Borrowing it
Nothing to install: this file belongs to nokonoko1203/claude-code-settings. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nokonoko1203/claude-code-settings/main/CLAUDE.mdgit clone --depth 1 https://github.com/nokonoko1203/claude-code-settingsWrote 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.
[](https://agentmods.dev/instructions/nokonoko1203/claude-code-settings/claude-md)<a href="https://agentmods.dev/instructions/nokonoko1203/claude-code-settings/claude-md"><img src="https://agentmods.dev/badge/instructions/nokonoko1203/claude-code-settings/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00325 | $0.00325 |
| Opus 5 | $0.00162 | $0.00162 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
claude-code-settings 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 6d 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.
What it actually says
Guidelines
This document defines the project's rules, objectives, and progress management methods. Please proceed with the project according to the following content.
Top-Level Rules
- To understand how to use a library, always use the Context7 MCP to retrieve the latest information.
- When investigating the source code, please use LSP as much as possible to ensure accurate code navigation and analysis.
- For front-end implementation, please ensure to verify the functionality using Playwright CLI (
playwright-clivia Bash) before considering the work complete. - If you need to check console logs or network requests, use
playwright-cli consoleandplaywright-cli network. - Do not write code until the user approves the plan. Follow the order: research → plan → approval → implement.
- Write research findings and plans as markdown files in
.tmp— never report only verbally. These files serve as shared documents for the user to review and annotate. - When the user adds annotations to a plan, address all of them and update the document. Do not start implementing until explicitly told to.
- When seeking a decision from the user, use AskUserQuestion.
- Respond critically and without pandering to my opinions, but don't be forceful in your criticism.
- Whenever a task arises, always launch the task management system and organize the details clearly.
- When launching an agent team, always form: Lead + Reviewer (Claude Code agents for design/review) and Implementer + Tester (Claude Code agents for implementation and testing).
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.
- 6d ago First seen · 18 lines · 325 tokens per session scan A 9d4ffa49a629
claude-code-settings CLAUDE.md is an instructions file published in the GitHub repository nokonoko1203/claude-code-settings (92 stars, last pushed 6mo ago), licensed MIT. It adds 325 tokens to every session, about $0.0016 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 2026-08-30.
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.
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.
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).
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).
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.
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.