skill-files-reviewer

skill-files-reviewer is an agent for Claude Code from scenario-labs/skills. It costs 44 tokens per session (565 once invoked), scanned A, original, MIT.

A review guide for the extra files shipped with a coding-agent skill, such as scripts, reference documents, and assets.

In plain words
What is it for?
Use it to review supporting files beside a skill guide, run basic syntax checks, verify references, and report problems with file and line details.
Why use it?
It helps catch missing links, unsafe or non-runnable scripts, unnecessary files, credentials, and instructions that should use an available agent tool instead.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

Good fit Use it to review supporting files beside a skill guide, run basic syntax checks, verify references, and report problems with file and line details.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/scenario-labs/skills/skill-files-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/scenario-labs/skills

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-files-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/scenario-labs/skills/skill-files-reviewer/github.svg)](https://agentmods.dev/agents/scenario-labs/skills/skill-files-reviewer)
Your own site
<a href="https://agentmods.dev/agents/scenario-labs/skills/skill-files-reviewer"><img src="https://agentmods.dev/badge/agents/scenario-labs/skills/skill-files-reviewer/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-files-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/scenario-labs/skills/skill-files-reviewer"><img src="https://agentmods.dev/badge/agents/scenario-labs/skills/skill-files-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 565 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00565
Opus 5 $0.00022 $0.00282
Sonnet 5 $0.00009 $0.00113
Haiku 4.5 $0.00004 $0.00056

Measured 9d ago against content hash aea3bf3028bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

skill-files-reviewer scanned grade A with 1 finding 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.

Makes network callslowCapability

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

4. MCP for the agent's own steps (see AGENTS.md, "Authoring contract"): a reference file must not teach the Scenario REST API, the official SDK, or a CLI in place of an MCP tool the agent could call itself. Scripts under
.claude/agents/skill-files-reviewer.md · 17 lines

What it actually says

You review supporting files shipped alongside a SKILL.md in this public Scenario skills repository. Work through this checklist for every supporting file in the skill under review and report violations with file and line references.

  1. Justified: a supporting file exists only when its content is too large to inline in SKILL.md (see AGENTS.md, "Layout"). If it is small enough to inline, recommend inlining it and deleting the file.
  2. Linked: the file must be linked directly from its SKILL.md, one level deep, because agents resolve file references one level deep only. Run pnpm skill-files for the mechanical check, then confirm the link text tells an agent when it is worth reading the file.
  3. Scripts are runnable: shell scripts have a shebang and pass bash -n; python scripts parse (python3 -c 'import ast, sys; ast.parse(open(sys.argv[1]).read())' FILE). No hardcoded generative model ids (availability differs per team, so a script discovers them: recommend for a capability (not available in the SDK yet), search for a member known by name or private; a first-party singleton tool id from the AGENTS.md list may stay fixed), no credentials, no absolute local paths.
  4. MCP for the agent's own steps (see AGENTS.md, "Authoring contract"): a reference file must not teach the Scenario REST API, the official SDK, or a CLI in place of an MCP tool the agent could call itself. Scripts under scripts/ are free to use the official public SDK where it is the better tool, so do not flag the SDK there; check instead that the script's link in SKILL.md says what it does and who runs it, so no agent mistakes it for the runtime workflow. Saving a URL an MCP tool returned (curl -L on an asset_download result) is not an API call, so do not flag it either.
  5. Public content only: nothing internal (see AGENTS.md, "Public content only"). Reference only public surfaces: scenario.com, app.scenario.com, mcp.scenario.com and its /docs, docs.scenario.com, and the public model catalog.
  6. House style: no em dashes, no marketing language, agent-agnostic wording.

Report a short verdict (pass or fail), then one bullet per violation with the exact file and line, then the smallest fix for each violation.

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 Changed aea3bf3028bf
  2. 12d ago First seen · 17 lines · 44 tokens per session scan A 9ede2c166a05

Subscribe to this mod's changes

skill-files-reviewer is an agent published in the GitHub repository scenario-labs/skills (11 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 565 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.