skillcheck CLAUDE.md

skillcheck CLAUDE.md is an instructions file for coding agents from Sagargupta16/skillcheck. It costs 964 tokens per session, scanned A, original, MIT.

Repository instructions for skillcheck, a TypeScript command-line tool that checks whether agent skills follow the Agent Skills specification. It also describes the project’s package, build, and test commands.

In plain words
What is it for?
Developing, building, linting, testing, and running the skillcheck CLI against example skill files.
Why use it?
They give the coding agent the project context and exact commands needed to make compatible changes and verify them.

Instructions file

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 instructions/sagargupta16/skillcheck/claude-md
Clone the repo
git clone --depth 1 https://github.com/Sagargupta16/skillcheck

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 skillcheck CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sagargupta16/skillcheck/claude-md.svg)](https://agentmods.dev/instructions/sagargupta16/skillcheck/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sagargupta16/skillcheck/claude-md"><img src="https://agentmods.dev/badge/instructions/sagargupta16/skillcheck/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 964 This file is loaded in full into every session.
When invoked 964 The same file — it is already loaded in full.
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 $0.00964 $0.00964
Opus 5 $0.00482 $0.00482
Sonnet 5 $0.00193 $0.00193
Haiku 4.5 $0.00096 $0.00096

Measured today against content hash 923009cf28c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skillcheck CLAUDE.md 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 today.

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.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file stacks on top of the workspace root at C:\Code\GitHub\:

  • Root CLAUDE.md -- voice, rules, routing map, references, skills, slash commands, conventions.
  • Root MEMORY.md -- live facts across repos.
  • Root STATUS.md -- live PR/CI/security dashboard.
  • .claude/resources/ -- deep reference for collaboration, workflow, git, OSS, debugging, voice.

Read those first. The guidance below only adds repo-specific context -- it does not override anything in the root.

Project

Conformance suite for Agent Skills (SKILL.md): lints skills against the agentskills.io spec today; roadmap is headless cross-runtime execution tests + a public caniuse-style compatibility matrix. Public OSS, npm package @sagargupta1610/skillcheck.

Stack

  • Language: TypeScript 7 (strict, ESM, NodeNext)
  • Framework: none -- CLI via commander, JS bundled by tsup, .d.ts emitted by tsc
  • Database: none
  • Package manager: pnpm
  • Deploy target: npm registry (CLI); matrix site later (Vercel)

Run

pnpm install
pnpm dev          # tsup --watch (JS only, no .d.ts)
pnpm build        # tsup -> dist/*.js, then tsc --emitDeclarationOnly -> dist/*.d.ts
node dist/cli.js lint fixtures/valid-skill

Test

pnpm test         # vitest
pnpm lint         # biome
pnpm typecheck

Entry points

  • src/cli.ts -- commander CLI (skillcheck lint)
  • src/index.ts -- library exports (lintSkillDir, parseSkillMd, types)

Key files

  • src/lint/rules.ts -- the "brain": all lint rule implementations and limits
  • src/extensions.ts -- SPEC_FIELDS + KNOWN_EXTENSIONS typed registry (spec fields, client extension fields)
  • src/lint/parse.ts -- SKILL.md frontmatter/body splitter (never throws)
  • fixtures/ -- valid-skill and broken-skill lint fixtures used by tests and CI smoke test

Gotchas

  • The Agent Skills spec is UNVERSIONED -- when rules change upstream, pin claims to a spec-repo git SHA in the finding message/docs.
  • Severity model is three-tier by design: error = skills-ref strict parity, warning = beyond-parity checks + client-guide downgrades, info = advisory (never gates CI). --profile strict is the default; --profile lenient downgrades name-too-long, name-dir-mismatch, unknown-frontmatter-field to warnings (--strict is a deprecated alias for the default). Don't collapse the tiers.
  • KNOWN_EXTENSIONS in src/extensions.ts tracks client extension fields (Claude Code, Cursor, Copilot, OpenCode); update it when runtimes ship new frontmatter keys.
  • Name collision landscape: getskillcheck.com is an unrelated paid static-analysis product; npm unscoped skillcheck/skill-check are taken. This package is scoped @sagargupta1610/skillcheck on purpose.
  • Never set dts: true in tsup.config.ts. tsup bundles [email protected] into its own dist/rollup.js rather than installing it, and that vendored copy calls a TS compiler internal the native TypeScript 7 port removed -- the build dies on Cannot read properties of undefined (reading 'useCaseSensitiveFileNames'). No dependency bump reaches a bundled module, and tsup 8.5.1 is already latest. Declarations come from tsc --emitDeclarationOnly in the build script instead, which tracks whatever TS version is installed. Revisit only if tsup ships a release that re-vendors rollup-plugin-dts >= 6.5.x (that version declares typescript: ^4.5 || ^5 || ^6 || ^7).

Read the full file on GitHub · 63 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. today Changed · +1 lines · +220 tokens per session 923009cf28c7
  2. 5d ago First seen · 62 lines · 744 tokens per session scan A 4250a455a001

Subscribe to this mod's changes

skillcheck CLAUDE.md is an instructions file published in the GitHub repository Sagargupta16/skillcheck (5 stars, last pushed yesterday), licensed MIT. It adds 964 tokens to every session, about $0.0048 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.

Related

Other instructions, from other repositories