04-audit — Claude Code skill: what it does, how to install
04-audit is a Claude Code skill that audits a codebase across seven quality pillars and produces a ranked report without changing code.
MIT ★ 571 updated 2026-10-29
/plugin marketplace add ai-driven-dev/framework
/plugin install aidd-dev@aidd-frameworkWhat 04-audit does
The skill diagnoses repositories in read-only mode across seven specific areas: code quality, architecture, security, dependencies, performance, tests, and UI. Each identified issue receives a severity level, a direct file:line reference, an explanation, an effort estimate, and a suggested resolution.
All audit findings are stored inside aidd_docs/tasks/<yyyy_mm>/<yyyy_mm_dd>_audit/. Each evaluated pillar writes its findings to <pillar>.md, while a full run compiles an aggregated report.md containing a unified table and top action items. If you submit a prompt without a specific target, the agent stops to ask whether to check one pillar or all seven.
Because the skill is strictly read-only, it will not edit files or implement fixes.
What it helps with
- Audit project source code for OWASP security flaws and secrets
- Detect performance bottlenecks like N+1 queries and heavy operations
- Evaluate test pyramid balance and critical-path coverage
- Generate a ranked report of technical debt with file locations and effort estimates
Example prompts for the agent
- Run a security audit on this codebase
- Audit architecture and check boundaries against our ADRs
- Perform a full quality audit across all pillars
How to install 04-audit
1Plugin marketplace
/plugin marketplace add ai-driven-dev/framework/plugin install aidd-dev@aidd-frameworkThis installs the whole aidd-dev plugin with all its skills
2Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 04-audit -a claude-code3Manually: put the files in place
~/.claude/skills/04-audit/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/04-audit/
1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 04-audit -a codex2Manually: put the files in place
.agents/skills/04-audit/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 04-audit -a cursor2Manually: put the files in place
.cursor/skills/04-audit/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ai-driven-dev/framework plugins/aidd-dev/skills/04-audit2Manually: put the files in place
.github/skills/04-audit/SKILL.md1Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 04-audit -a gemini-cli2Platform CLI
gemini skills install https://github.com/ai-driven-dev/framework --path plugins/aidd-dev/skills/04-auditManually: put the files in place
.devin/skills/04-audit/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add ai-driven-dev/framework --skill 04-audit -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about 04-audit
How to install 04-audit in Claude Code?
In Claude Code, run /plugin marketplace add ai-driven-dev/framework followed by /plugin install aidd-dev@aidd-framework.
What does the 04-audit skill do?
It inspects codebases across seven quality pillars to produce ranked Markdown reports without changing any project files.
Can 04-audit apply automated code fixes?
No. It operates exclusively in read-only mode to locate, rank, and document problems rather than fix them.
Source text
SKILL.md · MIT
--- name: 04-audit description: Audit a codebase read-only across seven quality pillars into one ranked report. Use when the user wants to assess, health-check, or audit a codebase or one pillar. Not for fixing findings, reviewing a change, or checking a feature works. argument-hint: scope | pillar --- # Skill: audit Diagnose a codebase against quality pillars and emit one ranked findings report. Read-only: it identifies and ranks problems, never changes code. ## Actions | # | Action | Pillar | Lens | | --- | -------------- | ------------ | -------------------------------------------------------------------- | | 01 | `code-quality` | code-quality | Clean code (naming, SOLID, DRY, readability, smells) and tech debt (dead code, complexity, file/function size, error handling) | | 02 | `architecture` | architecture | Conformance to C4 / ADRs, coupling, boundaries, layering | | 03 | `security` | security | OWASP risks, authz, input validation, secrets in code | | 04 | `dependencies` | dependencies | CVEs, licenses, outdated and unused deps, supply chain | | 05 | `performance` | performance | N+1 queries, hot paths, bundle size, heavy operations | | 06 | `tests` | tests | Critical-path coverage, flakiness, test pyramid balance | | 07 | `ui` | ui | Loading/error/empty states, visual hierarchy, design-system drift, responsive, a11y | Run the one pillar named, or offer all seven when the request is unscoped. Before running an action, read its file in `actions/`, not only the table or assets. ## Transversal rules - Read-only: diagnose and rank, never edit code. - Scope: run the one named pillar, or for an unscoped request ask once "all seven pillars, or one?" before running. Never silently default to one pillar, never blind-run all without offering the choice. - One folder per run, `aidd_docs/tasks/<yyyy_mm>/<yyyy_mm_dd>_audit/`, like a feature folder. Every pillar that runs always writes its own `<pillar>.md` there, alone or in a full run. A full run additionally writes a merged `report.md`: one Findings table (category = pillar, severity-first), one Top-actions list, and one Coverage section over all seven pillars. - Unscannable pillar: skip it, record it under `Coverage > Skipped` with the reason, and never invent findings for it. - Every finding row carries a severity, its pillar, a concrete `file:line`, the issue, a suggested fix, and an effort. ## Assets - `assets/audit-template.md`: the report structure both run modes fill.
© AI-Driven Dev · MIT · ai-driven-dev/framework