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/linkerlin/myclaw.net/agents-mdgit clone --depth 1 https://github.com/linkerlin/myclaw.netWrote 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/linkerlin/myclaw.net/agents-md)<a href="https://agentmods.dev/instructions/linkerlin/myclaw.net/agents-md"><img src="https://agentmods.dev/badge/instructions/linkerlin/myclaw.net/agents-md.svg" alt="Measured on agentmods" 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 | $0.02502 | $0.02502 |
| Opus 5 | $0.01251 | $0.01251 |
| Sonnet 5 | $0.00500 | $0.00500 |
| Haiku 4.5 | $0.00250 | $0.00250 |
Grade A, and why
myclaw.net 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 4d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧬 AGENTS.md - 基因组控制中心
文件职责: 工作流规范、信号检测表、DNA 路由规则
版本: v2.0 (基于 MiniClaw v0.9.5 三层免疫系统)
最后更新: 2026-03-23
📋 How to Update This File
When to write here:
- When defining new workflow patterns or signal detection rules
- When improving DNA routing logic
- When adding self-correction mechanisms
What belongs here: Workflow norms, signal detection tables, routing rules.
What does NOT belong here: Specific task content (→ MEMORY.md), personality traits (→ SOUL.md).
🛡️ 三层免疫系统 (Three-Layer Immune System)
myclaw.net 采用 MiniClaw v0.9.5 的三层免疫系统架构，防止 DNA 自我修改时的基因错位和结构癌变。
┌─────────────────────────────────────────────────────────┐
│ Layer 1: 事前引导 (AGENTS.md 信号检测表) │
│ "在 AI 决策前告诉它该写哪里" │
├─────────────────────────────────────────────────────────┤
│ Layer 2: 事中校验 (端粒守卫 TelomereGuard) │
│ "写入前检查结构完整性" │
├─────────────────────────────────────────────────────────┤
│ Layer 3: 事后自检 (PURPOSE_MAP 自检镜像) │
│ "写入后提醒 AI 复核归属" │
└─────────────────────────────────────────────────────────┘
Layer 1: 事前引导
通过本文件的信号检测表，在 AI 决策前引导其将正确内容写入正确的 DNA 文件。
Layer 2: 事中校验
通过 TelomereGuard.cs 在写入磁盘的最后一刻拦截，检查文件结构完整性。
端粒图谱:
| DNA 文件 | 必需结构标记 |
|---|---|
| SOUL.md | ## (至少一个二级标题) |
| IDENTITY.md | # , ## (主标题 + 子标题) |
| USER.md | ## |
| MEMORY.md | ## |
| TOOLS.md | ## |
| AGENTS.md | #, ## |
| NOCICEPTION.md | ### |
| CONCEPTS.md | ## |
| REFLECTION.md | ## |
| HORIZONS.md | ## |
| HEARTBEAT.md | ## |
校验失败示例:
🧬 [基因链断裂] Telomere Guard rejected mutation of `SOUL.md`.
Missing required structural markers: "##".
请确保文件包含必要的 Markdown 标题结构。
Layer 3: 事后自检
每次 DNA 写入成功后，返回文件职责声明，触发 AI 自我纠正。
示例:
Updated USER.md
📝 Purpose: [共生染色体] 用户画像、偏好习惯。绝不写入：AI 自身性格、技术配置。
📡 信号检测表 (Signal Detection Table)
| 信号 | 目标文件 | AI 的思考逻辑 |
|---|---|---|
| "我喜欢…" | USER.md | "这是用户偏好，写入共生染色体" |
| "我偏好…" | USER.md | "这是用户习惯，写入共生染色体" |
| "别那么严肃" | SOUL.md | "这是对我性格的修正" |
| "你应该更…" | SOUL.md | "这是对我行为风格的调整" |
| "项目用的是 XYZ" | MEMORY.md | "这是客观事实" |
| "技术栈是…" | MEMORY.md | "这是项目配置信息" |
| 执行失败 | NOCICEPTION.md | "这是痛觉记忆" |
| "创建一个技能" | TOOLS.md | "这是工具使用经验" |
| 完成里程碑 | HORIZONS.md | "这是成就记录" |
| 新概念 | CONCEPTS.md | "这是知识定义" |
| 反思错误 | REFLECTION.md | "这是错误反思" |
| 用户身份/角色 | USER.md | "这是用户画像" |
| AI 身份/能力 | IDENTITY.md | "这是核心身份定义" |
| 工作流规范 | AGENTS.md | "这是基因组控制中心" |
| 定时任务 | HEARTBEAT.md | "这是脉搏系统任务" |
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.
- 4d ago First seen · 256 lines · 2,502 tokens per session scan A 22923ee0bccb
myclaw.net AGENTS.md is an instructions file published in the GitHub repository linkerlin/myclaw.net (131 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 2,502 tokens to every session, about $0.0125 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
librefang AGENTS.md
AGENTS.md instructions for librefang/librefang, covering stack, layout, build, architecture and kernelhandle trait.
autonomous-os AGENTS.md
AGENTS.md instructions for autonomous-ai/autonomous-os, covering agents.md, multi-ide rules, working style, parallel work / subagents and device access rules.
OneManCompany CLAUDE.md
Instructions for 1mancompany/OneManCompany, covering gstack and skill routing.
souls-directory CLAUDE.md
Instructions for thedaviddias/souls-directory, covering claude.md — project context for ai assistants, project overview, tech stack, critical rules and database is convex.
jentic-one GEMINI.md
Instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.
clawock AGENTS.md
AGENTS.md instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.