{"slug":"code-audit","title":"code-audit","summary":"Reviews a codebase for bugs, design issues, and code cleanliness problems with specific file paths and line numbers. Use when auditing code quality, finding bugs, doing a code review, or reviewing a project for issues. Writes issues to `.issues/`.","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-11-03T17:19:25.416539Z","repo":{"url":"https://github.com/philoserf/claude-code-config","stars":13,"forks":0,"license":"MIT","updatedAt":"2026-11-03T15:40:56Z"},"bodyHtml":"<hr>\n<p>argument-hint: \"[path or scope]\"\nallowed-tools:</p>\n<ul>\n<li>Read</li>\n<li>Grep</li>\n<li>Glob</li>\n<li>Bash</li>\n<li>Write\ndescription: Reviews a codebase for bugs, design issues, and code cleanliness problems with specific file paths and line numbers. Use when auditing code quality, finding bugs, doing a code review, or reviewing a project for issues. Writes issues to <code>.issues/</code>.</li>\n</ul>\n<hr>\n<p>Review this codebase for bugs, design issues, and code cleanliness problems. Be specific and cite file paths and line numbers.</p>\n<p>Scope the review to <code>$ARGUMENTS</code> if provided, otherwise review the entire project. Examples: <code>src/auth/</code>, <code>lib/api.ts</code>, <code>security</code>, <code>tests/</code>.</p>\n<p>Skip vendored dependencies, build output, generated/minified code, and lockfiles (e.g. <code>node_modules/</code>, <code>dist/</code>, <code>build/</code>, <code>vendor/</code>, <code>*.min.js</code>, <code>package-lock.json</code>, <code>go.sum</code>).</p>\n<h2>Output</h2>\n<p>Findings go to <code>.issues/</code> and the overview to <code>.issues/000-audit.md</code>, following\n<a href=\"references/issues-protocol.md\">issues-protocol.md</a> — read it before writing anything. It\nis the canonical copy shared across the <code>code-*</code> review skills, and it defines the\nfile layout, the finding format and severity scale, the dedup checks against <code>.issues/</code> and\nGitHub, and what to do on a re-run.</p>\n<h2>Process</h2>\n<p>Work the protocol's \"Before filing anything\" checks against every candidate finding, then\nfile each surviving one as its own <code>.issues/</code> file in the protocol's format, with\n<code>**Source:** code-audit</code>.</p>\n<p>A bug you find in code another skill has already written about is the case to handle\ndeliberately, not the exception. <code>code-reduction</code> proposing that a function be deleted and\nthis skill finding a null deref inside it are both true; file yours, cross-reference\ntheirs, and say which move you would make first.</p>\n<p>Verify before you claim. A finding whose Description says what you ran and what it printed\nis worth several that assert from reading. Where a fix is checkable by an existing build or\ntest command, name it in <code>## Suggested fix</code>.</p>\n<h2>Overview</h2>\n<p>Write <code>.issues/000-audit.md</code> last, once the findings exist: what you covered, what you ran,\nwhere you stopped, what the set adds up to, and the index table. Report the same index to\nthe caller in the conversation.</p>\n<h2>Do not use when</h2>\n<ul>\n<li>Reviewing harness customizations (skills, hooks, settings) — use <code>/doctor</code></li>\n<li>Reviewing a specific staged or branch diff — use <code>/code-review</code></li>\n<li>The ask is a target design or a migration plan rather than a findings list — use\n<code>code-refactor</code></li>\n</ul>\n","files":[{"path":"references/issues-protocol.md","sizeBytes":9504,"isText":true},{"path":"SKILL.md","sizeBytes":2458,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"human-reviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"human-reviewed","screen":{"ran":true,"outcome":"flagged-cleared-by-moderator","suspicious":1,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-11-03T17:19:39.325059Z","sha256":"9199742DEE9A92FDA8CC15D440BB6C66ECD681C764FE627964AEA8C79585E0B6","sizeBytes":5420},"review":null,"source":{"repositoryUrl":"https://github.com/philoserf/claude-code-config","path":"skills/code-audit","license":"MIT","commit":"b07529914e271105b2b5437b143b0687844a5dc7","subtreeSha":"609EE929A1F4EEF69AB66638006367EFF1A78B0257BD74B0660CEBAAEE1BD94B","lastSyncedAt":"2026-11-03T17:19:25.411274Z"},"reviewedAt":"2026-11-04T18:02:04.755938Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/philoserf/claude-code-config/tree/main/skills/code-audit"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install philoserf-claude-code-config@llmmart"},{"target":"git","command":"git clone https://github.com/philoserf/claude-code-config.git"}]}