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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/cronusl-1141/ai-company/agents-md"><img src="https://agentmods.dev/badge/instructions/cronusl-1141/ai-company/agents-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/agents-md"><img src="https://agentmods.dev/badge/instructions/cronusl-1141/ai-company/agents-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 | $0.02487 | $0.02487 |
| Opus 5 | $0.01243 | $0.01243 |
| Sonnet 5 | $0.00497 | $0.00497 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
AI-company AGENTS.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 today.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md（自动生成 · 请勿手改）
本文件是仓库根目录 CLAUDE.md 的等价副本，供读取 AGENTS.md 约定的编码助手使用。
下方正文逐字节复制自 CLAUDE.md，两份文件的规则完全一致。
- 改规则请改
CLAUDE.md，再跑python3 scripts/gen_agents_md.py重新生成本文件，与源改动同批提交。 - 标准头正文在
plugin/harness/codex/agents_md_header.md，生成器与机检共读这一份。 - 恒等式由红线机检 I18 对钉（
scripts/check_agents_md.py）：AGENTS.md ≠ 标准头 + CLAUDE.md即红。
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
- 所有输出使用中文
- 共享类型只引用
src/aiteam/types.py - 代码风格: PEP 8，类型注解，async优先
Leader核心行为
- 专注统筹，实施工作委派团队成员
- 新需求先加入任务墙，系统级功能先写设计文档
- 完整规则通过SessionStart自动注入，也可查询 GET /api/system/rules
- 用户给出偏好/纠正/设计意图时，当场用
memory_add落方向层（≤400字；只影响单个任务的去task_memo_add）；记忆整理用memory_reconcile_candidates/apply（设计见 docs/memory-v2-design.md） - 发版走 skill /os-release（清单唯一落点；Release 正文与
gh命令由scripts/release_notes.py生成，commit/tag 需用户批准，push 与 publish 由用户执行）
多会话并行纪律（2026-07-10 事故后立规）
- 本仓库可能同时有多个 CC 会话在工作。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 ../…落在桌面等同级目录；仓库内子目录会被 OS 按"子目录归属"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。（2026-09-09 缔造者裁定；实录：12 棵同级树堆在桌面，5 棵的工作只存在于未提交文件） - 若确需在主 checkout 操作：动手前先
git branch --show-current确认位置；切换分支/切回 master 前先git log --oneline -3确认没带走或丢下别人的提交。 - 事故实录：两 agent 共享 checkout，一方切分支干活，另一方的提交无察觉落在其分支上，切回时造成"代码消失"假象（靠 reflog 零丢失恢复）。
- 提交前跑
bash scripts/check_invariants.sh（红线机检：hook 副本同步/无遗留副本/版本锁步/双 dist 一致/venv 禁令/README 数字与实测一致/ruff 门禁/hook 注册面统一/MCP 工具参数描述/表集合一致——条目与细则以脚本输出为准）。
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 机检；隔离方案已被否决）
- hook 多副本：plugin/hooks 与 src/aiteam/hooks 同名文件必须逐字节一致（I1 机检）——不是重复代码，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 内的工具数/页面数由 I6 对照实测机检——别手动"改回"旧值，加减 MCP 工具时同步双语 README
- 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，2026-07-07 立规）。注意这不指模板 frontmatter——plugin/agents/*.md 已固化层级别名
model: opus（2026-07-10 裁定，别名浮动不算写死）；派工纪律见编排宪章：Fable 编排、Opus 执行，workflowagent()默认显式model:'opus'（skill /os-workflow §3）；fable 须带[fable 理由: …]标记（workflow 内为// fable 理由:注释），S6 派工门禁机检兜底：缺省 model 拦、fable 无理由拦；额度溢出时的放宽是临时特例，须缔造者当次明令并注明有效期，不得沉淀为常规；用量七规则（机检先行、审查分级 L0/L1/L2 按风险定不按预算定、每条发现一个反驳者、审查给章节定位不给全文、折入先机检再决定下一轮、回传≤300 字、Leader 大文档改动派 opus 执行）见 skill /os-workflow §3.1（2026-09-05 缔造者裁定，方向记忆【模型分层与用量平衡】指向该节）；ultracode 常开不等于事事开 workflow：L0/L1 直接做，只有 L2 才开，限制的是"任何问题都按最复杂方式做完"，不是把复杂问题做简单 - 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
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.
- today Changed · +1 lines · +127 tokens per session 07a416c90da8
- yesterday First seen · 65 lines · 2,360 tokens per session scan A 2ecc97d9a548
AI-company AGENTS.md is an instructions file published in the GitHub repository CronusL-1141/AI-company (357 stars, last pushed yesterday), licensed MIT. It adds 2,487 tokens to every session, about $0.0124 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 2026-09-08.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.