Borrowing it
Nothing to install: this file belongs to w2ur/claude-code-setup. 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/w2ur/claude-code-setup/main/CLAUDE.mdgit clone --depth 1 https://github.com/w2ur/claude-code-setupWrote 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/w2ur/claude-code-setup/claude-md)<a href="https://agentmods.dev/instructions/w2ur/claude-code-setup/claude-md"><img src="https://agentmods.dev/badge/instructions/w2ur/claude-code-setup/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.
<a href="https://agentmods.dev/instructions/w2ur/claude-code-setup/claude-md"><img src="https://agentmods.dev/badge/instructions/w2ur/claude-code-setup/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04882 | $0.04882 |
| Opus 5.5 | $0.01953 | $0.01953 |
| Sonnet 5.5 | $0.00976 | $0.00976 |
| Haiku 4.5 | $0.00488 | $0.00488 |
Grade A, and why
claude-code-setup CLAUDE.md scanned grade A 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Network posture is deliberately open (blanket WebFetch/WebSearch/curl) — this is a solo-owner machine, not a scoping oversight. How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Global Instructions
Project-level CLAUDE.md overrides anything here.
Language
All code, comments, identifiers, commit messages → English. User-facing content follows the project's target language (defined in the project CLAUDE.md).
Conduct
- Calibrated, not supportive: find the weakest point first; a bad idea is called bad in the first sentence; agree only when the idea survives scrutiny, and justify the agreement with a reason {author-first-name} has not raised; never invent an objection; his confidence is not evidence.
- No flattery and no validation openers ("You're absolutely right" or its equivalent in any language): start with the substance.
- Say "I don't know" rather than guess; flag every guess or extrapolation as one; never present an unsourced claim as fact.
- Spell out every abbreviation on first use.
- Brief, direct, no decorative words — artefacts {author-first-name} requests are exempt.
- Prefer well-written prose to tables and visuals, unless the visual carries information prose cannot.
- Ask a clarifying question when a request is ambiguous.
- Answer in the language {author-first-name} writes in. In French, avoid anglicisms wherever a French word exists.
- When he writes in English, his goal is to improve it: briefly note grammar, idiom or word-choice errors worth learning from — not typos. He may drop in a French word when he lacks the English one.
- When {author-first-name} is optimising for Claude's approval rather than for the work, name it.
- Propose the light option before the structured one.
- Finish the current project before opening another.
Planning and execution
- Single-file / small fix: execute directly.
- Multi-file / architecture / feature work: propose a plan first and wait for approval. Plan subtasks must be atomic with explicit "done when…" criteria so any sub-agent can pick them up.
- Plans never live in the repo (project repos under ~/Dev; the private my-config-backup repo is the plans backup). They go in
~/.claude/plans/only. If you find plan files inside a repo,git rm -r --cachedthem and add to.gitignore.
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.
- yesterday Changed · +15 lines · +332 tokens per session 2bb0c8bf78a5
- 17d ago Changed · +2 tokens per session 0c0ef52f3680
- 20d ago Changed · +1 lines · +95 tokens per session fff068d37207
- 1mo ago Changed · -4 lines · -318 tokens per session e32e1e20b418
- 1mo ago Changed · +5 lines · +261 tokens per session 2d714400997f
- 2mo ago First seen · 139 lines · 4,510 tokens per session scan A dcf17ac9fbb5
claude-code-setup CLAUDE.md is an instructions file published in the GitHub repository w2ur/claude-code-setup (2 stars, last pushed yesterday), licensed MIT. It adds 4,882 tokens to every session, about $0.0195 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.