ai-agent-skills: Instructions file for Claude Code

CLAUDE.md

ai-agent-skills CLAUDE.md is an instructions file for Claude Code from nphausg/ai-agent-skills. It costs 1,631 tokens per session, scanned C, original, Apache-2.0.

Coding-agent instructions for the ai-agent-skills repository, including communication rules and a required planning workflow. They require architecture review before implementation and define rules for commits, pull requests, and pushes.

In plain words
What is it for?
Use them when planning or implementing changes in the repository, communicating with its maintainer, or deciding whether to commit, create a pull request, or push changes.
Why use it?
They prevent coding from starting before the likely effects on the project are understood, and clarify which version-control actions need permission. They also set consistent language and text-formatting expectations.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: names the AskUserQuestion tool; mentions Claude Code.

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nphausg/ai-agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/nphausg/ai-agent-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,631 This file is loaded in full into every session.
When invoked 1,631 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.01631 $0.01631
Opus 5 $0.00816 $0.00816
Sonnet 5 $0.00326 $0.00326
Haiku 4.5 $0.00163 $0.00163

Measured 8d ago against content hash 99e5521f0b0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

ai-agent-skills CLAUDE.md scanned grade C 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 8d 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.

- Original command: `rm -rf /some/path`
CLAUDE.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MUST

  • MUST only communicate to me in ENGLISH, and start every reply with "Hi Leo, "
  • Never commit unless asked. On "commit", auto-generate the message from the diff and commit immediately, no confirmation.
  • NEVER create GitLab/GitHub MRs or PRs without being explicitly asked. Diagnosing or finding a fix does NOT mean create the MR -- only explain the fix and wait for an explicit instruction.
  • Never push unless explicitly told to; after committing, ask before pushing.
  • NEVER start implementing without completing the full planning workflow below. No exceptions.
  • NEVER use typographic Unicode in authored content. Use ASCII only: -> (not the arrow char), - or -- (not em/en dashes), straight quotes " ' (not curly quotes), ... (not the ellipsis char). Reason: skill/marketplace/flow files are JSON-serialized with ensure_ascii=True, so any non-ASCII char becomes an ugly \uXXXX escape. Applies everywhere (SKILL.md frontmatter/descriptions, JSON, commit messages, docs, prose), not just JSON.

Coding Principles & Workflow

The principles are the mindset; the workflow enforces them. Think before you type; do not skip steps.

The Four Principles

The mindset behind the workflow. Each is a one-line rule plus its test; the workflow below is how they get enforced per task.

Principle Guards against The rule (and its test)
Think Before Coding wrong assumptions, hidden confusion State assumptions, surface tradeoffs, and ask when ambiguous or confused -- never pick an interpretation silently.
Simplicity First overengineering, bloat Minimum code that solves it -- no speculative features, abstractions, config, or error-handling for impossible cases. Test: a senior engineer wouldn't call it overcomplicated.
Surgical Changes orthogonal edits Touch only what the task needs; match existing style; don't refactor or "improve" unrelated code; remove only the orphans your change creates, never pre-existing dead code (mention it). Test: every changed line traces to the request.
Goal-Driven Execution vague success, "make it work" Turn the task into a verifiable goal -- tests-first (reproduce/validate, then make pass), a verify check per step, loop until proven.

Read the full file on GitHub · 117 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. 8d ago First seen · 117 lines · 1,631 tokens per session scan C 99e5521f0b0a

Subscribe to this mod's changes

ai-agent-skills CLAUDE.md is an instructions file published in the GitHub repository nphausg/ai-agent-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,631 tokens to every session, about $0.0082 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens