skills: Instructions file for Claude Code

CLAUDE.md

skills CLAUDE.md is an instructions file for Claude Code from skrrt-sh/skills. It costs 1,228 tokens per session, scanned A, original, MIT.

Repository instructions for the skrrt-sh/skills project, which distributes coding-agent skills in plugin folders and standalone skill folders. They define the project layout and require specific skills for Git commits, pull requests, and releases.

In plain words
What is it for?
Use them when editing skills, working with plugin structure, or preparing commits, pull requests, releases, and related Git workflow changes.
Why use it?
They help agents find the right files and follow the repository's approved workflow instead of creating Git changes with unapproved commands.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

This is skrrt-sh/skills's own configuration. It tells Claude Code how to work on skills 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 skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to skrrt-sh/skills. 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/skrrt-sh/skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/skrrt-sh/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 skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/skrrt-sh/skills/claude-md/github.svg)](https://agentmods.dev/instructions/skrrt-sh/skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/skrrt-sh/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/skrrt-sh/skills/claude-md/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 skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/skrrt-sh/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/skrrt-sh/skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,228 This file is loaded in full into every session.
When invoked 1,228 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01228 $0.01228
Opus 5 $0.00614 $0.00614
Sonnet 5 $0.00246 $0.00246
Haiku 4.5 $0.00123 $0.00123

Measured 4d ago against content hash 075e31206830, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

skills 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 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.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git workflow

Use the Skrrt ship skills for git work: commit for commits, pr for pull and merge requests, release for releases. Never hand-write git commit, gh pr create, gh release create, glab mr create, or glab release create instead. Reconfiguring the workflow is /setup, which only the user can run.

Read .agents/ship.md before changing any git workflow state.

Repository structure

This repo ships agent skills two ways. Each bucket is its own Claude Code plugin, so the bucket name is the slash namespace — /ship:commit, /docs:md-writer. The skills CLI discovers every SKILL.md in the repo by scanning (verified: it ignores manifest skill arrays) and installs bare names — /commit, /md-writer. The root plugin.json stays as the repo-wide declared inventory for tooling that reads it.

  • skills/ship/ — git shipping workflow: commit, pr, release, setup.
  • skills/docs/ — documentation tools: md-writer.

Each skill lives at skills/<bucket>/<name>/SKILL.md with its supporting files co-located (references/, scripts/, assets/, agents/, config/, evals/). There are no per-skill manifests and no plugin-level hooks — a skill that needs a script bundles it under its own scripts/ and invokes it from SKILL.md.

Every skill must also carry agents/openai.yaml (Codex interface and invocation policy) and evals/evals.json (at least three behavior cases); every model-invocable skill additionally needs evals/trigger-evals.json (20+ queries, 8+ each way). scripts/validate-skills.sh fails without them, and it also fails on any frontmatter key outside name, description, allowed-tools, and disable-model-invocation — the Agent Skills spec subset plus one exception, so the skills still package for claude.ai and the Skills API. setup is that exception: a run-once configurator the user enters deliberately, so it sets disable-model-invocation: true and allow_implicit_invocation: false. Every other skill stays model-invocable, because hiding one drops its description from the agent's context and the agent then runs the raw git/gh/glab command instead of the governed workflow. Side effects are gated by the permission rules in templates/claude-settings.json, not by hiding skills. A skill that bundles scripts pre-approves them with allowed-tools: Bash(${CLAUDE_SKILL_DIR}/scripts/<name>.sh:*) and invokes them directly — no bash prefix and no quotes, or the permission rule stops matching.

Read the full file on GitHub · 75 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 Changed · +7 lines · +167 tokens per session 075e31206830
  2. 9d ago First seen · 68 lines · 1,061 tokens per session scan A b4bd4e9e1f10

Subscribe to this mod's changes

skills CLAUDE.md is an instructions file published in the GitHub repository skrrt-sh/skills (2 stars, last pushed 3d ago), licensed MIT. It adds 1,228 tokens to every session, about $0.0061 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

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens