agent-skills: Instructions file for Claude Code

CLAUDE.md

agent-skills CLAUDE.md is an instructions file for Claude Code from WhatIfWeDigDeeper/agent-skills. It costs 9,257 tokens per session, scanned C, a copy of agent-skills copilot-instructions.md, MIT.

Instructions for Claude Code in the agent-skills project, covering repository structure, planning, spelling checks, and rules for keeping Claude Code guidance aligned with GitHub Copilot guidance.

In plain words
What is it for?
Use them when planning work, editing CLAUDE.md or Copilot instructions, working around sandbox limits, or checking project documentation and spelling.
Why use it?
They give Claude Code the project context and help prevent instruction files from drifting apart.

Instructions file for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

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

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/.../skills/<name>/SKILL.md.

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/whatifwedigdeeper/agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/whatifwedigdeeper/agent-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9,257 This file is loaded in full into every session.
When invoked 9,257 The same file — it is already loaded in full.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 86% copy Near-identical to another mod 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 $0.09257 $0.09257
Opus 5 $0.04628 $0.04628
Sonnet 5 $0.01851 $0.01851
Haiku 4.5 $0.00926 $0.00926

Measured 9d ago against content hash a1deccb671b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

agent-skills CLAUDE.md scanned grade C with 2 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 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **`git worktree remove` does not delete the directory or local branch**: use `-f -f` (overrides agent-isolation lock), then `rm -rf <path>` and `git branch -D <branch>`. **In sandbox mode the directory delete fails "Op

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **GraphQL queries with `!` type markers cannot be passed as inline shell strings in zsh** — `String!`, `Int!`, etc. trigger history expansion and produce `UNKNOWN_CHAR` errors from `gh api graphql`. Pass the query via
Origin

This is a copy

86% identical to agent-skills copilot-instructions.md — 291 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Keep .github/copilot-instructions.md in sync: whenever you add, update, or remove a rule in this file or in any subdirectory CLAUDE.md (e.g. skills/CLAUDE.md, evals/CLAUDE.md, tests/CLAUDE.md, specs/CLAUDE.md), apply the equivalent change to .github/copilot-instructions.md, and ensure .github/copilot-instructions.md includes the reciprocal reminder to mirror rule changes made there back into the appropriate CLAUDE.md. Subdirectory CLAUDE.md files are the canonical home for context-specific rules (skill authoring, eval benchmarks, test conventions); Copilot has only one instructions file, so subdirectory rules still mirror into .github/copilot-instructions.md; a rule dropped from a CLAUDE.md because a subdirectory CLAUDE.md covers it must stay in the Copilot file. The two assistants (Claude Code vs. Copilot) should encode the same project conventions. This applies to /learn as well — when running /learn in this project, always update both the appropriate CLAUDE.md and .github/copilot-instructions.md without asking which to update. The instruction-sync CI check enforces this pairing for any CLAUDE.md path in the repo — it does not compare the two files' content.

Repository Structure

Evals live under evals/ at the repo root, not inside skills/ — they are development artifacts and should not be bundled when a skill is distributed.

Subdirectory CLAUDE.md files: skills/CLAUDE.md (skill format, version bumping, design patterns), evals/CLAUDE.md (benchmarking rules), tests/CLAUDE.md (test naming conventions, CI workflow requirements), and specs/CLAUDE.md (spec-editing rules) auto-load in Claude Code when working in those directories — they are omitted from this root file to reduce context.

New subdirectory CLAUDE.md format: Use # <Name> as the first heading and make the first paragraph note that the file auto-loads when working in <dir>/ — matches the existing pattern in skills/CLAUDE.md and evals/CLAUDE.md.

Read the full file on GitHub · 173 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. 9d ago First seen · 173 lines · 9,257 tokens per session scan C a1deccb671b3

Subscribe to this mod's changes

agent-skills CLAUDE.md is an instructions file published in the GitHub repository WhatIfWeDigDeeper/agent-skills (2 stars, last pushed 16d ago), licensed MIT. It adds 9,257 tokens to every session, about $0.0463 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). It is 86% identical to agent-skills copilot-instructions.md, differing in 291 lines, and is treated as a copy.

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 · 3,737 tokens