Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/lawofall/agentcore/agents-mdgit clone --depth 1 https://github.com/Lawofall/AgentCoreWhat 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 | $0.00780 | $0.00780 |
| Opus 5 | $0.00390 | $0.00390 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
AgentCore 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 2d 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.
What it actually says
AGENTS.md
AgentCore：面向大众的 Multi-Agent AI 工作台——真正的 Agent 团队协作（非「单 Agent + 子任务派发」）。Monorepo：apps/server · apps/desktop · apps/mobile · apps/admin + packages/。
跨工具 AI / 贡献者入口（本文件入仓、保持短）。详细产品与架构说明在 docs/，不在此复述。
文档以中文为准；根 README 仅一句英文产品介绍（检索用）。English docs are not maintained.
先读哪里
| 我要… | 去哪 |
|---|---|
| 任务路由 / 设计文档总入口 | docs/索引.md |
| 产品一句话、最短跑通、仓库地图 | README.md |
| 贡献 / PR / 勿提交什么 | CONTRIBUTING.md |
| 问问题 / Issue 去哪 | SUPPORT.md |
| clone 后跑通前后端 | docs/02-架构/本地开发.md |
Docs 与 Rules
| 公开仓 | 说明 | |
|---|---|---|
docs/01–05 |
✅ | What/Why：现状 + 已确认蓝图（⏳ = 已确认未落地；以代码与文内短指针为准） |
docs/06-规划/ |
❌ 不入公开树 | 详细提案仅维护者本地；勿依赖公开 clone 里存在该目录 |
.cursor/rules/ |
✅ | How（Cursor AI 操作细则）；与 docs/ 分工见 doc-governance.mdc |
开发 / 测试（最短）
在仓库根 pnpm install；后端见本地开发（uv sync、Compose、Alembic）。
验证分三档，默认走最低档——全量很贵：一次干净 release:gate 约 15–25 min，其中桌面截图独占 ~4 min（4 worker），后端全量 pytest ~5 min。
- 改完即验（默认）——只跑点名的测试文件 / 用例：
uv run pytest tests/x.py::test_y、pnpm --filter agentcore-desktop exec vitest run <文件> - 交付收尾——只跑改动所涉包：
pnpm test:server:unit、pnpm --filter <包> test -- --run、pnpm --filter <包> typecheck；不碰没改的包 - 发布门禁——仅发布决策时
pnpm release:gate；非发布语境要跑就--only <段>或release:gate:lite
改 OpenAPI / SSE / fold 才需 pnpm gen:types + pnpm conformance（没动契约就别跑，gen:types 是全仓重生成）。
窄化命令配方、门禁分段与反空转纪律 → verify-scope.mdc。
包级命令见各 apps/*/README。安全漏洞 → SECURITY.md（勿开公开 Issue）。
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.
- 2d ago First seen · 42 lines · 780 tokens per session scan A 25188f99e309
AgentCore AGENTS.md is an instructions file published in the GitHub repository Lawofall/AgentCore (78 stars, last pushed 2d ago), licensed MIT. It adds 780 tokens to every session, about $0.0039 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 2026-08-30.
Other instructions, from other repositories
n8n-desk CLAUDE.md
Claude Code instructions for geckse/n8n-desk, covering claude.md — n8n-desk build guide, project state, tech stack, project structure and critical patterns.
PiDeck AGENTS.md
Instructions for ayuayue/PiDeck, covering agents.md, 项目简介, 代码结构与跨层契约, 架构规则（硬性） and 模块内聚与低耦合（硬性）.
limboo CLAUDE.md
Instructions for limboo-ai/limboo, covering claude.md, 1. what is limboo?, 2. tech stack (current), 3. project structure and the three electron contexts (critical mental model).
tubecli AGENTS.md
Instructions for tubecreate/tubecli, covering contributor & ai assistant guidelines, attribution — must be preserved and scope.
Mutsumi AGENTS.md
Instructions for NERDSORG/Mutsumi, covering mutsumi 项目开发指南（agent 贡献者版）, 1. 架构总览, 核心分层原则, 2. notebook 系统与 ui 层 and 2.1 .mtm 文件模型与 serializer（notebook/serializer.ts）.
sprawling CLAUDE.md
Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.