agentmods.dev

AI4L: Skill for Claude Code

.claude/skills/check/SKILL.md

check is a skill for Claude Code from forever-healthy/AI4L. It costs 8 tokens per session (640 once invoked), scanned B, original, MIT.

A project consistency checker for files such as documentation, instructions, and prompts. It checks version numbers, numbering, and consistency across a defined set of project files.

In plain words
What is it for?
Use it to verify a documentation-heavy project against its reference version and listed project files.
Why use it?
It catches mismatched versions and conflicting or inconsistent project information before release or review.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; reads ~/.codex paths.

This is forever-healthy/AI4L's own configuration. It tells Claude Code how to work on AI4L itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AI4L configures →

not rated 43repo changed 12d ago B scan SkillSpector: warn 8 tokens original MIT
View source ↗ forever-healthy/AI4L forever-healthy.org
Reuse

Borrowing it

Nothing to install: this file belongs to forever-healthy/AI4L. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/forever-healthy/AI4L/main/.claude/skills/check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/forever-healthy/AI4L

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 check

README.md
[![agentmods](https://agentmods.dev/badge/skills/forever-healthy/ai4l/check/github.svg)](https://agentmods.dev/skills/forever-healthy/ai4l/check)
Your own site
<a href="https://agentmods.dev/skills/forever-healthy/ai4l/check"><img src="https://agentmods.dev/badge/skills/forever-healthy/ai4l/check/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 check

Your own site · 80×15
<a href="https://agentmods.dev/skills/forever-healthy/ai4l/check"><img src="https://agentmods.dev/badge/skills/forever-healthy/ai4l/check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 640 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 13
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 14
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00008 $0.00640
Opus 5.5 $0.00003 $0.00256
Sonnet 5.5 $0.00002 $0.00128
Haiku 4.5 $0.00001 $0.00064

Measured 12d ago against content hash b5e4dbb77ecc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

check scanned grade B 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 12d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

* Compare the `mcp__*` entries in the allow lists of `.claude/settings.json` and, where present, `.public/.claude/settings.json` with the servers in scope; report a prescribed server that is not allowed
.claude/skills/check/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI4L - Project Verification & Consistency Checking

Handles consistency checking for all major files in the repo, including version numbers, item numbering, and overall consistency across files

[project_files]

  • .claude/skills/er/SKILL.md

  • .claude/skills/check/SKILL.md

  • .claude/agents/er-auditor.md

  • .claude/agents/er-creator.md

  • .claude/agents/er-fixer.md

  • .claude/agents/er-combiner.md

  • AGENTS.md

  • CLAUDE.md

  • README.md

  • CONTRIBUTING.md

  • prompts/ER.md

  • prompts/PERSONA.md

  • .grok/rules/rules.md

  • docs/Using-Chat-UI.md

  • docs/Using-Claude-Desktop.md

  • docs/Using-CLI-Environments.md

  • docs/Lessons-Learned.md

  • docs/Limitations.md

  • docs/Examples.md

Version

  • Check all [project_files] version numbers
  • Use the version stated in the VERSION file in the project root as a reference.
  • Make sure that all targets are consistent with it, including the version in the badges.
  • Some files do not have badges, just the version in the text. Make sure those are consistent as well.
  • If a file has no version, leave it as it is

Consistency Checking

  • Check all target files for consistency and completeness
  • Check the numbering of all items and the item count in ER.md
  • Also check numbered step lists (1., 2., 3. …) in ER.md, not just x.y items
  • Test each sequence for gaps and duplicates explicitly — a gap paired with a duplicate passes a count/min/max test

Environment Configs

.mcp.json is the source for MCP servers; .codex/config.toml, .grok/config.toml and the Claude settings files are hand-maintained. The servers in scope are those AGENTS.md prescribes for the agents; other servers in .mcp.json are out of scope.

  • For each server in scope, compare command and args in .codex/config.toml and .grok/config.toml with .mcp.json; report a server missing from a TOML and any argument that differs
  • Compare the mcp__* entries in the allow lists of .claude/settings.json and, where present, .public/.claude/settings.json with the servers in scope; report a prescribed server that is not allowed
  • Run /sync into a temporary directory and diff against the committed generated files; report any drift

Read the full file on GitHub · 66 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. 12d ago Changed · +8 lines scan A → B b5e4dbb77ecc
  2. 14d ago Changed · +2 lines f32c71f36e9c
  3. 1mo ago Changed 250957de2ed3
  4. 1mo ago Changed 4811379fbd82
  5. 1mo ago Changed 887fa7b53145
  6. 1mo ago Changed a6f52b25f9e0
  7. 1mo ago Changed 48a50c432004
  8. 1mo ago Changed acc539fbed0f
  9. 1mo ago Changed 67c9cc855dd3
  10. 2mo ago First seen · 56 lines · 8 tokens per session scan A 157e714684e5

Subscribe to this mod's changes

check is a skill published in the GitHub repository forever-healthy/AI4L (43 stars, last pushed 10d ago), licensed MIT. It adds 8 tokens to every session and 640 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Writing and docsevidencehealthlongevitypeptidesrejuvenationtherapeutics
Related

check compared with skills from other repositories

check next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
checkforever-healthy/AI4LSkill4310d agoMITB8Claude Code
healthbroomva/skillsSkill55d agoMITA86Claude Code, Codex
longevity-protocolSkillMedev/health-and-longevitySkill11mo agoMITA158Claude Code, Codex
mobility-routineSkillMedev/health-and-longevitySkill11mo agoMITA137Claude Code, Codex
nutrition-plannerSkillMedev/health-and-longevitySkill11mo agoMITA152Claude Code, Codex
sleep-optimizerSkillMedev/health-and-longevitySkill11mo agoMITA154Claude Code, Codex
zone-2-cardio-planSkillMedev/health-and-longevitySkill11mo agoMITA126Claude Code, Codex