Borrowing it
Nothing to install: this file belongs to femto/minion. 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/femto/minion/main/CLAUDE.mdgit clone --depth 1 https://github.com/femto/minionWrote 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/femto/minion/claude-md)<a href="https://agentmods.dev/instructions/femto/minion/claude-md"><img src="https://agentmods.dev/badge/instructions/femto/minion/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/femto/minion/claude-md"><img src="https://agentmods.dev/badge/instructions/femto/minion/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 | $0.02183 | $0.02183 |
| Opus 5.5 | $0.00873 | $0.00873 |
| Sonnet 5.5 | $0.00437 | $0.00437 |
| Haiku 4.5 | $0.00218 | $0.00218 |
Grade A, and why
minion 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧠 记忆存储
系统架构记忆
-
never put test in the top level folder
-
agent.run_async() 返回的是一个async函数,需要先await才能获得async generator
- 正确用法:
async for event in (await agent.run_async(input_obj, **kwargs)): - 错误用法:
async for event in agent.run_async(input_obj, **kwargs): - 这是因为run_async是async函数,它delegate到其他函数,本身需要await才能返回真正的async generator
- 正确用法:
-
Agent构造函数设计模式
- 所有Agent应继承BaseAgent并使用@dataclass装饰器
- 构造函数参数应与BaseAgent对齐,使用dataclass字段而非__init__方法
- stream相关参数不应在构造函数中,而是通过run_async(stream=True/False)动态控制
-
LLM构造和获取最佳实践
- MinionToolCallingAgent构造时会自动从model配置创建LLM
- 标准LLM获取模式(参考brain.py):
# 方式1:直接指定model名称,从config.models获取配置 model = "gpt-4o" # 或其他模型: "gemini-2.0-flash-exp", "deepseek-r1", "phi-4", "llama3.2" llm_config = config.models.get(model) llm = create_llm_provider(llm_config) # 方式2:使用默认模型 llm = create_llm_provider(config.models.get("default")) # 方式3:在Agent构造时传入model名称,让Agent自动创建 agent = MinionToolCallingAgent(model="gpt-4o") # 会自动创建LLM # 使用dataclass风格构造 agent = MinionToolCallingAgent( name="my_agent", tools=[tool1, tool2], model="gpt-4o", max_tool_threads=4 ) - Brain类LLM处理逻辑:支持字符串model名称或直接传入LLM实例
- 如果llm参数是字符串,会调用
create_llm_provider(config.models.get(llm)) - 如果llm参数是LLM实例,直接使用
- 支持llms字典批量处理多个模型配置
- 如果llm参数是字符串,会调用
-
functions.final_answer调用修复
- 修复了
functions.final_answer()调用不抛异常的问题 - 问题原因:
functions命名空间中的final_answer是原始版本,不会抛出FinalAnswerException - 解决方案:在
evaluate_async_python_code中创建异常包装器后,同时更新functions命名空间 - 现在
functions.final_answer()和直接调用final_answer()都会正确抛出异常并设置is_final_answer=True
- 修复了
-
worker.py终止逻辑修复
- 修复了Python executor返回
is_final_answer=True但任务不终止的问题 - 问题原因:worker.py获取了
is_final_answer值但没有使用,硬编码terminated=False - 解决方案:当
is_final_answer=True时立即返回terminated=True的AgentResponse - 现在final_answer工具调用会正确终止任务执行
- 修复了Python executor返回
-
Minion流式处理重构
- 在基类Minion中添加了
stream_node_execution通用方法 - 所有子类现在使用统一的流式处理逻辑,直接yield StreamChunk对象
- 移除了错误的final_answer检测逻辑,final_answer处理由LmpActionNode负责
- 保持StreamChunk对象的原始结构,便于上层UI正确处理不同类型的chunk
- 在基类Minion中添加了
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 · 167 lines · 2,183 tokens per session scan A 4a5716a3ef91
minion CLAUDE.md is an instructions file published in the GitHub repository femto/minion (151 stars, last pushed 29d ago), licensed MIT. It adds 2,183 tokens to every session, about $0.0087 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.
minion CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| minion CLAUDE.mdfemto/minion | Instructions file | 151 | 29d ago | MIT | A | 2,183 | 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 | yesterday | 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 |