Borrowing it
Nothing to install: this file belongs to Shiyao-Huang/awesome-agent-evolution. 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/Shiyao-Huang/awesome-agent-evolution/main/CLAUDE.mdgit clone --depth 1 https://github.com/Shiyao-Huang/awesome-agent-evolutionWrote 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/shiyao-huang/awesome-agent-evolution/claude-md)<a href="https://agentmods.dev/instructions/shiyao-huang/awesome-agent-evolution/claude-md"><img src="https://agentmods.dev/badge/instructions/shiyao-huang/awesome-agent-evolution/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/shiyao-huang/awesome-agent-evolution/claude-md"><img src="https://agentmods.dev/badge/instructions/shiyao-huang/awesome-agent-evolution/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 | $0.04086 | $0.04086 |
| Opus 5.5 | $0.01634 | $0.01634 |
| Sonnet 5.5 | $0.00817 | $0.00817 |
| Haiku 4.5 | $0.00409 | $0.00409 |
Grade A, and why
awesome-agent-evolution 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 2mo 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Claude/Claude Code 在本仓库工作时，以 AGENTS.md 为最高操作手册。本文件只补充 Claude 侧协作规则。
Priority
- 公开文案质量是最高指导：网页、README、README-EN、论文页、topic/blog/SEO 入口和 metadata 必须有逻辑、可读、可吸收、双语同证据链，并通过读者/编辑 agents 与学术 agents 双通道审查。
- 再以当前对话里的用户直接输入为准；本地私有用户输入记忆只能辅助判断，禁止提交或发布。
- 再读 README.md、CONTENT_INDEX.md、docs/project-management/project-structure.md。
- 改动后刷新 docs/indexes/master-index.md。
User Input Privacy
用户输入原文、抽取文件和长期用户记忆只保留本地，不进入公开仓库。公开手册只保留操作原则：目标来源以当前用户输入为准，raw/processed/work/results 分层治理，长期产物必须索引化，论文和网站改动必须验证。
非四层构成材料不要直接删除；先按 docs/project-management/noncanonical-cleanup-policy.md 归类，并刷新 docs/indexes/noncanonical-index.md。
Claude Working Style
- 用分层表达输出判断：1 句话、3 句话、5 句话、完整论证。
- 对论文和项目分析，优先补”数据从哪来、分析了哪些、进化相关有哪些、时间顺序如何”。
- 对 GitHub 项目排名，禁止把累计 Star 当作主要价值信号；优先查
analysis/github-star-growth-ranking.md、data-engine/github-star-history/和覆盖状态，用 2026 新增 Star / recent velocity 判断当前阶段动量。 - 对网站内容，优先保证 SEO title/description、静态可构建、public reports 可访问。
- 对项目卡，使用 model-card 类结构：任务、方法、证据、局限、适用场景、教学价值。
- 图表优先：当图表比文字更容易表达时，必须使用 Mermaid DAG、SVG 或数据可视化，不要只写文字。
- Mom Test：README 和面向用户的内容必须让非专业人士能理解项目做什么、为什么重要。
- Public copy review gate：所有公开文案，尤其网站、README、README-EN、SEO/topic/blog 页面和 metadata，发布前必须经过
3-5个读者/编辑 agents 与3个学术 agents 审查。读者/编辑看可读性、Mom Test、行动路径、中英入口；学术 agents 看术语、证据链、claim 强度、限制和[UNVERIFIED]。无法调度时必须在交付中写明风险，不能标记为质量已完成。 - 证据链：每个分析结论标注数据来源。无法追溯的标注
[UNVERIFIED]。 - 中文调查同步：
survey/是中文版调查，与paper-drafts/平行。修改一方时检查另一方是否需要同步。 - 读者/Agent 边界：README、网站首页、论文页、SEO 页面是给外部读者/消费者看的；不要把 agent 启动检查、内部构建命令、wiki ingest 流程、handoff 或自我系统说明塞进 README 主体。Agent 操作规则写在
AGENTS.md、CLAUDE.md、CLOUD.md或docs/ops/。 - Workflow 分流：具体执行见 docs/ops/audience-boundary-workflow.md。公开页面只写读者问题、证据、结论和下一步阅读；内部 workflow、验证门禁、handoff 和自我镜像规则留在 ops/wiki/agent 手册。
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.
- 2mo ago First seen · 240 lines · 4,086 tokens per session scan A c7e04d187e3a
awesome-agent-evolution CLAUDE.md is an instructions file published in the GitHub repository Shiyao-Huang/awesome-agent-evolution (68 stars, last pushed 3mo ago), licensed MIT. It adds 4,086 tokens to every session, about $0.0163 per session on Opus 5.5. 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.
awesome-agent-evolution CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| awesome-agent-evolution CLAUDE.mdShiyao-Huang/awesome-agent-evolution | Instructions file | 68 | 3mo ago | MIT | A | 4,086 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |