[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MKCSJGAEYEFJ1M1XB22PJ3":3,"skill-same:01M6MKCSJGAEYEFJ1M1XB22PJ3":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":28,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":70},"01M6MKCSJGAEYEFJ1M1XB22PJ3","skill-staged-review",null,"Use when a PR or feature needs both specification and code-quality review","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-staged-review\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41],"review","skill staged review","staged","code","specification","code-quality","quality review","pr","feature","true","use","quality","when","2026-11-10 10:12:30",false,"---\nname: skill-staged-review\ndescription: \"Use when a PR or feature needs both specification and code-quality review\"\ndisable-model-invocation: true\n---\n\n> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.\n> Cross-reference commands use installed skill names in Codex rather than `\u002Focto:*` slash commands.\n> Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it.\n> For host tool equivalents, see `skills\u002Fblocks\u002Fcodex-host-adapter.md`.\n\n\n## Execution Contract (MANDATORY - CANNOT SKIP)\n\nThis generated Codex skill preserves an enforced workflow contract from the source skill.\n\n**PROHIBITED:**\n- Do not summarize, simulate, or skip the referenced workflow command when this skill requires execution.\n- Do not claim provider output or validation artifacts exist without checking the actual files or command output.\n- Do not continue silently when a required provider, command, or host capability is unavailable; report the unavailable dependency and use a supported fallback.\n\n\n# Two-Stage Review Pipeline\n\nSeparates **spec compliance** (did you build the right thing?) from **code quality**\n(did you build it right?). Stage 1 must pass before Stage 2 runs.\n\n\n## Stage 1: Spec Compliance\n\nValidates the implementation against the intent contract.\n\n### Step 1: Load Intent Contract\n\n```bash\nPLAN_STORAGE=\"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Fplan-storage.sh\"\nOCTO_PLAN_DIR=\"$(\"$PLAN_STORAGE\" current \"$PWD\" 2>\u002Fdev\u002Fnull || true)\"\nINTENT_FILE=\"${OCTO_PLAN_DIR:+${OCTO_PLAN_DIR}\u002Fsession-intent.md}\"\nif [[ -f \"$INTENT_FILE\" ]]; then\n  echo \"Intent contract found: $INTENT_FILE\"\n  cat \"$INTENT_FILE\"\nelse\n  echo \"WARNING: No current resolved intent contract found for this workspace\"\n  echo \"Skipping Stage 1 — proceeding to Stage 2 (code quality) only.\"\nfi\n```\n\n**If no intent contract exists:** Warn the user and skip to Stage 2. Do NOT fabricate\nsuccess criteria — the contract must exist from a prior workflow.\n\n### Step 2: Validate Success Criteria\n\nFor each success criterion in the intent contract:\n\n1. **Read the criterion** from the `## Success Criteria` section\n2. **Find evidence** in the codebase that the criterion is met\n3. **Mark status:**\n   - `[PASS]` — Evidence confirms criterion is met\n   - `[FAIL]` — Evidence shows criterion is NOT met\n   - `[PARTIAL]` — Partially met, gaps identified\n\nPresent results:\n\n```markdown\n## Stage 1: Spec Compliance\n\n### Success Criteria Check\n\n#### Good Enough Criteria\n- [PASS] Criterion 1: \u003Chow it was met>\n- [FAIL] Criterion 2: \u003Cwhy not met, what's missing>\n\n#### Exceptional Criteria\n- [PARTIAL] Criterion 1: \u003Cwhat's done, what's remaining>\n```\n\n### Step 3: Validate Boundaries\n\nFor each boundary in the intent contract:\n\n1. **Read the boundary** from the `## Boundaries` section\n2. **Check for violations** in the implementation\n3. **Mark status:**\n   - `[RESPECTED]` — No violations found\n   - `[VIOLATED]` — Implementation crosses the boundary\n\n```markdown\n### Boundary Check\n- [RESPECTED] Boundary 1: \u003Cconfirmation>\n- [VIOLATED] Boundary 2: \u003Cwhat violated it>\n```\n\n### Step 4: Stage 1 Gate\n\n| Result | Action |\n|--------|--------|\n| All criteria PASS + all boundaries RESPECTED | Proceed to Stage 2 |\n| Any criterion FAIL | Report failures. Ask user: fix now or proceed anyway? |\n| Any boundary VIOLATED | Report violations. Ask user: fix now or proceed anyway? |\n\n**If user chooses to fix:** Stop review, list specific fixes needed.\n**If user chooses to proceed:** Note the overrides and continue to Stage 2.\n\n\n## Stage 2: Code Quality\n\nRuns stub detection and full code quality review.\n\n### Step 1: Stub Detection\n\nRun 5 checks on all changed files:\n\n```bash\n# Get changed files\nif git diff --cached --name-only 2>\u002Fdev\u002Fnull | head -1 > \u002Fdev\u002Fnull; then\n  changed_files=$(git diff --cached --name-only)\nelif git diff --name-only HEAD~1..HEAD 2>\u002Fdev\u002Fnull | head -1 > \u002Fdev\u002Fnull; then\n  changed_files=$(git diff --name-only HEAD~1..HEAD)\nelse\n  changed_files=$(git diff --name-only)\nfi\n\n# Filter source files\nsource_files=$(echo \"$changed_files\" | grep -E \"\\.(ts|tsx|js|jsx|py|go|rs|sh)$\" || true)\n\nSTUB_ISSUES=0\n\nfor file in $source_files; do\n  [[ -f \"$file\" ]] || continue\n\n  # Check 1: TODO\u002FFIXME\u002FPLACEHOLDER markers\n  todo_count=$(grep -cE \"(TODO|FIXME|PLACEHOLDER|XXX)\" \"$file\" 2>\u002Fdev\u002Fnull || echo \"0\")\n  if [[ \"$todo_count\" -gt 0 ]]; then\n    echo \"WARNING: $file has $todo_count TODO\u002FFIXME markers\"\n    STUB_ISSUES=$((STUB_ISSUES + 1))\n  fi\n\n  # Check 2: Empty function bodies\n  empty_fn=$(grep -cE \"function.*\\{\\s*\\}|=>\\s*\\{\\s*\\}\" \"$file\" 2>\u002Fdev\u002Fnull || echo \"0\")\n  if [[ \"$empty_fn\" -gt 0 ]]; then\n    echo \"ERROR: $file has $empty_fn empty functions\"\n    STUB_ISSUES=$((STUB_ISSUES + 1))\n  fi\n\n  # Check 3: Suspicious null\u002Fundefined returns\n  null_ret=$(grep -cE \"return (null|undefined);\" \"$file\" 2>\u002Fdev\u002Fnull || echo \"0\")\n  if [[ \"$null_ret\" -gt 0 ]]; then\n    echo \"WARNING: $file has $null_ret null\u002Fundefined returns — verify intentional\"\n    STUB_ISSUES=$((STUB_ISSUES + 1))\n  fi\n\n  # Check 4: Substantive line count\n  subst_lines=$(grep -cvE \"^\\s*(\u002F\u002F|\u002F\\*|\\*|#|import|export|$)\" \"$file\" 2>\u002Fdev\u002Fnull || echo \"0\")\n  if [[ \"$subst_lines\" -lt 5 ]]; then\n    echo \"WARNING: $file has only $subst_lines substantive lines\"\n    STUB_ISSUES=$((STUB_ISSUES + 1))\n  fi\n\n  # Check 5: Mock\u002Ftest data in production code\n  mock_count=$(grep -cE \"const.*(mock|test|dummy|fake).*=\" \"$file\" 2>\u002Fdev\u002Fnull || echo \"0\")\n  if [[ \"$mock_count\" -gt 0 ]]; then\n    echo \"WARNING: $file has $mock_count mock\u002Ftest data references\"\n    STUB_ISSUES=$((STUB_ISSUES + 1))\n  fi\ndone\n\necho \"Stub detection complete: $STUB_ISSUES issues found\"\n```\n\n### Step 2: Multi-LLM Quality Review (RECOMMENDED)\n\n**After stub detection, dispatch code to multiple providers for parallel quality review.** A Claude-only review pipeline misses what external models catch — Codex excels at logic errors and correctness, while Antigravity provides an independent security and edge-case analysis. Using both produces higher-confidence findings.\n\n**Check provider availability and dispatch in parallel:**\n\n```bash\n# Get the diff for review\nDIFF_CONTENT=$(git diff --cached 2>\u002Fdev\u002Fnull || git diff HEAD~1..HEAD 2>\u002Fdev\u002Fnull || git diff)\n```\n\n**If external providers are available — dispatch focused reviews through Octopus routing:**\n```bash\nproviders=()\ncommand -v codex >\u002Fdev\u002Fnull 2>&1 && providers+=(codex)\ncommand -v agy >\u002Fdev\u002Fnull 2>&1 && providers+=(agy)\n\nfor provider in \"${providers[@]}\"; do\n  safe_provider=$(printf '%s' \"$provider\" | tr -c '[:alnum:]_-' '_')\n  \"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Forchestrate.sh\" spawn \"$provider\" \\\n    \"Review this code diff for LOGIC, CORRECTNESS, and SECURITY issues. Focus on:\n1. Logic bugs and off-by-one errors\n2. Unhandled error paths\n3. Race conditions or concurrency issues\n4. Incorrect type handling or implicit coercions\n5. Security issues at trust boundaries\n\nReport ONLY high-confidence issues. Do NOT flag style preferences.\n\nDIFF:\n${DIFF_CONTENT}\" > \"\u002Ftmp\u002Foctopus-review-${safe_provider}.md\" 2>\u002Fdev\u002Fnull &\ndone\n```\n\n**Wait for external reviews to complete, then synthesize all findings from Claude plus available external providers into a unified quality assessment.** If external providers are unavailable, fall back to the Claude-only review below.\n\n**Claude (you) performs the full quality review regardless:**\n\n1. **Architecture alignment** — Does the code follow project patterns?\n2. **Error handling** — Are errors caught and handled appropriately?\n3. **Security** — Any OWASP Top 10 issues?\n4. **Performance** — Any obvious bottlenecks or N+1 queries?\n5. **Readability** — Clear naming, reasonable complexity?\n6. **Test coverage** — Are new behaviors tested?\n\n**Synthesize external findings:** If external providers returned results, merge their findings with yours. Where providers disagree on severity, note the divergence. Where multiple providers flag the same issue, mark it as high-confidence.\n\n### Step 3: Present Stage 2 Results\n\n```markdown\n## Stage 2: Code Quality\n\n### Stub Detection\n- Files scanned: N\n- Issues found: N\n- [Details of each issue]\n\n### Quality Review\n- Architecture: [PASS\u002FWARN\u002FFAIL]\n- Error Handling: [PASS\u002FWARN\u002FFAIL]\n- Security: [PASS\u002FWARN\u002FFAIL]\n- Performance: [PASS\u002FWARN\u002FFAIL]\n- Readability: [PASS\u002FWARN\u002FFAIL]\n- Test Coverage: [PASS\u002FWARN\u002FFAIL]\n\n### Blocking Issues\n[List any issues that must be fixed before merge]\n\n### Recommendations\n[Non-blocking suggestions for improvement]\n```\n\n\n## Combined Report\n\nAfter both stages complete, present the unified report:\n\n```markdown\n## Staged Review — Complete\n\n### Stage 1: Spec Compliance\n- Success Criteria: N\u002FN passed\n- Boundaries: N\u002FN respected\n- Verdict: [PASS\u002FFAIL]\n\n### Stage 2: Code Quality\n- Stub Detection: N issues\n- Quality Score: [HIGH\u002FMEDIUM\u002FLOW]\n- Blocking Issues: N\n- Verdict: [PASS\u002FFAIL]\n\n### Overall Verdict: [PASS\u002FFAIL]\n\n[If FAIL: list specific items that must be addressed]\n[If PASS: ready for merge\u002Fship]\n```\n\n\n## When to Use Each Review Type\n\n| Review Type | When | What It Checks |\n|-------------|------|----------------|\n| **skill-code-review** | Quick PR review | Code quality only |\n| **skill-staged-review** | Major feature completion | Spec compliance + code quality |\n| **skill-verification-gate** | Before any completion claim | Evidence of passing |\n\n\n## Error Handling\n\n| Error | Resolution |\n|-------|------------|\n| No intent contract | Skip Stage 1, warn user, run Stage 2 only |\n| No changed files | Report nothing to review |\n| Git not available | Use file listing instead of git diff |\n| Stage 1 failures | Ask user: fix or override |\n| Stage 2 blocking issues | Must fix before merge |\n\n\n## The Bottom Line\n\n```\nStaged Review = Spec Compliance (Stage 1) + Code Quality (Stage 2)\nStage 1 gates Stage 2. Both must pass for overall PASS.\n```\n\n**Build the right thing, then build it right.**\n\n\n## Post Results to PR (v8.44.0)\n\nAfter the combined report is generated, check for an open PR and post findings.\n\n```bash\n# Detect open PR on current branch\nCURRENT_BRANCH=$(git rev-parse --abbrev-ref HEAD 2>\u002Fdev\u002Fnull || echo \"\")\nPR_NUM=\"\"\n\nif [[ -n \"$CURRENT_BRANCH\" && \"$CURRENT_BRANCH\" != \"main\" && \"$CURRENT_BRANCH\" != \"master\" ]]; then\n    if command -v gh &>\u002Fdev\u002Fnull; then\n        PR_NUM=$(gh pr list --head \"$CURRENT_BRANCH\" --json number --jq '.[0].number' 2>\u002Fdev\u002Fnull || echo \"\")\n    fi\nfi\n\nif [[ -n \"$PR_NUM\" ]]; then\n    # Post combined report through the outbound credential gate.\n    REPO_SLUG=$(gh repo view --json nameWithOwner --jq .nameWithOwner)\n    COMMENT_BODY=\"## Staged Review — Claude Octopus\n\n${COMBINED_REPORT}\n\n*Staged review by Claude Octopus (\u002Focto:staged-review)*\"\n    if ! \"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Fsafe-gh-comment.sh\" \\\n            --repo \"$REPO_SLUG\" pr-comment \"$PR_NUM\" - \u003C\u003C\u003C \"$COMMENT_BODY\"; then\n        echo \"GitHub write state is unknown; check for the staged review comment before retrying:\" >&2\n        gh pr view \"$PR_NUM\" --repo \"$REPO_SLUG\" --comments || true\n        return 1 2>\u002Fdev\u002Fnull || exit 1\n    fi\n\n    echo \"Staged review posted to PR #${PR_NUM}\"\nfi\n```\n\n**Behavior:**\n- Auto-posts when running inside `\u002Focto:deliver` or `\u002Focto:embrace` workflows\n- Asks user first when invoked standalone via `\u002Focto:staged-review`\n","> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.\n> Cross-reference commands use installed skill names in Codex rather than `\u002Focto:*` slash commands.\n> Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it.\n> For host tool equivalents, see `skills\u002Fblocks\u002Fcodex-host-adapter.md`.\n\n\n## Execution Contract (MANDATORY - CANNOT SKIP)\n\nThis generated Codex skill preserves an enforced workflow contract from the source skill.\n\n**PROHIBITED:**\n- Do not summarize, simulate, or skip the referenced workflow command when this skill requires execution.\n- Do not claim provider output or validation artifacts exist without checking the actual files or command output.\n- Do not continue silently when a required provider, command, or host capability is unavailable; report the unavailable dependency and use a supported fallback.\n\n\n# Two-Stage Review Pipeline\n\nSeparates **spec compliance** (did you build the right thing?) from **code quality**\n(did you build it right?). Stage 1 must pass before Stage 2 runs.\n\n\n## Stage 1: Spec Compliance\n\nValidates the implementation against the intent contract.\n\n### Step 1: Load Intent Contract\n\n```bash\nPLAN_STORAGE=\"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Fplan-storage.sh\"\nOCTO_PLAN_DIR=\"$(\"$PLAN_STORAGE\" current \"$PWD\" 2>\u002Fdev\u002Fnull || true)\"\nINTENT_FILE=\"${OCTO_PLAN_DIR:+${OCTO_PLAN_DIR}\u002Fsession-intent.md}\"\nif [[ -f \"$INTENT_FILE\" ]]; then\n  echo \"Intent contract found: $INTENT_FILE\"\n  cat \"$INTENT_FILE\"\nelse\n  echo \"WARNING: No current resolved intent contract found for this workspace\"\n  echo \"Skipping Stage 1 — proceeding to Stage 2 (code quality) only.\"\nfi\n```\n\n**If no intent contract exists:** Warn the user and skip to Stage 2. Do NOT fabricate\nsuccess criteria — the contract must exist from a prior workflow.\n\n### Step 2: Validate Success Criteria\n\nFor each success criterion in the intent contract:\n\n1. **Read the criterion** from the `## Success Criteria` section\n2. **Find evidence** in the codebase that the criterion is met\n3. **Mark status:**\n   - `[PASS]` — Evidence confirms criterion is met\n   - `[FAIL]` — Evidence shows criterion is NOT met\n   - `[PARTIAL]` — Partially met, gaps identified\n\nPresent results:\n\n```markdown\n## Stage 1: Spec Compliance\n\n### Success Criteria Check\n\n#### Good Enough Criteria\n- [PASS] Criterion 1: \u003Chow it was met>\n- [FAIL] Criterion 2: \u003Cwhy not met, what's missing>\n\n#### Exceptional Criteria\n- [PARTIAL] Criterion 1: \u003Cwhat's done, what's remaining>\n```\n\n### Step 3: Validate Boundaries\n\nFor each boundary in the intent contract:\n\n1. **Read the boundary** from the `## Boundaries` section\n2. **Check for violations** in the implementation\n3. **Mark status:**\n   - `[RESPECTED]` — No violations found\n   - `[VIOLATED]` — Implementation crosses the boundary\n\n```markdown\n### Boundary Check\n- [RESPECTED] Boundary 1: \u003Cconfirmation>\n- [VIOLATED] Boundary 2: \u003Cwhat violated it>\n```\n\n### Step 4: Stage 1 Gate\n\n| Result | Action |\n|--------|--------|\n| All criteria PASS + all boundaries RESPECTED | Proceed to Stage 2 |\n| Any criterion FAIL | Report failures. Ask user: fix now or proceed anyway? |\n| Any boundary VIOLATED | Report violations. Ask user: fix now or proceed anyway? |\n\n**If user chooses to fix:** Stop review, list specific fixes needed.\n**If user chooses to proceed:** Note the overrides and continue to Stage 2.\n\n\n## Stage 2: Code Quality\n\nRuns stub detection and full code quality review.\n\n### Step 1: Stub Detection\n\nRun 5 checks on all changed files:\n\n```bash\n# Get changed files\nif git diff --cached --name-only 2>\u002Fdev\u002Fnull | head -1 > \u002Fdev\u002Fnull; then\n  changed_files=$(git diff --cached --name-only)\nelif git diff --name-only HEAD~1..HEAD 2>\u002Fdev\u002Fnull | head -1 > \u002Fdev\u002Fnull; then\n  changed_files=$(git diff --name-only HEAD~1..HEAD)\nelse\n  changed_files=$(git diff --name-only)\nfi\n\n# Filter source files\nsource_files=$(echo \"$changed_files\" | grep -E \"\\.(ts|tsx|js|jsx|py|go|rs|sh)$\" || true)\n\nSTUB_ISSUES=0\n\nfor file in $source_files; do\n  [[ -f \"$file\" ]] || continue\n\n  # Check 1: TODO\u002FFIXME\u002FPLACEHOLDER markers\n  todo_count=$(grep -cE \"(TODO|FIXME|PLACEHOLDER|XXX)\" \"$file\" 2>\u002Fdev\u002Fnull || echo \"0\")\n  if [[ \"$todo_count\" -gt 0 ]]; then\n    echo \"WARNING: $file has $todo_count TODO\u002FFIXME markers\"\n    STUB_ISSUES=$((STUB_ISSUES + 1))\n  fi\n\n  # Check 2: Empty function bodies\n  empty_fn=$(grep -cE \"function.*\\{\\s*\\}|=>\\s*\\{\\s*\\}\" \"$file\" 2>\u002Fdev\u002Fnull || echo \"0\")\n  if [[ \"$empty_fn\" -gt 0 ]]; then\n    echo \"ERROR: $file has $empty_fn empty functions\"\n    STUB_ISSUES=$((STUB_ISSUES + 1))\n  fi\n\n  # Check 3: Suspicious null\u002Fundefined returns\n  null_ret=$(grep -cE \"return (null|undefined);\" \"$file\" 2>\u002Fdev\u002Fnull || echo \"0\")\n  if [[ \"$null_ret\" -gt 0 ]]; then\n    echo \"WARNING: $file has $null_ret null\u002Fundefined returns — verify intentional\"\n    STUB_ISSUES=$((STUB_ISSUES + 1))\n  fi\n\n  # Check 4: Substantive line count\n  subst_lines=$(grep -cvE \"^\\s*(\u002F\u002F|\u002F\\*|\\*|#|import|export|$)\" \"$file\" 2>\u002Fdev\u002Fnull || echo \"0\")\n  if [[ \"$subst_lines\" -lt 5 ]]; then\n    echo \"WARNING: $file has only $subst_lines substantive lines\"\n    STUB_ISSUES=$((STUB_ISSUES + 1))\n  fi\n\n  # Check 5: Mock\u002Ftest data in production code\n  mock_count=$(grep -cE \"const.*(mock|test|dummy|fake).*=\" \"$file\" 2>\u002Fdev\u002Fnull || echo \"0\")\n  if [[ \"$mock_count\" -gt 0 ]]; then\n    echo \"WARNING: $file has $mock_count mock\u002Ftest data references\"\n    STUB_ISSUES=$((STUB_ISSUES + 1))\n  fi\ndone\n\necho \"Stub detection complete: $STUB_ISSUES issues found\"\n```\n\n### Step 2: Multi-LLM Quality Review (RECOMMENDED)\n\n**After stub detection, dispatch code to multiple providers for parallel quality review.** A Claude-only review pipeline misses what external models catch — Codex excels at logic errors and correctness, while Antigravity provides an independent security and edge-case analysis. Using both produces higher-confidence findings.\n\n**Check provider availability and dispatch in parallel:**\n\n```bash\n# Get the diff for review\nDIFF_CONTENT=$(git diff --cached 2>\u002Fdev\u002Fnull || git diff HEAD~1..HEAD 2>\u002Fdev\u002Fnull || git diff)\n```\n\n**If external providers are available — dispatch focused reviews through Octopus routing:**\n```bash\nproviders=()\ncommand -v codex >\u002Fdev\u002Fnull 2>&1 && providers+=(codex)\ncommand -v agy >\u002Fdev\u002Fnull 2>&1 && providers+=(agy)\n\nfor provider in \"${providers[@]}\"; do\n  safe_provider=$(printf '%s' \"$provider\" | tr -c '[:alnum:]_-' '_')\n  \"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Forchestrate.sh\" spawn \"$provider\" \\\n    \"Review this code diff for LOGIC, CORRECTNESS, and SECURITY issues. Focus on:\n1. Logic bugs and off-by-one errors\n2. Unhandled error paths\n3. Race conditions or concurrency issues\n4. Incorrect type handling or implicit coercions\n5. Security issues at trust boundaries\n\nReport ONLY high-confidence issues. Do NOT flag style preferences.\n\nDIFF:\n${DIFF_CONTENT}\" > \"\u002Ftmp\u002Foctopus-review-${safe_provider}.md\" 2>\u002Fdev\u002Fnull &\ndone\n```\n\n**Wait for external reviews to complete, then synthesize all findings from Claude plus available external providers into a unified quality assessment.** If external providers are unavailable, fall back to the Claude-only review below.\n\n**Claude (you) performs the full quality review regardless:**\n\n1. **Architecture alignment** — Does the code follow project patterns?\n2. **Error handling** — Are errors caught and handled appropriately?\n3. **Security** — Any OWASP Top 10 issues?\n4. **Performance** — Any obvious bottlenecks or N+1 queries?\n5. **Readability** — Clear naming, reasonable complexity?\n6. **Test coverage** — Are new behaviors tested?\n\n**Synthesize external findings:** If external providers returned results, merge their findings with yours. Where providers disagree on severity, note the divergence. Where multiple providers flag the same issue, mark it as high-confidence.\n\n### Step 3: Present Stage 2 Results\n\n```markdown\n## Stage 2: Code Quality\n\n### Stub Detection\n- Files scanned: N\n- Issues found: N\n- [Details of each issue]\n\n### Quality Review\n- Architecture: [PASS\u002FWARN\u002FFAIL]\n- Error Handling: [PASS\u002FWARN\u002FFAIL]\n- Security: [PASS\u002FWARN\u002FFAIL]\n- Performance: [PASS\u002FWARN\u002FFAIL]\n- Readability: [PASS\u002FWARN\u002FFAIL]\n- Test Coverage: [PASS\u002FWARN\u002FFAIL]\n\n### Blocking Issues\n[List any issues that must be fixed before merge]\n\n### Recommendations\n[Non-blocking suggestions for improvement]\n```\n\n\n## Combined Report\n\nAfter both stages complete, present the unified report:\n\n```markdown\n## Staged Review — Complete\n\n### Stage 1: Spec Compliance\n- Success Criteria: N\u002FN passed\n- Boundaries: N\u002FN respected\n- Verdict: [PASS\u002FFAIL]\n\n### Stage 2: Code Quality\n- Stub Detection: N issues\n- Quality Score: [HIGH\u002FMEDIUM\u002FLOW]\n- Blocking Issues: N\n- Verdict: [PASS\u002FFAIL]\n\n### Overall Verdict: [PASS\u002FFAIL]\n\n[If FAIL: list specific items that must be addressed]\n[If PASS: ready for merge\u002Fship]\n```\n\n\n## When to Use Each Review Type\n\n| Review Type | When | What It Checks |\n|-------------|------|----------------|\n| **skill-code-review** | Quick PR review | Code quality only |\n| **skill-staged-review** | Major feature completion | Spec compliance + code quality |\n| **skill-verification-gate** | Before any completion claim | Evidence of passing |\n\n\n## Error Handling\n\n| Error | Resolution |\n|-------|------------|\n| No intent contract | Skip Stage 1, warn user, run Stage 2 only |\n| No changed files | Report nothing to review |\n| Git not available | Use file listing instead of git diff |\n| Stage 1 failures | Ask user: fix or override |\n| Stage 2 blocking issues | Must fix before merge |\n\n\n## The Bottom Line\n\n```\nStaged Review = Spec Compliance (Stage 1) + Code Quality (Stage 2)\nStage 1 gates Stage 2. Both must pass for overall PASS.\n```\n\n**Build the right thing, then build it right.**\n\n\n## Post Results to PR (v8.44.0)\n\nAfter the combined report is generated, check for an open PR and post findings.\n\n```bash\n# Detect open PR on current branch\nCURRENT_BRANCH=$(git rev-parse --abbrev-ref HEAD 2>\u002Fdev\u002Fnull || echo \"\")\nPR_NUM=\"\"\n\nif [[ -n \"$CURRENT_BRANCH\" && \"$CURRENT_BRANCH\" != \"main\" && \"$CURRENT_BRANCH\" != \"master\" ]]; then\n    if command -v gh &>\u002Fdev\u002Fnull; then\n        PR_NUM=$(gh pr list --head \"$CURRENT_BRANCH\" --json number --jq '.[0].number' 2>\u002Fdev\u002Fnull || echo \"\")\n    fi\nfi\n\nif [[ -n \"$PR_NUM\" ]]; then\n    # Post combined report through the outbound credential gate.\n    REPO_SLUG=$(gh repo view --json nameWithOwner --jq .nameWithOwner)\n    COMMENT_BODY=\"## Staged Review — Claude Octopus\n\n${COMBINED_REPORT}\n\n*Staged review by Claude Octopus (\u002Focto:staged-review)*\"\n    if ! \"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Fsafe-gh-comment.sh\" \\\n            --repo \"$REPO_SLUG\" pr-comment \"$PR_NUM\" - \u003C\u003C\u003C \"$COMMENT_BODY\"; then\n        echo \"GitHub write state is unknown; check for the staged review comment before retrying:\" >&2\n        gh pr view \"$PR_NUM\" --repo \"$REPO_SLUG\" --comments || true\n        return 1 2>\u002Fdev\u002Fnull || exit 1\n    fi\n\n    echo \"Staged review posted to PR #${PR_NUM}\"\nfi\n```\n\n**Behavior:**\n- Auto-posts when running inside `\u002Focto:deliver` or `\u002Focto:embrace` workflows\n- Asks user first when invoked standalone via `\u002Focto:staged-review`\n",{"name":5,"description":7,"disable-model-invocation":47},true,"main","f620abaff09061f8c8b1f1559dca3fdd031a32e5","plugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-staged-review",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":47},[60,63,66],{"tool":61,"command":62},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-staged-review",{"tool":64,"command":65},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-staged-review",{"tool":67,"command":68},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-staged-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-staged-review\u002FSKILL.md",[71],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"agents\u002Fopenai.yaml","REFERENCE","参考文档",166,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-staged-review\u002Fagents\u002Fopenai.yaml",[78,88,96,104,112,120],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":87},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":87},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":87},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":108,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":87},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":116,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":87},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":124,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":87},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]