agentmods.dev

reaudit

reaudit is a skill for Claude Code from Azzygoatcoder/agent-useful-skills. It costs 114 tokens per session (920 once invoked), scanned A, original, MIT.

A workflow for checking whether security findings from an earlier audit have been fixed. It compares changed files with the audit record and updates each finding’s status.

In plain words
What is it for?
Re-auditing changed files, marking findings as fixed or deferred, and viewing security-fix progress.
Why use it?
It avoids repeating the entire audit when only certain files changed and makes unresolved or partial fixes visible.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the code-security-skills plugin — 4 skills shipped together

not rated 6repo +2 11d ago A scan 114 tokens original MIT

Good fit Re-auditing changed files, marking findings as fixed or deferred, and viewing security-fix progress.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/azzygoatcoder/agent-useful-skills/reaudit
View source ↗ Azzygoatcoder/agent-useful-skills
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Azzygoatcoder/agent-useful-skills --skill reaudit
Clone the repo
git clone --depth 1 https://github.com/Azzygoatcoder/agent-useful-skills

Made for: Claude Code.

Or install code-security-skills, the plugin that ships this one along with the rest of its 4 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for reaudit

README.md
[![agentmods](https://agentmods.dev/badge/skills/azzygoatcoder/agent-useful-skills/reaudit/github.svg)](https://agentmods.dev/skills/azzygoatcoder/agent-useful-skills/reaudit)
Your own site
<a href="https://agentmods.dev/skills/azzygoatcoder/agent-useful-skills/reaudit"><img src="https://agentmods.dev/badge/skills/azzygoatcoder/agent-useful-skills/reaudit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for reaudit

Your own site · 80×15
<a href="https://agentmods.dev/skills/azzygoatcoder/agent-useful-skills/reaudit"><img src="https://agentmods.dev/badge/skills/azzygoatcoder/agent-useful-skills/reaudit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 920 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00114 $0.00920
Opus 5 $0.00057 $0.00460
Sonnet 5 $0.00023 $0.00184
Haiku 4.5 $0.00011 $0.00092

Measured 9d ago against content hash 03f2486b6f13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reaudit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/code-security-skills/skills/reaudit/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/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 <ID> Lightweight: mark finding as fixed No
/reaudit mark-deferred <ID> 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 <!-- AUDIT:STATUS=... --> lines. Extract FILE, LINES, STATUS for each finding.

  2. Diff-filter — run git diff --name-only <audit-commit>..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=<hash> 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 <ID>)

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

  1. Grep the report for <!-- AUDIT:STATUS=... line containing the given ID
  2. If STATUS=open or STATUS=not-fixed:
    • Change to STATUS=fixed COMMIT=<current HEAD hash>
    • Report: "SSRF-1 marked as fixed (commit abc1234)"
  3. If already STATUS=fixed: warn but allow updating the commit hash
  4. If STATUS=deferred: warn — user should confirm the deferral reason no longer applies

Multiple IDs can be specified: /reaudit mark-fixed SSRF-1 PATH-1 AUTH-1

Mode 3: mark-deferred (/reaudit mark-deferred <ID>)

Read the full file on GitHub · 101 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 101 lines · 114 tokens per session scan A 03f2486b6f13

Subscribe to this mod's changes

reaudit is a skill published in the GitHub repository Azzygoatcoder/agent-useful-skills (6 stars, last pushed 11d ago), licensed MIT. It adds 114 tokens to every session and 920 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeSecurityai-agentsdeepseek-harnessmonoreposkills
Related

Other skills, from other repositories

dsh-plugin-dev

An authoritative development guide for DeepSeek Harness plugins. DeepSeek Harness is a system where models, tools, services, events, and adapters are built as plugins.

zimodzh/dsh-plugin-dev-skills · 156 tokens

dsh-plugin-client

A development guide for the browser interface of a DSH plugin, including its package structure, registered interface locations, and build setup.

hackerFish/awesome-dsh-skills · 46 tokens

dsh-plugin-dev

A guide for creating and debugging DeepSeek Harness plugins, which are add-ons packaged as npm modules with configuration files.

hackerFish/awesome-dsh-skills · 35 tokens

dsh-plugin-i18n

A pattern for giving a DSH plugin’s user interface English and Chinese text that changes immediately when the selected language changes.

hackerFish/awesome-dsh-skills · 46 tokens

dsh-git-commit

A Git commit guide for writing standardised commit messages and performing basic checks before committing code. Git commits are saved checkpoints in a project’s history.

hackerFish/awesome-dsh-skills · 30 tokens

dsh-dependency-audit

A guide for reviewing and upgrading project dependencies, which are third-party packages the project relies on. It covers security warnings, installation scripts, lock files, breaking changes, tests, rollback plans, and reducing unnecessary dependencies.

hackerFish/awesome-dsh-skills · 36 tokens