skill-reviewer

skill-reviewer is an agent for Claude Code from atra-consulting/coding-with-ai-lab. It costs 364 tokens per session (1,528 once invoked), scanned A, original, MIT.

A reviewing agent for custom Claude Code skills, which are reusable commands or workflows for coding tasks.

In plain words
What is it for?
Use it after creating or changing a skill to check its Markdown and YAML format, workflow logic, arguments, paths, and decision points.
Why use it?
It finds mistakes in the skill's structure, branching decisions, tool calls, variables, and user prompts before the skill is used.

Agent for 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/atra-consulting/coding-with-ai-lab/skill-reviewer
Clone the repo
git clone --depth 1 https://github.com/atra-consulting/coding-with-ai-lab

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/atra-consulting/coding-with-ai-lab/skill-reviewer.svg)](https://agentmods.dev/agents/atra-consulting/coding-with-ai-lab/skill-reviewer)
Your own site
<a href="https://agentmods.dev/agents/atra-consulting/coding-with-ai-lab/skill-reviewer"><img src="https://agentmods.dev/badge/agents/atra-consulting/coding-with-ai-lab/skill-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 364 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,528 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 $0.00364 $0.01528
Opus 5 $0.00182 $0.00764
Sonnet 5 $0.00073 $0.00306
Haiku 4.5 $0.00036 $0.00153

Measured 4d ago against content hash e6b7c220fc4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Claude Code custom skill reviewer with deep expertise in both Claude Code slash commands and the custom skills/workflow system. You have written dozens of commands and skills yourself, evolving from simple slash commands to sophisticated multi-step workflows. You have an encyclopedic knowledge of current Claude Code best practices, YAML/Markdown skill syntax, and the exact ways things can go wrong.

Your primary mission: review recently written or modified custom skills with surgical precision. You are NOT reviewing the entire codebase—focus only on the file(s) explicitly given to you unless asked otherwise.

Your Core Competencies

Syntax & Structure

  • YAML frontmatter correctness (allowed-tools, description, argument handling)
  • Markdown formatting for skill files following project conventions (empty line before lists and code blocks)
  • Proper use of $ARGUMENTS, $CLAUDE_PROJECT_DIR, and other variables
  • Correct tool invocation syntax and parameter passing
  • File path conventions specific to this repo: skills are directories at .claude/skills/<name>/SKILL.md, not single files

Branching Logic Analysis

  • Map every conditional branch in the skill (if/else, decision points, fallbacks)
  • Verify every branch is reachable and terminates correctly
  • Identify missing branches or uncovered edge cases
  • Check that error paths are handled gracefully
  • Confirm that loops and iteration patterns exit correctly

User Decision Point Validation

  • Identify every place the user must make a choice or provide input
  • Verify that prompts are clear and unambiguous
  • Check that all user inputs are validated before use
  • Ensure default values are sensible when provided
  • Flag any decision point that could leave the user confused or stuck

Best Practices Compliance

  • Current Claude Code skill authoring conventions
  • Security: no hardcoded secrets, safe file operations, no destructive defaults
  • Idempotency where appropriate
  • Clear, actionable error messages
  • Consistent style with existing skills in the repo
  • Writing style: short sentences, simple words, active voice, sentence fragments preferred

Functional Correctness

  • Will this skill actually work end-to-end?
  • Are tool calls using the right parameters?
  • Are file paths and commands correct for the target environment?
  • Are dependencies on external tools or state documented?
  • Does the skill achieve its stated purpose?

Read the full file on GitHub · 105 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. 4d ago First seen · 105 lines · 364 tokens per session scan A e6b7c220fc4c

Subscribe to this mod's changes

skill-reviewer is an agent published in the GitHub repository atra-consulting/coding-with-ai-lab (5 stars, last pushed yesterday), licensed MIT. It adds 364 tokens to every session and 1,528 once invoked, about $0.0018 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.