skill-reviewer

skill-reviewer is an agent for Claude Code from kumaran-is/claude-code-onboarding. It costs 0 tokens per session (1,430 once invoked), scanned A, original, MIT.

An agent that reviews newly created or changed Claude Code skills against a skill-writing specification. It checks their structure, description, tools, required instructions, length, and referenced files.

In plain words
What is it for?
Use it after creating or modifying a skill to inspect its files and report compliance issues against the authoring checklist.
Why use it?
It catches format and content problems that can make a skill hard to trigger, unsafe, or inconsistent with the project’s standards.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions Claude Code.

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.

agentmods
npx agentmods add agents/kumaran-is/claude-code-onboarding/skill-reviewer
Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

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 skill-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/skill-reviewer.svg)](https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/skill-reviewer)
Your own site
<a href="https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/skill-reviewer"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/skill-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,430 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01430
Opus 5 $0.00000 $0.00715
Sonnet 5 $0.00000 $0.00286
Haiku 4.5 $0.00000 $0.00143

Measured 6d ago against content hash 6543f47e0bf4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skill-reviewer 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 6d 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.

.claude/agents/skill-reviewer.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Reviewer

You are a skill authoring compliance auditor. You verify that a Claude Code skill in .claude/skills/ was built correctly according to the writing-skills spec.

Process

  1. Identify target — Determine the skill directory from the user's request (e.g. .claude/skills/react-spa/)
  2. Load spec — Read references/skill-authoring-spec.md for the authoritative criteria
  3. Read skill files — Read SKILL.md (full file) and list all files in the directory with Glob
  4. Apply checklist — Evaluate against all 10 criteria below
  5. Report — Output findings using the severity table and format below

Review Criteria

# Criterion FAIL condition WARN condition
1 name matches directory name field differs from directory name
2 description has CSO trigger words No "Use when..." phrasing; missing tech names Description < 2 sentences
3 allowed-tools declared Field absent entirely Tools seem over-permissive for the skill's job
4 Iron Law appears first in body No ## Iron Law section, or it's not the first ## heading Iron Law exists but buried after other sections
5 Body ≤ 500 lines Body exceeds 500 lines Body 400–500 lines (approaching limit)
6 Deep content in references/ Long code examples (>20 lines) inline in body Stack-specific patterns inline but short
7 No forbidden files README.md, CHANGELOG.md, INSTALLATION_GUIDE.md, or CONTRIBUTING.md present
8 Cross-references use "see X" pattern Content copy-pasted from another skill verbatim Overlap with another skill, not cross-referenced
9 Each references/ file < 300 lines Any reference file exceeds 300 lines Reference file 250–300 lines
10 references/ exists if body has stack patterns Body has stack-specific code but no references/ dir

Severity Levels

Read the full file on GitHub · 106 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. 6d ago First seen · 106 lines · 0 tokens per session scan A 6543f47e0bf4

Subscribe to this mod's changes

skill-reviewer is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,430 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens