# Reaudit

> Use when the user types /reaudit or asks to verify that security fixes have been applied, re-audit a codebase after fixes, or check whether previous audit findings are resolved. Shortcut for code-security-audit Phase 4 (re-audit verification). Triggers on "/reaudit", "re-audit", "verify fixes", "再审计", "检查修复", "确认修复". Also enables lightweight state tracking: /reaudit mark-fixed <ID>, /reaudit mark…

- **Type:** Skill
- **Install:** `agentstack add skill-azzygoatcoder-claude-useful-skills-reaudit`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Azzygoatcoder](https://agentstack.voostack.com/s/azzygoatcoder)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Azzygoatcoder](https://github.com/Azzygoatcoder)
- **Source:** https://github.com/Azzygoatcoder/claude-useful-skills/tree/master/code-security-skills/skills/reaudit

## Install

```sh
agentstack add skill-azzygoatcoder-claude-useful-skills-reaudit
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# /reaudit — Verify Security Fixes & State Tracking

Three modes of operation:

| Command | Action | Reads files? |
|---------|--------|-------------|
| `/reaudit` | Full incremental re-audit (Phase 4) | Only changed files |
| `/reaudit mark-fixed ` | Lightweight: mark finding as fixed | No |
| `/reaudit mark-deferred ` | Lightweight: mark as structurally deferred | No |
| `/reaudit status` | Show fix progress summary | No (scans annotations) |

---

## Mode 1: Full Re-Audit (`/reaudit`)

Load and follow `code-security-audit` Phase 4. Key steps:

1. **Parse status annotations** — scan `docs/SECURITY_AUDIT.md` for all `` lines. Extract `FILE`, `LINES`, `STATUS` for each finding.

2. **Diff-filter** — run `git diff --name-only ..HEAD`. Only findings whose `FILE` appears in the diff need re-verification.

3. **Re-verify changed-file findings** — read the file at the flagged location, check fix status:
   - `STATUS=fixed COMMIT=` if fix is in place
   - `STATUS=not-fixed` if still vulnerable
   - `STATUS=partial` if partially addressed

4. **Skip unchanged-file findings** — keep current STATUS, don't re-read.

5. **Check for regressions** — scan added lines in the diff for new vulnerability patterns.

6. **Add Re-Audit section** to the report (structure defined in `code-security-audit` Phase 4).

---

## Mode 2: mark-fixed (`/reaudit mark-fixed `)

Lightweight state update. No file reads. Use after committing a fix.

1. Grep the report for `
```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Azzygoatcoder](https://github.com/Azzygoatcoder)
- **Source:** [Azzygoatcoder/claude-useful-skills](https://github.com/Azzygoatcoder/claude-useful-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-azzygoatcoder-claude-useful-skills-reaudit
- Seller: https://agentstack.voostack.com/s/azzygoatcoder
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.