agentmods.dev

metagolifeform: Instructions file for Claude Code

AGENTS.md

metagolifeform AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from metago-ai/metagolifeform. It costs 33,357 tokens per session, scanned A, original, MIT.

A set of instructions for an AI coding assistant that defines a required six-step delivery process and four checks before work can be called complete.

In plain words
What is it for?
Use it to guide software tasks through requirement tracking, interface checks, screenshot comparison, and a final machine-checked delivery report.
Why use it?
It prevents unfinished work from being marked done by requiring documented requirements, automated checks, visual comparisons, and evidence.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: PostToolUse hook event, but also the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

This is metago-ai/metagolifeform's own configuration. It tells Claude Code, Codex and OpenCode how to work on metagolifeform itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything metagolifeform configures →

not rated 5repo changed today A scan 33,357 tokens original MIT
View source ↗ metago-ai/metagolifeform metago.life
Reuse

Borrowing it

Nothing to install: this file belongs to metago-ai/metagolifeform. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/metago-ai/metagolifeform/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/metago-ai/metagolifeform

Made for: Claude Code, Codex, OpenCode.

Wrote 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.

agentmods badge for metagolifeform AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/metago-ai/metagolifeform/agents-md/github.svg)](https://agentmods.dev/instructions/metago-ai/metagolifeform/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/metago-ai/metagolifeform/agents-md"><img src="https://agentmods.dev/badge/instructions/metago-ai/metagolifeform/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.

agentmods 80×15 button for metagolifeform AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/metago-ai/metagolifeform/agents-md"><img src="https://agentmods.dev/badge/instructions/metago-ai/metagolifeform/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33,357 This file is loaded in full into every session.
When invoked 33,357 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.33357 $0.33357
Opus 5.5 $0.13343 $0.13343
Sonnet 5.5 $0.06671 $0.06671
Haiku 4.5 $0.03336 $0.03336

Measured today against content hash 126efa2be100, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

metagolifeform AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- [ ] **L2.1 Web 端可达**：`curl -I https://metago.life/studio/` 返回 200（附状态码）
AGENTS.md · 1,675 lines

How it starts

The opening of the file, as written. The whole thing — 1,675 lines — stays where its author put it; the contents beside it link to each section on GitHub.

元构超级智能生命体运行法则（MetaGO Lifeform Operating Law）

本文件是元构智能生命体运行法则的母本（DeepSeek Harness 第一人称视角撰写）。每次会话自动加载。 基于 元构初始文档/（4 附录卷 · V9.0–V36.3 原文 + 附录卷-原子契约补全-V36.11）与本文增量，由 元构·智能生命体 V36.12.0 安装。

多平台说明：本母本以 DeepSeek Harness 为运行时撰写；安装到其他平台时，scripts/install.* 会从 adapters/<platform>/ 模板生成对应平台的适配版（CLAUDE.md / AGENTS.md / metago.mdc 等）， 平台专属措辞（如"DeepSeek Harness 的四个子系统"）在适配版中会被替换为对应平台的等价结构。 直接阅读本文件的非 DeepSeek Harness 用户：把"DeepSeek Harness"读作"当前 AI 编程平台"即可，法则本体与平台无关。

第零节 UDGK 通用交付门禁（Universal Delivery Gate Kit）

UDGK = Universal Delivery Gate Kit（通用交付门禁工程套件）V3.0.0。 任何任务宣告「完成」前，必须运行 UDGK 交付门禁（verify-delivery.cjs 四重门禁），任何一项 FAIL 禁止宣告完成。

0.1 6 步执行流程（强制按序）

1. node scripts/init-delivery.cjs      # 初始化（生成 RTM 空表 + delivery.config.json + 目录骨架）
2. 逐字读需求文档 → 填满 RTM           # 一条需求缺失 = 禁止往下
3. 实现 → 每条需求写形态断言            # 复制 templates/form-assertions.spec.ts 到 e2e/asserts/
4. 截图基线 → 视觉 diff                # visual-regression.cjs --snapshot + --baseline
5. node scripts/verify-delivery.cjs    # 四重门禁 → 出报告
6. 报告全绿 + 证据截图 → 才允许宣告完成  # 任一 FAIL → 回到 2/3/4 修复

0.2 四重门禁（缺一不可，机器可判定、可一票否决）

  1. RTM 完整性：docs/rtm.md 表头四列齐备（要求→代码→断言→证据）+ 无空要求 + 无空证据
  2. 形态断言：e2e/asserts/ 断言全部通过（把「长什么样」翻译成 DOM 断言，P0 阻断）
  3. 视觉 diff：current/ 与 baseline/ 像素差 ≤ 阈值（默认 2%），量化「界面真的变了没有」
  4. 报告生成：docs/delivery-report.md 全绿，证据链完整

0.3 配置驱动

所有脚本读 delivery.config.json（需求文档在哪、断言目录、截图目录、diff 阈值）。换项目只改配置不改代码。

0.4 执行命令

node scripts/init-delivery.cjs          # 初始化骨架
node scripts/verify-delivery.cjs --strict   # 四重门禁（strict=警告也FAIL）
node scripts/visual-regression.cjs --snapshot --urls=<页面>   # 截图
node scripts/visual-regression.cjs --baseline                  # 建基线

0.5 反绕过条款

  • 禁止「应该没问题」代替实际验证
  • 禁止跳过四重门禁中任意一重
  • 禁止将「编译通过」等同于「形态达标」
  • 禁止不跑 verify-delivery.cjs 就宣告完成
  • 每项 ✅ 必须附带执行证据（命令输出 / HTTP 状态码 / 截图 / 断言结果）

0.6 形态达标（L8）核心原则

  • 仅修改样式参数（圆角/字号）不满足形态要求
  • 必须实现独立组件形态（工具调用卡片、思考流可折叠块、AI 头像、事件流逐块追加）
  • 每个形态要求必须有对应 DOM 断言 + 视觉基线证据

Read the full file on GitHub · 1,675 lines

Changes

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.

  1. today Changed · +255 lines · +6,910 tokens per session 126efa2be100
  2. 26d ago Changed ba0a7d2b2311
  3. 1mo ago Changed · +218 lines · +5,290 tokens per session 10957afcdc35
  4. 1mo ago First seen · 1,202 lines · 21,157 tokens per session scan A e70382b17914

Subscribe to this mod's changes

metagolifeform AGENTS.md is an instructions file published in the GitHub repository metago-ai/metagolifeform (5 stars, last pushed today), licensed MIT. It adds 33,357 tokens to every session, about $0.1334 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

ai-evolutionai-lifeformcursormcpmetagotrae
Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,581 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens