[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MK7X4BEAN4SJ4CTPC3NC9V":3,"skill-same:01M6MK7X4BEAN4SJ4CTPC3NC9V":86},{"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":31,"publishedAt":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":62,"ownerHtmlUrl":63,"ownerBlogUrl":64,"ownerDescription":65,"updatedAt":66,"install":67,"resources":79},"01M6MK7X4BEAN4SJ4CTPC3NC9V","skill-code-review",null,"Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis","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-code-review\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"review","code review","code","skill code review","inline","for","true","comments","with","multi","ai code review","expert","use","quality","pr comments","analysis","security analysis","pr","security","2026-11-10 10:12:30",false,"---\nname: skill-code-review\ndescription: \"Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis\"\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# Code Review Skill\n\n## MANDATORY COMPLIANCE — DO NOT SKIP\n\n**When this skill is invoked, you MUST execute the multi-LLM review pipeline. You are PROHIBITED from:**\n- Doing a direct single-model code review without multi-provider synthesis\n- Deciding the scope is \"too broad\" and narrowing it without asking the user\n- Skipping the provider check or structured review phases\n- Substituting two background Sonnet agents for the full multi-provider pipeline\n- Rationalizing \"a focused audit would be more effective\" — the user wants multi-LLM perspectives\n\n\n**Your first output line MUST be:** `🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-LLM Code Review`\n\nInvokes the code-reviewer persona for thorough code analysis during the `ink` (deliver) phase.\n\n## Quick Mode\n\nFor fast sanity checks (staged changes, small PRs), skip the full review pipeline and run just two phases:\n\n```bash\n# Quick: grasp (consensus on scope) → tangle (parallel review)\n\"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Forchestrate.sh\" grasp \"[review request]\"\n\"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Forchestrate.sh\" tangle \"[synthesized scope]\"\n```\n\nUse quick mode when user says \"check this PR\", \"quick review\", \"sanity check my changes\", or for pre-commit checks. Use the full review for PRs with security\u002Farchitecture impact.\n\n## Usage\n\n```bash\n# Via orchestrate.sh\n\"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Forchestrate.sh\" spawn code-reviewer \"Review this pull request for security issues\"\n\n# Via auto-routing (detects review intent)\n\"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Forchestrate.sh\" auto \"review the authentication implementation\"\n```\n\n## Capabilities\n\n- AI-powered code quality analysis\n- Security vulnerability detection\n- Performance optimization suggestions\n- Architecture and design pattern review\n- TDD compliance and test-first evidence review\n- Autonomous code generation risk detection\n- Best practices enforcement\n\n## Persona Reference\n\nThis skill wraps the `code-reviewer` persona defined in:\n- `agents\u002Fpersonas\u002Fcode-reviewer.md`\n- CLI: `codex-review`\n- Model: `gpt-5.2-codex`\n- Phases: `ink`\n\n## Example Prompts\n\n```\n\"Review this PR for OWASP Top 10 vulnerabilities\"\n\"Analyze the error handling in src\u002Fapi\u002F\"\n\"Check for memory leaks in the connection pool\"\n\"Review the test coverage for the auth module\"\n```\n\n\n## Autonomous Implementation Review\n\nWhen the review context indicates `AI-assisted`, `Autonomous \u002F Dark Factory`, or unclear provenance, raise the rigor bar. Do not treat generated code as trustworthy just because it is polished.\n\n### TDD Evidence\n\nCheck for concrete signs that the change followed red-green-refactor rather than test-after implementation:\n\n- Compare the diff and recent history when available to see whether tests were added before or alongside production changes.\n- Prefer behavior-defining tests over snapshot-only or mock-heavy tests that merely restate the implementation.\n- Verify the production code looks like the minimum needed to satisfy the tests, rather than a speculative abstraction with unused options.\n- If evidence is missing, mark TDD compliance as unknown and do not assume TDD happened.\n\n### Autonomous Codegen Risk Patterns\n\nElevate or add findings when you see patterns common in high-autonomy output:\n\n- Option-heavy APIs or abstractions not justified by tests or current requirements\n- Placeholder logic, TODO\u002FFIXME-driven control flow, or dead branches that appear \"future ready\"\n- Mock, fake, or dummy behavior leaking into production paths\n- Unwired components, unused helpers, or code that exists without an execution path\n- Silent failure handling, broad catch blocks, missing logs, or weak operational visibility\n- Missing rollback notes, migration guards, or release-safety checks for risky changes\n\n### Review Output Addendum\n\nAdd a short section to the review synthesis when autonomy or TDD is in scope:\n\n```markdown\n## TDD \u002F Autonomy Assessment\n\n- Provenance: Human-authored | AI-assisted | Autonomous \u002F Dark Factory | Unknown\n- TDD evidence: Confirmed | Partial | Unknown\n- Autonomous risk signals: None | Minor | Significant\n- Recommendation: Ship | Fix before merge | Re-run with \u002Focto:tdd or tighter supervision\n```\n\n\n## Implementation Completeness Verification\n\nAfter the code-reviewer persona completes, run stub detection to verify implementation completeness.\n\n### Stub Detection Process\n\n**Step 1: Get changed files**\n\n```bash\n# Get files changed in the commit\u002FPR\nif [ -n \"$COMMIT_RANGE\" ]; then\n    changed_files=$(git diff --name-only \"$COMMIT_RANGE\")\nelse\n    changed_files=$(git diff --name-only HEAD~1..HEAD)\nfi\n\n# Filter for source code files\nsource_files=$(echo \"$changed_files\" | grep -E \"\\.(ts|tsx|js|jsx|py|go)$\")\n```\n\n**Step 2: Check for stub patterns**\n\nFor each changed file, check for common stub indicators:\n\n```bash\nfor file in $source_files; do\n    echo \"Checking $file for stubs...\"\n\n    # Check 1: Comment-based stubs\n    stub_count=$(grep -E \"(TODO|FIXME|PLACEHOLDER|XXX)\" \"$file\" 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ')\n\n    if [ \"$stub_count\" -gt 0 ]; then\n        echo \"⚠️  WARNING: Found $stub_count stub indicators in $file\"\n        grep -n -E \"(TODO|FIXME|PLACEHOLDER)\" \"$file\" | head -3\n    fi\n\n    # Check 2: Empty function bodies\n    empty_functions=$(grep -E \"function.*\\{\\s*\\}|const.*=>.*\\{\\s*\\}\" \"$file\" 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ')\n\n    if [ \"$empty_functions\" -gt 0 ]; then\n        echo \"❌ ERROR: Found $empty_functions empty functions in $file\"\n        echo \"   Empty functions must be implemented before merge\"\n    fi\n\n    # Check 3: Return null\u002Fundefined\n    null_returns=$(grep -E \"return (null|undefined);\" \"$file\" 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ')\n\n    if [ \"$null_returns\" -gt 0 ]; then\n        echo \"⚠️  WARNING: Found $null_returns null\u002Fundefined returns in $file\"\n        echo \"   Verify these are intentional, not stubs\"\n    fi\n\n    # Check 4: Substantive content check\n    substantive_lines=$(grep -vE \"^\\s*(\u002F\u002F|\u002F\\*|\\*|import|export|$)\" \"$file\" 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ')\n\n    if [[ \"$file\" == *.tsx ]] && [ \"$substantive_lines\" -lt 10 ]; then\n        echo \"⚠️  WARNING: Component $file only has $substantive_lines substantive lines\"\n        echo \"   Components should typically be >10 lines\"\n    fi\n\n    # Check 5: Mock\u002Ftest data in production\n    mock_data=$(grep -E \"const.*(mock|test|dummy|fake).*=\" \"$file\" 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ')\n\n    if [ \"$mock_data\" -gt 0 ]; then\n        echo \"⚠️  WARNING: Found $mock_data references to mock\u002Ftest data in $file\"\n        echo \"   Ensure these are not placeholders for production code\"\n    fi\ndone\n```\n\n**Step 3: Add findings to review synthesis**\n\nInclude stub detection results in the review output:\n\n```markdown\n## Implementation Completeness\n\n**Stub Detection Results:**\n\n✅ **Fully Implemented Files:**\n- src\u002Fcomponents\u002FUserProfile.tsx (42 substantive lines)\n- src\u002Fapi\u002Fusers.ts (67 substantive lines)\n\n⚠️  **Files with Warnings:**\n- src\u002Fcomponents\u002FDashboard.tsx\n  - 3 TODO comments (non-blocking)\n  - Consider addressing before release\n\n❌ **Files Requiring Implementation:**\n- src\u002Futils\u002Fanalytics.ts\n  - 2 empty functions detected (BLOCKING)\n  - Must implement before merge\n\n**Verification Levels:**\n- Level 1 (Exists): 5\u002F5 files ✅\n- Level 2 (Substantive): 3\u002F5 files ⚠️\n- Level 3 (Wired): 4\u002F5 files ✅\n- Level 4 (Functional): Tests pending\n\n**Recommendation:**\n- Fix empty functions in analytics.ts before merge\n- Address TODO comments in Dashboard.tsx in follow-up PR\n- All other files meet implementation standards\n```\n\n### Stub Detection Reference\n\nSee `.claude\u002Freferences\u002Fstub-detection.md` for comprehensive patterns and detection strategies.\n\n### When to Block Merge\n\n**BLOCKING Issues (must fix):**\n- ❌ Empty function bodies\n- ❌ Mock data in production code paths\n- ❌ Components not imported\u002Fwired anywhere\n- ❌ API endpoints returning empty objects\n\n**NON-BLOCKING Issues (note in review):**\n- ⚠️ TODO\u002FFIXME comments (create follow-up tickets)\n- ⚠️ Null returns (if intentional)\n- ⚠️ Low line count (if appropriate for the component)\n\n\n## Post Review to PR (v8.44.0)\n\nAfter generating the review synthesis, check if the current branch has an open PR and offer to post findings as a PR comment.\n\n### Step 1: Detect Open PR\n\n```bash\n# Check if we're on a branch with an open PR\nCURRENT_BRANCH=$(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 \"$CURRENT_BRANCH\" --json number --jq '.[0].number' 2>\u002Fdev\u002Fnull || echo \"\")\n    fi\nfi\n```\n\n### Step 2: Post Review Comment\n\nIf an open PR exists, post the review findings as a PR comment:\n\n```bash\nif [[ -n \"$PR_NUM\" ]]; then\n    echo \"Found open PR #${PR_NUM} on branch ${CURRENT_BRANCH}\"\n\n    # Build the review comment body from synthesis\n    REVIEW_BODY=\"## Code Review — Claude Octopus\n\n${REVIEW_SYNTHESIS}\n\n*Review generated by Claude Octopus (\u002Focto:review)*\n*Providers: available external providers + 🔵 Claude*\"\n\n    # Post through the outbound credential gate. Never interpolate generated\n    # Markdown directly into a gh shell argument.\n    REPO_SLUG=$(gh repo view --json nameWithOwner --jq .nameWithOwner)\n    if ! \"${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 \"$REVIEW_BODY\"; then\n        echo \"GitHub write state is unknown; check for the review comment before retrying:\" >&2\n        gh pr view \"$PR_NUM\" --repo \"$REPO_SLUG\" --comments || true\n        return 1 2>\u002Fdev\u002Fnull || exit 1\n    fi\n    echo \"Review posted to PR #${PR_NUM}\"\n\n    # Update agent registry if this agent is tracked\n    REGISTRY=\"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Fagent-registry.sh\"\n    if [[ -x \"$REGISTRY\" ]]; then\n        AGENT_ID=$(git rev-parse --abbrev-ref HEAD 2>\u002Fdev\u002Fnull || echo \"\")\n        \"$REGISTRY\" update \"$AGENT_ID\" --pr \"$PR_NUM\" 2>\u002Fdev\u002Fnull || true\n    fi\nfi\n```\n\n**If no PR exists:** Skip posting, present review in terminal only.\n**If `gh` CLI not available:** Skip posting, suggest user install GitHub CLI.\n\n### When to Auto-Post vs Ask\n\n- **Auto-post:** When invoked as part of `\u002Focto:deliver`, `\u002Focto:factory`, or `\u002Focto:embrace` (automated workflows)\n- **Ask first:** When invoked standalone via `\u002Focto:review` — use AskUserQuestion:\n  ```\n  \"PR #N found. Post review findings as a PR comment?\"\n  Options: \"Yes, post to PR\", \"No, terminal only\"\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# Code Review Skill\n\n## MANDATORY COMPLIANCE — DO NOT SKIP\n\n**When this skill is invoked, you MUST execute the multi-LLM review pipeline. You are PROHIBITED from:**\n- Doing a direct single-model code review without multi-provider synthesis\n- Deciding the scope is \"too broad\" and narrowing it without asking the user\n- Skipping the provider check or structured review phases\n- Substituting two background Sonnet agents for the full multi-provider pipeline\n- Rationalizing \"a focused audit would be more effective\" — the user wants multi-LLM perspectives\n\n\n**Your first output line MUST be:** `🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-LLM Code Review`\n\nInvokes the code-reviewer persona for thorough code analysis during the `ink` (deliver) phase.\n\n## Quick Mode\n\nFor fast sanity checks (staged changes, small PRs), skip the full review pipeline and run just two phases:\n\n```bash\n# Quick: grasp (consensus on scope) → tangle (parallel review)\n\"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Forchestrate.sh\" grasp \"[review request]\"\n\"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Forchestrate.sh\" tangle \"[synthesized scope]\"\n```\n\nUse quick mode when user says \"check this PR\", \"quick review\", \"sanity check my changes\", or for pre-commit checks. Use the full review for PRs with security\u002Farchitecture impact.\n\n## Usage\n\n```bash\n# Via orchestrate.sh\n\"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Forchestrate.sh\" spawn code-reviewer \"Review this pull request for security issues\"\n\n# Via auto-routing (detects review intent)\n\"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Forchestrate.sh\" auto \"review the authentication implementation\"\n```\n\n## Capabilities\n\n- AI-powered code quality analysis\n- Security vulnerability detection\n- Performance optimization suggestions\n- Architecture and design pattern review\n- TDD compliance and test-first evidence review\n- Autonomous code generation risk detection\n- Best practices enforcement\n\n## Persona Reference\n\nThis skill wraps the `code-reviewer` persona defined in:\n- `agents\u002Fpersonas\u002Fcode-reviewer.md`\n- CLI: `codex-review`\n- Model: `gpt-5.2-codex`\n- Phases: `ink`\n\n## Example Prompts\n\n```\n\"Review this PR for OWASP Top 10 vulnerabilities\"\n\"Analyze the error handling in src\u002Fapi\u002F\"\n\"Check for memory leaks in the connection pool\"\n\"Review the test coverage for the auth module\"\n```\n\n\n## Autonomous Implementation Review\n\nWhen the review context indicates `AI-assisted`, `Autonomous \u002F Dark Factory`, or unclear provenance, raise the rigor bar. Do not treat generated code as trustworthy just because it is polished.\n\n### TDD Evidence\n\nCheck for concrete signs that the change followed red-green-refactor rather than test-after implementation:\n\n- Compare the diff and recent history when available to see whether tests were added before or alongside production changes.\n- Prefer behavior-defining tests over snapshot-only or mock-heavy tests that merely restate the implementation.\n- Verify the production code looks like the minimum needed to satisfy the tests, rather than a speculative abstraction with unused options.\n- If evidence is missing, mark TDD compliance as unknown and do not assume TDD happened.\n\n### Autonomous Codegen Risk Patterns\n\nElevate or add findings when you see patterns common in high-autonomy output:\n\n- Option-heavy APIs or abstractions not justified by tests or current requirements\n- Placeholder logic, TODO\u002FFIXME-driven control flow, or dead branches that appear \"future ready\"\n- Mock, fake, or dummy behavior leaking into production paths\n- Unwired components, unused helpers, or code that exists without an execution path\n- Silent failure handling, broad catch blocks, missing logs, or weak operational visibility\n- Missing rollback notes, migration guards, or release-safety checks for risky changes\n\n### Review Output Addendum\n\nAdd a short section to the review synthesis when autonomy or TDD is in scope:\n\n```markdown\n## TDD \u002F Autonomy Assessment\n\n- Provenance: Human-authored | AI-assisted | Autonomous \u002F Dark Factory | Unknown\n- TDD evidence: Confirmed | Partial | Unknown\n- Autonomous risk signals: None | Minor | Significant\n- Recommendation: Ship | Fix before merge | Re-run with \u002Focto:tdd or tighter supervision\n```\n\n\n## Implementation Completeness Verification\n\nAfter the code-reviewer persona completes, run stub detection to verify implementation completeness.\n\n### Stub Detection Process\n\n**Step 1: Get changed files**\n\n```bash\n# Get files changed in the commit\u002FPR\nif [ -n \"$COMMIT_RANGE\" ]; then\n    changed_files=$(git diff --name-only \"$COMMIT_RANGE\")\nelse\n    changed_files=$(git diff --name-only HEAD~1..HEAD)\nfi\n\n# Filter for source code files\nsource_files=$(echo \"$changed_files\" | grep -E \"\\.(ts|tsx|js|jsx|py|go)$\")\n```\n\n**Step 2: Check for stub patterns**\n\nFor each changed file, check for common stub indicators:\n\n```bash\nfor file in $source_files; do\n    echo \"Checking $file for stubs...\"\n\n    # Check 1: Comment-based stubs\n    stub_count=$(grep -E \"(TODO|FIXME|PLACEHOLDER|XXX)\" \"$file\" 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ')\n\n    if [ \"$stub_count\" -gt 0 ]; then\n        echo \"⚠️  WARNING: Found $stub_count stub indicators in $file\"\n        grep -n -E \"(TODO|FIXME|PLACEHOLDER)\" \"$file\" | head -3\n    fi\n\n    # Check 2: Empty function bodies\n    empty_functions=$(grep -E \"function.*\\{\\s*\\}|const.*=>.*\\{\\s*\\}\" \"$file\" 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ')\n\n    if [ \"$empty_functions\" -gt 0 ]; then\n        echo \"❌ ERROR: Found $empty_functions empty functions in $file\"\n        echo \"   Empty functions must be implemented before merge\"\n    fi\n\n    # Check 3: Return null\u002Fundefined\n    null_returns=$(grep -E \"return (null|undefined);\" \"$file\" 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ')\n\n    if [ \"$null_returns\" -gt 0 ]; then\n        echo \"⚠️  WARNING: Found $null_returns null\u002Fundefined returns in $file\"\n        echo \"   Verify these are intentional, not stubs\"\n    fi\n\n    # Check 4: Substantive content check\n    substantive_lines=$(grep -vE \"^\\s*(\u002F\u002F|\u002F\\*|\\*|import|export|$)\" \"$file\" 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ')\n\n    if [[ \"$file\" == *.tsx ]] && [ \"$substantive_lines\" -lt 10 ]; then\n        echo \"⚠️  WARNING: Component $file only has $substantive_lines substantive lines\"\n        echo \"   Components should typically be >10 lines\"\n    fi\n\n    # Check 5: Mock\u002Ftest data in production\n    mock_data=$(grep -E \"const.*(mock|test|dummy|fake).*=\" \"$file\" 2>\u002Fdev\u002Fnull | wc -l | tr -d ' ')\n\n    if [ \"$mock_data\" -gt 0 ]; then\n        echo \"⚠️  WARNING: Found $mock_data references to mock\u002Ftest data in $file\"\n        echo \"   Ensure these are not placeholders for production code\"\n    fi\ndone\n```\n\n**Step 3: Add findings to review synthesis**\n\nInclude stub detection results in the review output:\n\n```markdown\n## Implementation Completeness\n\n**Stub Detection Results:**\n\n✅ **Fully Implemented Files:**\n- src\u002Fcomponents\u002FUserProfile.tsx (42 substantive lines)\n- src\u002Fapi\u002Fusers.ts (67 substantive lines)\n\n⚠️  **Files with Warnings:**\n- src\u002Fcomponents\u002FDashboard.tsx\n  - 3 TODO comments (non-blocking)\n  - Consider addressing before release\n\n❌ **Files Requiring Implementation:**\n- src\u002Futils\u002Fanalytics.ts\n  - 2 empty functions detected (BLOCKING)\n  - Must implement before merge\n\n**Verification Levels:**\n- Level 1 (Exists): 5\u002F5 files ✅\n- Level 2 (Substantive): 3\u002F5 files ⚠️\n- Level 3 (Wired): 4\u002F5 files ✅\n- Level 4 (Functional): Tests pending\n\n**Recommendation:**\n- Fix empty functions in analytics.ts before merge\n- Address TODO comments in Dashboard.tsx in follow-up PR\n- All other files meet implementation standards\n```\n\n### Stub Detection Reference\n\nSee `.claude\u002Freferences\u002Fstub-detection.md` for comprehensive patterns and detection strategies.\n\n### When to Block Merge\n\n**BLOCKING Issues (must fix):**\n- ❌ Empty function bodies\n- ❌ Mock data in production code paths\n- ❌ Components not imported\u002Fwired anywhere\n- ❌ API endpoints returning empty objects\n\n**NON-BLOCKING Issues (note in review):**\n- ⚠️ TODO\u002FFIXME comments (create follow-up tickets)\n- ⚠️ Null returns (if intentional)\n- ⚠️ Low line count (if appropriate for the component)\n\n\n## Post Review to PR (v8.44.0)\n\nAfter generating the review synthesis, check if the current branch has an open PR and offer to post findings as a PR comment.\n\n### Step 1: Detect Open PR\n\n```bash\n# Check if we're on a branch with an open PR\nCURRENT_BRANCH=$(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 \"$CURRENT_BRANCH\" --json number --jq '.[0].number' 2>\u002Fdev\u002Fnull || echo \"\")\n    fi\nfi\n```\n\n### Step 2: Post Review Comment\n\nIf an open PR exists, post the review findings as a PR comment:\n\n```bash\nif [[ -n \"$PR_NUM\" ]]; then\n    echo \"Found open PR #${PR_NUM} on branch ${CURRENT_BRANCH}\"\n\n    # Build the review comment body from synthesis\n    REVIEW_BODY=\"## Code Review — Claude Octopus\n\n${REVIEW_SYNTHESIS}\n\n*Review generated by Claude Octopus (\u002Focto:review)*\n*Providers: available external providers + 🔵 Claude*\"\n\n    # Post through the outbound credential gate. Never interpolate generated\n    # Markdown directly into a gh shell argument.\n    REPO_SLUG=$(gh repo view --json nameWithOwner --jq .nameWithOwner)\n    if ! \"${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 \"$REVIEW_BODY\"; then\n        echo \"GitHub write state is unknown; check for the review comment before retrying:\" >&2\n        gh pr view \"$PR_NUM\" --repo \"$REPO_SLUG\" --comments || true\n        return 1 2>\u002Fdev\u002Fnull || exit 1\n    fi\n    echo \"Review posted to PR #${PR_NUM}\"\n\n    # Update agent registry if this agent is tracked\n    REGISTRY=\"${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}\u002F.claude-octopus\u002Fplugin}}\u002Fscripts\u002Fagent-registry.sh\"\n    if [[ -x \"$REGISTRY\" ]]; then\n        AGENT_ID=$(git rev-parse --abbrev-ref HEAD 2>\u002Fdev\u002Fnull || echo \"\")\n        \"$REGISTRY\" update \"$AGENT_ID\" --pr \"$PR_NUM\" 2>\u002Fdev\u002Fnull || true\n    fi\nfi\n```\n\n**If no PR exists:** Skip posting, present review in terminal only.\n**If `gh` CLI not available:** Skip posting, suggest user install GitHub CLI.\n\n### When to Auto-Post vs Ask\n\n- **Auto-post:** When invoked as part of `\u002Focto:deliver`, `\u002Focto:factory`, or `\u002Focto:embrace` (automated workflows)\n- **Ask first:** When invoked standalone via `\u002Focto:review` — use AskUserQuestion:\n  ```\n  \"PR #N found. Post review findings as a PR comment?\"\n  Options: \"Yes, post to PR\", \"No, terminal only\"\n  ```\n",{"name":5,"description":7,"disable-model-invocation":56},true,"main","f620abaff09061f8c8b1f1559dca3fdd031a32e5","plugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-code-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":68,"prompt":78,"zipAvailable":56},[69,72,75],{"tool":70,"command":71},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-code-review",{"tool":73,"command":74},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-code-review",{"tool":76,"command":77},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-code-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-code-review\u002FSKILL.md",[80],{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"agents\u002Fopenai.yaml","REFERENCE","参考文档",170,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-code-review\u002Fagents\u002Fopenai.yaml",[87,97,105,113,121,129],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":96},"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":96},"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":109,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":96},"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":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":117,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":96},"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":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":125,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":96},"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":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":133,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":96},"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",[],[]]