Borrowing it
Nothing to install: this file belongs to CronusL-1141/AI-company. 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/CronusL-1141/AI-company/master/CLAUDE.mdgit clone --depth 1 https://github.com/CronusL-1141/AI-companyWrote 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/cronusl-1141/ai-company/claude-md)<a href="https://agentmods.dev/instructions/cronusl-1141/ai-company/claude-md"><img src="https://agentmods.dev/badge/instructions/cronusl-1141/ai-company/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/cronusl-1141/ai-company/claude-md"><img src="https://agentmods.dev/badge/instructions/cronusl-1141/ai-company/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 | $0.02576 | $0.02576 |
| Opus 5.5 | $0.01030 | $0.01030 |
| Sonnet 5.5 | $0.00515 | $0.00515 |
| Haiku 4.5 | $0.00258 | $0.00258 |
Grade A, and why
AI-company 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 16d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Team OS
技术栈: Python 3.12 + FastAPI | React 19 + Vite | SQLite 架构: Storage → API → Dashboard（详见 docs/architecture.md）
核心约束
- 中文是默认语言（对话、文档、任务/记忆条目、commit message）；例外：
README.md与CHANGELOG.md保持英文为正本（README.zh-CN.md/CHANGELOG.zh-CN.md是镜像译本）、代码标识符用英文 - 共享类型只引用
src/aiteam/types.py - IO 路径一律 async，请求处理里禁阻塞调用（一次同步 Git 扫描就曾拖住整个 API）；秒级纯 Python 计算同样不能在请求处理里跑，放进线程也会抢 GIL，要放子进程（记忆整理 candidates 曾冻住 API 13 分钟）
Leader核心行为
- 新需求先加入任务墙，系统级功能先写设计文档
- 用户给出偏好、纠正或设计意图时当场落账：运行期 agent 需要被告知的写方向层（
memory_add），开发期产品设计写设计文档与任务墙 decision；只影响单个任务的用task_memo_add（字数上限、桶配额与整理流程见 docs/memory-v2-design.md） - 发版走 skill /os-release（清单唯一落点）；不论走没走 skill：commit/tag 须用户批准，push 与 publish 由用户执行
多会话并行纪律
- 本仓库可能同时有多个会话在工作（Claude Code 与 Codex 都算）。第二个及之后的会话改代码必须用
git worktree隔离，禁止共享同一 checkout 写代码。 - worktree 一律建在仓库内
.worktrees/<名字>（已 gitignore），禁止git worktree add ../…落到同级目录：OS 按「子目录归属」把仓库内子目录解析到本项目，同级目录解析不到。用完git worktree remove <路径>再git worktree prune。 - 确需在主 checkout 操作：动手前
git branch --show-current，切分支前git log --oneline -3——共享 checkout 切分支会带走别人未察觉的提交（实录见 docs/architecture.md 附录）。 - 提交前跑
bash scripts/check_invariants.sh（红线条目以脚本输出为准）。本机全量测试用python3 -m pytest tests/ -n 4 --dist loadfile（约 5 分钟；CI 保持串行）。
刻意决策 — 禁止悄悄回退
以下设计看着反常但全是故意的（各有血泪史或机检背书），发现"可以修好"的冲动时先停手：
- venv 禁令：四类进程共享依赖，坚持系统 Python + sys.executable（I5 只扫
src/aiteam/**.py，在 shell 里建 venv 它抓不到） - hook 多副本是故意的：
plugin/hooks与src/aiteam/hooks同名文件逐字节一致（I1，共享核 hook_core.py 在含 Codex 适配器的三处各存一份）——禁止「去重」，改一处必须同步所有副本 - tasks.config.memo 是冻结档案：记忆 v2 升表后新 memo 只进 task_memos 表，旧 JSON 保留作历史——不是脏数据，别清理也别再写入
- README 里的工具数/页面数以实测为准（I6 扫双语两份）——别手改回旧值
- 模型默认值留空（仅指 DB 观测字段）：agents.model 未知就空着由观测回填，别补具体型号（写死必过时）
- 无定时器/后台守护：CC 非常驻，周期 cron 已刻意退役，一律按需工具——别"补回"调度
Council 四纪律（会议 e7e90df0 决议、用户批准；约束 Leader 裁决）
- no-data≠zero：任何基于"表 0 行/零调用"的裁撤，必须先排除采集断链/迁移丢失/口径隔离三种成因才可议——本库是迁移新库，历史分母不可信（曾差点在残库上砍掉会议功能）
- 排期闸=行动信号>表态信号：外部 issue 👍 数只能排细节优先级，立项须有真实人类行动信号（动手提 PR/追问后翻转）
- dogfooding 验收=故障注入非时长：对外讲"崩溃不丢"前必须有一次真实杀 session 恢复实证，"自用一周"证明不了持久性
- 会议以决策上墙收尾（decision 或任务墙条目），否则视同没开。减法要留痕：刻意决策回退 / 砍工具删表 / 削弱或删除机检红线，走会议或缔造者当场裁定都算数，但结论必须上墙——这类东西丢了难重建，血泪史全是这个形态。加法不设闸：新增机检条目、加严已有判据、新增工具或表，写清理由直接做。拿不准算加法还是减法，按减法办。会议能力保留但不进对外叙事第一屏
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.
- 16d ago Changed 897321a48bc1
- 26d ago Changed · +196 tokens per session 829df1497f76
- 1mo ago Changed · +2 lines · +285 tokens per session 60c734569cb0
- 1mo ago Changed · +96 tokens per session 0c640313fd0d
- 1mo ago Changed · -1 lines · -292 tokens per session 929bdfaa482b
- 1mo ago Changed · +1 lines · +127 tokens per session 00250a6aefc2
- 1mo ago Changed · +6 lines · +558 tokens per session 064d3c34141f
- 1mo ago First seen · 46 lines · 1,606 tokens per session scan A 52a320442961
AI-company CLAUDE.md is an instructions file published in the GitHub repository CronusL-1141/AI-company (374 stars, last pushed 16d ago), licensed MIT. It adds 2,576 tokens to every session, about $0.0103 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.