issue: [codex#15640](https://github.com/openai/codex/issues/15640).
-
-CERTIFIED → CI. NOT CERTIFIED → dialogue loop.
-
-### Step 3: Dialogue Loop
-
-Per-finding response in `.reviews/response.json`: `{"finding": "1", "action": "FIXED|DISPUTED|ACCEPTED", "summary": "..."}`. Update `handoff.json`: increment `round`, status `PENDING_RECHECK`, add `fixes_applied` (numbered, file:line refs).
-
-Recheck prompt: "TARGETED RECHECK. For each finding: FIXED → verify certify condition. DISPUTED → ACCEPT if sound, REJECT with reasoning. ACCEPTED → verify applied. Do NOT raise new findings unless P0. End with score, CERTIFIED or NOT CERTIFIED."
+**When to run:** high-stakes changes (auth, payments, data), releases/publishes, complex refactors. **When to skip:** trivial changes, time-sensitive hotfixes, risk < review cost. **Prerequisites:** Codex CLI (`npm i -g @openai/codex`) + OpenAI API key. **Reviewer at flagship tier (#233):** even when project pins `sonnet[1m]`, reviewer runs `gpt-5.5` / Opus 4.7 max — adversarial diversity is the point.
 
-**Convergence:** 2 rounds is the sweet spot, 3 max (research: 14 repos + 7 papers). After 3 still NOT CERTIFIED → escalate to user.
+PROTOCOL is universal across domains; only `review_instructions` and `verification_checklist` change.
 
-**Anti-patterns:** "find at least N problems," "review this," 1-10 without criteria, letting reviewer see author's reasoning (anchoring).
+1. **Preflight** (`.reviews/preflight-{review_id}.md`) — what you already checked: `/code-review` passed, tests passing, manual verifications, known limits. Reduces reviewer findings to 0-1/round.
+2. **Mission-first handoff** (`.reviews/handoff.json`) — required JSON keys: `"review_id"`, `"status": "PENDING_REVIEW"`, `"round": 1`, `"mission"` / `"success"` / `"failure"` (2-3 sentences each — without them you get "looks good"), `"files_changed"`, `"verification_checklist"` — the **verification checklist** is specific items with file:line refs (NOT a generic "review this"), `"review_instructions"`, `"preflight_path"`. Optional `"pr_number":` opts into the PreCompact self-heal (#209): if PR is MERGED, `/compact` treats handoff as implicit CERTIFIED.
+3. **Run reviewer:** `codex exec -c 'model_reasoning_effort="xhigh"' -s danger-full-access -o .reviews/latest-review.md "<prompt>"`. Always `xhigh`. CC sandbox blocks Codex's Rust binary (`SCDynamicStore`) — use `dangerouslyDisableSandbox: true` on Bash; Codex has its own sandbox. xhigh runs take 1-5 min; for a heartbeat use `scripts/codex-review-with-progress.sh`.
+4. **Dialogue loop:** per-finding response (`{"finding": "1", "action": "FIXED|DISPUTED|ACCEPTED", "summary": "..."}` in `.reviews/response.json`). Bump round, set status `PENDING_RECHECK`, add `fixes_applied` (numbered, file:line). Recheck prompt: "TARGETED RECHECK. FIXED → verify certify condition. DISPUTED → ACCEPT if sound, REJECT with reasoning. ACCEPTED → verify applied. No new findings unless P0."
 
-**Multiple reviewers** (Claude review + Codex + human): `gh api repos/OWNER/REPO/pulls/PR/comments` for all feedback, respond to each reviewer independently (different blind spots), pick stronger argument on conflicts, max 3 iterations per reviewer.
+**Convergence:** 2 rounds sweet spot, 3 max (research: 14 repos + 7 papers). After 3 still NOT CERTIFIED → escalate.
 
-**Non-code domains** (research, persuasion, medical): same handoff format, adapt `review_instructions` + `verification_checklist`, add `audience` + `stakes`.
+**Multi-reviewer / non-code domains:** when running multiple reviewers in parallel (e.g. Claude review + Codex + human), respond per-reviewer (different blind spots, no shared anchoring). For non-code domains (research, persuasion, medical), keep the same handoff format and add `"audience"` + `"stakes"` keys.
 
 ### Release Review Focus
 
 Before any release/publish, add to `verification_checklist`: **CHANGELOG consistency** (sections present, no lost entries), **Version parity** (package.json + SDLC.md + CHANGELOG + wizard metadata), **Stale examples** (hardcoded version strings), **Docs accuracy** (README + ARCHITECTURE reflect current features), **CLI-distributed file parity** (live skills/hooks match CLI templates).
 
-(Full protocol with rationale and convergence diagrams: `CLAUDE_CODE_SDLC_WIZARD.md` → Cross-Model Review.)
+**Full protocol** (rationale, full JSON example, anti-patterns like "find at least N", convergence diagrams): `CLAUDE_CODE_SDLC_WIZARD.md` → "Cross-Model Review Loop".
 
 ## Documentation Sync (REQUIRED — During Planning)
 

package/skills/update/SKILL.md

@@ -93,11 +93,13 @@ Parse CHANGELOG entries between the user's installed version and latest. Present
 
 ```
 Installed: 1.42.0
-Latest:    1.70.0
+Latest:    1.72.0
 
 What changed:
-- [1.70.0] token-bloat fix phase 2 — `hooks/tdd-pretool-check.sh` TDD CHECK JSON nudge (the per-`Write/Edit` "Are you writing IMPLEMENTATION before a FAILING TEST?" reminder) now fires once per CC `session_id` instead of every src/ edit. Saves ~0.5-1.5K tokens/session (10-30 src Edits × ~50 tok). Same atomic-noclobber claim pattern as v1.69.0 BASELINE gate. Non-src/ edits don't consume the sentinel slot.
-- [1.69.0] token-bloat fix phase 1 — `hooks/sdlc-prompt-check.sh` BASELINE block (the ~250-token "TodoWrite FIRST / STATE CONFIDENCE / AUTO-INVOKE" reminder) now fires once per CC `session_id`. Saves ~12K tokens/session. SETUP-not-complete + EFFORT-bump warnings still fire every prompt (dynamic state).
+- [1.72.0] #323 closed — customization-aware `check` recommendation + new `--preserve-customized` flag. `init --force --preserve-customized` skips CUSTOMIZED files (action `PRESERVE`), still OVERWRITEs MATCH and CREATEs MISSING. Default `init --force` unchanged. 10 tests.
+- [1.71.0] token-bloat phase 3 — `skills/sdlc/SKILL.md` Cross-Model Review trimmed (~70 → ~20 lines, -427 tokens). Full protocol + examples moved to canonical `CLAUDE_CODE_SDLC_WIZARD.md` "Cross-Model Review Loop" section.
+- [1.70.0] token-bloat fix phase 2 — `hooks/tdd-pretool-check.sh` TDD CHECK JSON nudge fires once per CC `session_id` instead of every src/ edit. Saves ~0.5-1.5K tokens/session.
+- [1.69.0] token-bloat fix phase 1 — `hooks/sdlc-prompt-check.sh` BASELINE block fires once per CC `session_id`. Saves ~12K tokens/session.
 - [1.68.0–1.65.0] roadmap hygiene — five paperwork closes: #97 Anthropic Policy NO-GO + AAR-paper validating parallel; #99 AutoGPT NO-GO; #95 Nous NO-GO; #243 token-history liveness verified; #210 Node-24 false-green; #235 Thoughtworks AI Evals NO-GO. **6/6 external-product audits NO-GO** (continues #76, #77). Research write-ups in `.reviews/research-*.md`.
 - [1.64.0] XDLC ecosystem cross-references — README, wizard doc, and ROADMAP now cross-reference all three sibling packages (`agentic-sdlc-wizard`, `codex-sdlc-wizard`, `claude-gdlc-wizard`). New "Ecosystem (Sibling Projects)" section in README. 3 new doc-consistency tests prevent drift.
 - [1.63.0] cache-cost observability closeout (#204 absorbed by #220) — `tests/test-token-spike.sh` gains explicit cache-miss regression test + negative-control test. SDLC skill + wizard doc gain "Cache-Cost Surprises" sections covering 10-20× silent cost blowups (mid-session CLAUDE.md edits, idle pruning, upstream cache bugs) and detection via `hooks/token-spike-check.sh`'s `costly_tokens` metric.