review-skills

review-skills is a skill for Claude Code from HuntsDesk/ve-kit. It costs 44 tokens per session (1,283 once invoked), scanned A, original, MIT.

A review process for auditing every skill definition in a project's .claude/skills folder. It checks metadata, instructions, activation wording, supporting files, and missing capabilities.

In plain words
What is it for?
Use it for periodic or post-change audits of project skills, especially after adding several skills or changing the Claude Code version; it creates a task for each finding.
Why use it?
It finds configuration errors, confusing triggers, poor organization, outdated references, and opportunities to combine or split skills before they make the skill menu harder to use.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

Good fit Use it for periodic or post-change audits of project skills, especially after adding several skills or changing the Claude Code version; it creates a task for each finding.

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

Made for: Claude Code.

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 review-skills

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/huntsdesk/ve-kit/review-skills"><img src="https://agentmods.dev/badge/skills/huntsdesk/ve-kit/review-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,283 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 $0.00044 $0.01283
Opus 5 $0.00022 $0.00642
Sonnet 5 $0.00009 $0.00257
Haiku 4.5 $0.00004 $0.00128

Measured 10d ago against content hash e5a93f228b39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review-skills 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 10d 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.

skills/review-skills/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Review Protocol

Comprehensive review of every .claude/skills/*/SKILL.md file. Part of the review-* skill family. Cites ../_shared/review-checklist.md and ../_shared/anthropic-configuration-guide.md.

Owner: docs-manager agent.

When to invoke

  • After adding multiple new skills in quick succession
  • Quarterly audit
  • After Claude Code version bumps that change skill frontmatter capabilities
  • When the / autocomplete menu gets cluttered or confusing

Output contract

Board tasks only. Lean summary to main agent.


Step 1 — Inventory

List every .claude/skills/*/SKILL.md file (excluding _shared/). For each:

  • Parse frontmatter: name, description, disable-model-invocation, user-invocable, allowed-tools, paths, model, effort, context, agent
  • Count body lines
  • List supporting files in the skill directory
  • Extract referenced files / commands / agents from the body

Step 2 — Frontmatter validation

For each skill, check against review-checklist.md §"Skills":

Issue Severity
name mismatches directory critical
description missing high
description generic or vague medium
disable-model-invocation / user-invocable combination nonsensical high
allowed-tools uses tool names that don't exist high
paths glob invalid syntax high
Uses invented frontmatter keys high
description + when_to_use combined > 1,536 chars high

Step 3 — Invocation semantics

For each skill, decide whether the flag combination matches intent:

Pattern Intent Flag combo
User-triggered command with side effects /commit, /deploy disable-model-invocation: true, user-invocable: true
Reference knowledge Claude applies /common-tasks, /troubleshooting (defaults)
Background knowledge, not user-invocable Internal guides user-invocable: false
Workflow Claude runs, user may also invoke /plan, /review user-invocable: true, model-invocable

Read the full file on GitHub · 138 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. 10d ago First seen · 138 lines · 44 tokens per session scan A e5a93f228b39

Subscribe to this mod's changes

review-skills is a skill published in the GitHub repository HuntsDesk/ve-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,283 once invoked, about $0.0002 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.