Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/xiaobei930/cc-best/claude-mdgit clone --depth 1 https://github.com/xiaobei930/cc-bestWrote 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/xiaobei930/cc-best/claude-md)<a href="https://agentmods.dev/instructions/xiaobei930/cc-best/claude-md"><img src="https://agentmods.dev/badge/instructions/xiaobei930/cc-best/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 | $0.01281 | $0.01281 |
| Opus 5 | $0.00641 | $0.00641 |
| Sonnet 5 | $0.00256 | $0.00256 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
cc-best 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{{PROJECT_NAME}} Constitution
Version: 1.0.0 | Ratified: {{DATE}} | Last Amended: {{DATE}}
This document is the project's "constitution", defining inviolable core principles. 本文档是项目的"宪法"，定义不可违背的核心原则。
{{PROJECT_DESCRIPTION}}
Quick Navigation | 快速导航
| Document 文档 | Purpose 用途 |
|---|---|
memory-bank/progress.md |
Current status 当前状态 |
memory-bank/architecture.md |
System architecture 系统架构 |
memory-bank/tech-stack.md |
Tech stack 技术选型 |
rules/common/methodology.md |
Full methodology 完整方法论 |
Core Constraints | 核心约束
- Constraint 1 约束1 - Description 说明
- Constraint 2 约束2 - Description 说明
Current State | 当前状态
{{CURRENT_PHASE}} - See 详见 memory-bank/progress.md
Key Principles | 关键原则 (IMPORTANT)
完整原则详见
rules/common/methodology.md
Must Follow 必须遵守: P1 接口先查文档禁止猜测 | P3 需求先明确禁止假设 | P7 不懂就说禁止装懂 | CP4 函数单一职责嵌套≤3
Autonomous Decisions 自主决策: A1 上下文推断不中断 | A2 记录依据+置信度 | A3 下游可纠偏 | A4 不确定用MVP标TBD | A5 区分Bug和假设错误
Workflow | 工作流程
/cc-best:pm → /cc-best:clarify(if needed) → /cc-best:lead → /cc-best:designer(frontend) → /cc-best:dev → /cc-best:verify → /cc-best:qa → /cc-best:commit → /clear → loop
Role Commands 角色命令: /cc-best:pm /cc-best:clarify /cc-best:lead /cc-best:designer /cc-best:dev /cc-best:qa /cc-best:verify
Tool Commands 工具命令: /cc-best:build /cc-best:test /cc-best:run /cc-best:status /cc-best:commit /cc-best:compact-context /cc-best:checkpoint /cc-best:hotfix
Mode Commands 模式命令: /cc-best:iterate (autonomous) /cc-best:pair (pair programming) /cc-best:model (model strategy)
📝 Clone users: remove
cc-best:prefix or runscripts/node/convert-to-local.js
/cc-best:iterate Mode Rules | 模式规则 (IMPORTANT)
After completing a task, immediately execute the next one. NO summarizing and waiting. 任务完成后必须立即执行下一个任务，禁止输出总结后等待用户响应。
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.
- 5d ago First seen · 124 lines · 1,281 tokens per session scan A aed37b89d91a
cc-best CLAUDE.md is an instructions file published in the GitHub repository xiaobei930/cc-best (50 stars, last pushed 2mo ago), licensed MIT. It adds 1,281 tokens to every session, about $0.0064 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
claude-code-ultimate-guide CLAUDE.md
Claude Code instructions for FlorianBruniaux/claude-code-ultimate-guide, covering claude code ultimate guide - project context, purpose, repository structure, published at: https://cc.bruniaux.com/whitepapers/ and key files.
claude-code-ultimate-guide copilot-instructions.md
Copilot instructions for FlorianBruniaux/claude-code-ultimate-guide: Use /CLAUDE.md as the single source of truth for this repository.
awesome-agentic-coding AGENTS.md
AGENTS.md instructions for Supersynergy/awesome-agentic-coding, covering agents.md, commands and repo rules.
AIWiki CLAUDE.md
Claude Code instructions for XuebinMa/AIWiki, covering claude.md — aiwiki 项目记忆, 这是什么, 每次动手前必读（按顺序）, 写作 / 翻译用 skill（不要手搓流程） and 保持连贯的硬规则（防止跨会话的风格 / 内容漂移）.
awesome-agentic-coding CLAUDE.md
Claude Code instructions for Supersynergy/awesome-agentic-coding, a project described as: Turn Claude Code into a failsafe, token-efficient, one-shot coding machine. 50+ tools, 7 skills, 5 hooks, 3 agents, 9 deep-dive guides. 1-click setup.
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.