skill-review-audit

skill-review-audit is a skill for Claude Code, Codex from okwinds/miscellany. It costs 71 tokens per session (1,586 once invoked), scanned B, original, MIT.

A read-only review process for auditing an AI agent skill and its related files. It examines instructions, scripts, references, assets, triggering behavior, side effects, security and privacy risks, provenance, and quality.

In plain words
What is it for?
Use it to review a skill before adoption, assess commands and file or network effects, identify supply-chain and privacy concerns, and write prioritized recommendations for improvement.
Why use it?
It reveals what a skill can cause, where it may be unsafe or incomplete, and how well it is likely to work before changes are made. The default read-only approach avoids altering the skill during the audit.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it to review a skill before adoption, assess commands and file or network effects, identify supply-chain and privacy concerns, and write prioritized recommendations for improvement.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/okwinds/miscellany/skill-review-audit
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 okwinds/miscellany --skill skill-review-audit
Clone the repo
git clone --depth 1 https://github.com/okwinds/miscellany

Made for: Claude Code, Codex.

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 skill-review-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/okwinds/miscellany/skill-review-audit/github.svg)](https://agentmods.dev/skills/okwinds/miscellany/skill-review-audit)
Your own site
<a href="https://agentmods.dev/skills/okwinds/miscellany/skill-review-audit"><img src="https://agentmods.dev/badge/skills/okwinds/miscellany/skill-review-audit/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 skill-review-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/okwinds/miscellany/skill-review-audit"><img src="https://agentmods.dev/badge/skills/okwinds/miscellany/skill-review-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,586 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00071 $0.01586
Opus 5 $0.00036 $0.00793
Sonnet 5 $0.00014 $0.00317
Haiku 4.5 $0.00007 $0.00159

Measured 9d ago against content hash d2d5befaee5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

skill-review-audit scanned grade B with 2 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/scan_skill.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Destructive operations** (rm -rf, overwriting, migrations, irreversible actions).

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Network access (curl/wget, HTTP clients, package installs, API calls).
agent/skills/skill-review-audit/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Review & Audit

Produce a systematic, multi-dimensional review of any skill directory (a SKILL.md plus optional scripts/, references/, assets/, and install metadata).

Non-Mutating Constraint (Default)

  • Default is read-only: do not create, delete, or modify any files (including apply_patch, sed -i, overwriting configs, auto-fixes, git commit, etc.).
  • If the user wants changes applied, ask for explicit human authorization first and wait for a clear “yes, apply these edits” (or equivalent) before touching the filesystem.
  • You may still propose fixes as text (recommendations or patch snippets), but do not apply them without authorization.

Outcomes

  • A clear description of what the skill teaches and what it does not.
  • A map of tooling + side effects the skill may cause when followed (commands, network, file writes, permissions).
  • A risk assessment (security, privacy, safety, supply chain) with mitigations.
  • A quality assessment (correctness, completeness, maintainability, UX) with prioritized improvements.
  • Optional scoring using references/scoring-rubric.md.
  • A report formatted using references/report-template.md.

Inputs To Request (If Missing)

  • Skill identifier: name and/or filesystem path to the skill directory.
  • Target agent environment (e.g. Codex CLI / Claude Code / other) and any constraints (offline, no web, sandboxed, etc.).
  • Intended usage context (what kinds of user prompts should trigger it; what “done” looks like).

Workflow (Do In Order)

0) Scope The Review

  • Confirm whether the review is (a) informational only (read-only) or (b) includes proposing patches (still read-only unless explicitly authorized to apply).
  • Define what “safe enough” means for the target environment (network allowed? can write files? secrets present?).
  • Restate the Non-Mutating Constraint and ask for authorization if the user requests edits to be applied.

1) Inventory & Provenance

Read the full file on GitHub · 145 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 145 lines · 71 tokens per session scan B d2d5befaee5f

Subscribe to this mod's changes

skill-review-audit is a skill published in the GitHub repository okwinds/miscellany (50 stars, last pushed 4mo ago), licensed MIT. It adds 71 tokens to every session and 1,586 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens