nanocc: Instructions file for Claude Code

CLAUDE.md

nanocc CLAUDE.md is an instructions file for Claude Code from ZJUFangzh/nanocc. It costs 2,405 tokens per session, scanned A, original, MIT.

Project instructions for nanocc, a small Python recreation of Claude Code that can run as a command-line tool or be embedded in another product as an agent runtime. It describes the project structure, technology choices, and configuration.

In plain words
What is it for?
Use it when developing nanocc, checking its architecture and progress, configuring language-model providers, or understanding its boundary with the separate cowork project.
Why use it?
It gives contributors a shared reference for where code belongs, which design decisions to follow, and how providers, models, and API keys are configured.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is ZJUFangzh/nanocc's own configuration. It tells Claude Code how to work on nanocc itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nanocc configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ZJUFangzh/nanocc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ZJUFangzh/nanocc/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ZJUFangzh/nanocc

Made for: Claude Code.

Wrote 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.

agentmods badge for nanocc CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zjufangzh/nanocc/claude-md/github.svg)](https://agentmods.dev/instructions/zjufangzh/nanocc/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zjufangzh/nanocc/claude-md"><img src="https://agentmods.dev/badge/instructions/zjufangzh/nanocc/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.

agentmods 80×15 button for nanocc CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zjufangzh/nanocc/claude-md"><img src="https://agentmods.dev/badge/instructions/zjufangzh/nanocc/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,405 This file is loaded in full into every session.
When invoked 2,405 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02405 $0.02405
Opus 5.5 $0.00962 $0.00962
Sonnet 5.5 $0.00481 $0.00481
Haiku 4.5 $0.00241 $0.00241

Measured 2mo ago against content hash a135fcd8b815, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nanocc 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.

CLAUDE.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — nanocc 项目指南

项目概述

nanocc 是 Claude Code 2.1.88 的 Python 精简复刻,目标 ~10,000 行。 定位为纯 agent runtime:既可作为 CLI 日常使用,也可作为 Agent SDK 嵌入到上层产品。 IM 接入(Telegram/Slack/...)、桌面 GUI、多 session 编排等产品层功能由独立的 cowork 项目实现, 不在 nanocc 范围内。详见 docs/cowork-boundary.md。

关键文件

  • ARCHITECTURE.md — 完整架构规划(10 个 Phase),任何设计决策都以此为准
  • docs/progress.md — 开发进度和已完成的 Phase 记录
  • docs/cowork-boundary.md — nanocc 与 cowork 的边界,cowork 项目消费 nanocc 的方式
  • ../claude-code-main/ — Claude Code 源码参考

技术栈

  • Python >=3.11,用 uv 管理依赖和运行
  • 构建: hatchling(pyproject.toml)
  • CLI: click + rich
  • LLM: anthropic SDK(原生)+ openai SDK(兼容层)
  • 默认 Provider: openrouter(OpenAI 兼容 API)
  • 类型系统: dataclass(不用 Pydantic)

配置

Provider/Model/API Key 通过 ~/.nanocc/settings.json(全局)或 .nanocc/settings.json(项目级)配置:

{
  "provider": "openrouter",
  "model": "qwen/qwen3.5-flash-02-23",
  "apiKey": "sk-or-v1-..."
}

自定义 OpenAI 兼容 API:

{
  "provider": "custom",
  "apiBaseUrl": "https://my-api.com/v1",
  "model": "my-model",
  "apiKey": "..."
}

优先级:/model 会话覆盖 > CLI 标志 > 环境变量 > settings.json > 内置默认值

已知 provider:openrouter、anthropic、openai(自动匹配 baseUrl)。 其他名字走 OpenAI 兼容(custom),需配 apiBaseUrl。

常用命令

# 运行(配好 settings.json 后无需额外参数)
uv run nanocc -p "prompt"                          # 单轮
uv run nanocc                                       # REPL
uv run nanocc -c                                    # 恢复上次会话
uv run nanocc -m qwen/qwen3.5-flash --api-key $KEY # CLI 标志覆盖 settings

# REPL 中切换模型 / 恢复会话
> /model                                            # 查看当前模型
> /model qwen/qwen3.5-flash-02-23                   # 切换模型
> /resume                                           # 列出并恢复历史会话

# 安装为全局 CLI(editable 模式,改代码立即生效)
uv tool install -e .                                # 推荐:装到 ~/.local/bin/nanocc
pip install -e .                                    # 备选:装到当前 Python 环境
# 装完后任意目录直接运行 nanocc,无需 uv run

# 开发
uv run python -c "import nanocc"                    # 验证导入
uv run python -m nanocc --help                      # CLI 帮助

# 测试
uv run pytest tests/ -v                             # 全量测试(170 个)
uv run pytest tests/test_query.py -v                # 单模块测试

Read the full file on GitHub · 169 lines

Changes

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.

  1. 2mo ago First seen · 169 lines · 2,405 tokens per session scan A a135fcd8b815

Subscribe to this mod's changes

nanocc CLAUDE.md is an instructions file published in the GitHub repository ZJUFangzh/nanocc (6 stars, last pushed 7mo ago), licensed MIT. It adds 2,405 tokens to every session, about $0.0096 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 2026-08-31.

Related

nanocc CLAUDE.md compared with instructions from other repositories

nanocc CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
nanocc CLAUDE.mdZJUFangzh/nanoccInstructions file67mo agoMITA2,405Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode