skill-check

skill-check is a command for coding agents from VersoXBT/skill-manager. It costs 14 tokens per session (506 once invoked), scanned A, original, MIT.

An audit command that lists installed skills, where they came from, their structure, and available updates.

In plain words
What is it for?
It helps inventory skills, group them by category, review sources and token counts, find updates, and optionally fix reported issues.
Why use it?
It replaces manual checking of many skill files and highlights missing information or other structural problems.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the skill-manager plugin — 1 skill, 1 command, 1 agent shipped together

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 commands/versoxbt/skill-manager/skill-check
Clone the repo
git clone --depth 1 https://github.com/VersoXBT/skill-manager

Or install skill-manager, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent.

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-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/versoxbt/skill-manager/skill-check.svg)](https://agentmods.dev/commands/versoxbt/skill-manager/skill-check)
Your own site
<a href="https://agentmods.dev/commands/versoxbt/skill-manager/skill-check"><img src="https://agentmods.dev/badge/commands/versoxbt/skill-manager/skill-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 506 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 $0.00014 $0.00506
Opus 5 $0.00007 $0.00253
Sonnet 5 $0.00003 $0.00101
Haiku 4.5 $0.00001 $0.00051

Measured 3d ago against content hash 256d1245397e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-check 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 3d 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.

commands/skill-check.md · 47 lines

What it actually says

Skill Check

Show the user everything they have installed and flag anything that needs attention.

Step 1: Run the audit

node "${CLAUDE_PLUGIN_ROOT}/scripts/index.js" check $ARGUMENTS

Step 2: Present the results

The script outputs a markdown report. Present it to the user with these additions:

  1. Group skills by category — look at each skill's name and description and group them (e.g. backend, frontend, blockchain, testing, devops, security, ai/ml, workflow, tooling, coding, etc.). Use your judgement.
  2. Show the full inventory — every skill with its description, source, GitHub repo (user/repo short link), and token count. The Repo column is resolved automatically from plugin.json, skill-lock, or marketplace git remotes.
  3. Summarize structure issues — don't list every "missing version" individually, just say "X skills missing version field" and list the ones with real problems (missing frontmatter, empty files)
  4. Show available updates clearly

Step 3: Fix Mode (only if --fix flag present)

If $ARGUMENTS contains --fix:

  1. Run with --json --fix:

    node "${CLAUDE_PLUGIN_ROOT}/scripts/index.js" check --json --fix $ARGUMENTS
    
  2. Present the fix plan — what will be fixed, which files

  3. Ask for confirmation

  4. Apply fixes using the Edit tool:

    • STRUCT-002: Add minimal frontmatter (name, description placeholder, version)
    • STRUCT-003: Add name field from directory name
    • STRUCT-005: Add version: 0.1.0
  5. Re-run audit to show before/after

Protection Rules

  • Plugin/official skills: NEVER modify. Report only. Suggest claude plugin update <name>.
  • User-created skills (~/.claude/skills/ non-symlink): CAN be fixed.
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. 3d ago First seen · 47 lines · 0 tokens per session scan A 256d1245397e

Subscribe to this mod's changes

skill-check is a command published in the GitHub repository VersoXBT/skill-manager (6 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 506 once invoked, about $0.0001 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.