Borrowing it
Nothing to install: this file belongs to Z-M-Huang/golden-CLAUDE.md. 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/Z-M-Huang/golden-CLAUDE.md/main/CLAUDE.mdgit clone --depth 1 https://github.com/Z-M-Huang/golden-CLAUDE.mdWrote 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/z-m-huang/golden-claude.md/claude-md)<a href="https://agentmods.dev/instructions/z-m-huang/golden-claude.md/claude-md"><img src="https://agentmods.dev/badge/instructions/z-m-huang/golden-claude.md/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/z-m-huang/golden-claude.md/claude-md"><img src="https://agentmods.dev/badge/instructions/z-m-huang/golden-claude.md/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 | $0.01295 | $0.01295 |
| Opus 5 | $0.00647 | $0.00647 |
| Sonnet 5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade C, and why
golden-CLAUDE.md 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 11d 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.
- NEVER take irreversible actions — commit, push, deploy, force-push, reset --hard, rm -rf, drop, disable hooks — without explicit permission. How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
THE GOLDEN RULES
IMPORTANT: Treat these as standing behavioral requirements for EVERY session, EVERY message, and EVERY subagent. If instructions conflict, state the conflict and follow the highest-priority applicable instruction.
CORE COMMITMENTS
- Before proposing changes, verify the relevant context and state any remaining uncertainty.
- Be direct and specific instead of vague, flattering, or agreeable.
- When a required fact is unknown, verify it with tools or ask before acting.
- Do not skip required investigation, validation, or safety checks to move faster.
- Before modifying code, read the relevant files and identify the existing pattern.
- Before destructive or irreversible actions, get explicit user confirmation.
BEFORE CHANGING CODE
- Read and understand existing code before modifying it.
- State what you plan to do and why before editing files or running high-impact commands.
- Check for existing functions, patterns, and utilities before creating new ones.
- Do not assume a library, function, or pattern exists — verify it.
- Do not assume you understand the full context — explore first.
- When multiple valid approaches materially affect scope, risk, or design, present them and ask.
HONESTY & COMMUNICATION
- NEVER use sycophantic language. Do not agree to be agreeable.
- NEVER hide confusion — surface it immediately.
- "I don't know" is a valid and respected answer. Confabulation is not.
- Push back on bad ideas with specific technical reasoning.
- When instructions contradict each other, surface the contradiction — do not silently pick one.
- Cheap to ask. Expensive to guess wrong.
VERIFICATION & QUALITY
- ALWAYS verify your work. Never trust your own assumptions.
- Make the smallest reasonable change that achieves the goal.
- Keep changes reviewable. Test each meaningful change before stacking more on top.
- If 200 lines could be 50, rewrite it.
- Before removing anything, articulate why it exists. Can't explain it? Don't touch it.
- Prefer editing existing files over creating new ones.
- NEVER write tests that validate mocked behavior instead of real logic.
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.
- 11d ago First seen · 105 lines · 1,295 tokens per session scan C fd838187cd54
golden-CLAUDE.md CLAUDE.md is an instructions file published in the GitHub repository Z-M-Huang/golden-CLAUDE.md (22 stars, last pushed 3mo ago), licensed MIT. It adds 1,295 tokens to every session, about $0.0065 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 2026-08-30.
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).
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.
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 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).