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 skills add metago-ai/metagolifeform --skill metago-disciplinegit clone --depth 1 https://github.com/metago-ai/metagolifeformWrote 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/skills/metago-ai/metagolifeform/metago-discipline)<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-discipline"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-discipline/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/skills/metago-ai/metagolifeform/metago-discipline"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-discipline.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 | $0.00066 | $0.00513 |
| Opus 5.5 | $0.00026 | $0.00205 |
| Sonnet 5.5 | $0.00013 | $0.00103 |
| Haiku 4.5 | $0.00007 | $0.00051 |
Grade A, and why
metago-discipline 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 1mo 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
AI 自律执行协议（metago-discipline）
描述
在输出"任务完成"前必须执行的五问自检，作为交付的最后一道防线。包含反绕过识别机制，把"AI 知道要做"变成"AI 不可绕过地执行"。
触发条件
每次 AI Agent 输出"任务完成"或"交付完成"状态前自动激活。
核心流程
- 五问自检
- ① 是否运行 npm run verify？
- ② verify 输出是否有 FAIL？
- ③ 交付报告含验证小节？
- ④ 每项 ✅ 有执行证据？
- ⑤ 是否做了业务层验证？
- 任何一问答"否" → 禁止宣告完成
- 反绕过识别
- 检测"应该没问题"/"逻辑上正确"/"之前验证过"等绕过话术
- 输出自检结果 + 绕过检测结果
输出格式
五问自检清单（每项 ✅/❌ + 证据或缺失项），反绕过检测结果。
根源文档
AGENTS.md 第十五章「AI 自律执行协议」
与其他技能的协同
- 与
metago-delivery-gate协同：组成完整质量闭环 - 与
metago-self-check协同：双重自检，防遗漏 - 与
metago-fact-check协同：验证报告中声明的事实真伪
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.
- 1mo ago First seen · 46 lines · 66 tokens per session scan A f43cd67cb8ca
metago-discipline is a skill published in the GitHub repository metago-ai/metagolifeform (5 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 513 once invoked, about $0.0003 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.
Other skills, from other repositories
todo-for-ai-agent-runtime
Runtime integration skill for external agents connecting to Todo for AI over HTTP API Token / Agent Key, including auth, task lease, events, commit, and task logs.
monetization-guide
A Chinese-language guide for creating business and pricing plans. It first classifies the situation, such as launching a new paid product, changing prices, or exploring a new way to earn revenue.
wechat-article-scraper
A batch tool for downloading WeChat public-account articles from their URLs as Markdown files. It also downloads the articles' images and links them locally.
karpathy-guidelines
Tool-agnostic behavioral guidelines for AI coding assistants. Use when writing, reviewing, debugging, or refactoring code to reduce overengineering, surface ambiguity, make surgical changes, and define verifiable success criteria.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).