runkids/veto/codebase-audit
- community
Checking that the SKILL.md file is still in the repository.
Cross-validate CLI flags, rules, tests, and integrations for consistency across the veto codebase. Use this skill whenever the user asks to: audit the codebase, check for consistency issues, find undocumented flags, verify test coverage, validate rule definitions, or check integration completeness. This is a read-only audit — it reports issues but never modifies files. Use after large refactors, before releases, or whenever you suspect code has drifted.
Install
npx vskill@latest install runkids/veto/codebase-auditSKILL.md
Read-only consistency audit across the veto codebase. $ARGUMENTS specifies focus area (e.g., "rules", "flags", "tests", "auth") or omit for full audit.
Scope: This skill only READS and REPORTS. It does not modify any files.
Audit Dimensions
Run all dimensions in parallel where possible. For each, produce a summary table.
1. CLI Flag Audit
Compare every flag/subcommand in src/cli/mod.rs against README and --help output.
Report:
- UNDOCUMENTED: Flag exists in code but not in README
- STALE: Flag documented but not in code
- OK: Flag matches
2. Rule Coverage Audit
Validate rules in src/rules/defaults.rs:
Report per risk level (critical, high, medium, low):
- TESTED: Rule pattern has matching test case
- UNTESTED: Rule exists but no test covers it
- ORPHAN: Test references pattern not in defaults
3. Auth Method Audit
Cross-check auth methods across:
src/auth/manager.rs(dispatch)src/cli/mod.rs(--auth flag options)src/commands/auth.rs(auth subcommands)
Report:
- COMPLETE: Auth method registered in all 3 locations
- PARTIAL: Missing from one or more locations
- DEAD: Registered but implementation missing
4. Integration Audit
Check src/commands/setup.rs integrations:
Verify each integration (Claude, Gemini, OpenCode, Cursor) has:
- Setup command handler
- Gate mode support (
--claude,--gemini, etc.) - Uninstall support
Report:
- COMPLETE: Integration fully wired
- PARTIAL: Missing setup/gate/uninstall
- STUB: Defined but not implemented
5. Test Coverage
For each module:
Report:
- COVERED: Module has test section with cases
- PARTIAL: Test section exists but few cases
- MISSING: No tests for this module
6. Shell Wrapper Bypass Audit
Verify bypass detection in src/rules/engine.rs covers known vectors:
| Vector | Expected | |
|---|---|---|
bash -c | Detected | |
sh -c | Detected | |
eval | Detected | |
sudo | Detected | |
xargs | Detected | |
env | Detected | |
pipe to sh/bash | Detected |
Report:
- DETECTED: Bypass vector is handled
- MISSING: Known vector not covered
Output Format
Rules
- Read-only — never modify files, only report
- Evidence-based — every finding must include file path and line number
- No false positives — verify with grep before flagging
- Scope $ARGUMENTS — if user specifies "rules", only run dimension 2
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryChecking.skillshare/skills/codebase-audit/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/runkids/veto/codebase-audit)