Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/metago-ai/metagolifeformnpx agentmods add skills/metago-ai/metagolifeform/metago-delivery-gateWrote 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-delivery-gate)<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-delivery-gate"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-delivery-gate/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-delivery-gate"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-delivery-gate.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 | $0.00081 | $0.01549 |
| Opus 5 | $0.00041 | $0.00775 |
| Sonnet 5 | $0.00016 | $0.00310 |
| Haiku 4.5 | $0.00008 | $0.00155 |
Grade A, and why
metago-delivery-gate 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 12d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UDGK 通用交付门禁（metago-delivery-gate）
描述
把「文档/需求」翻译成「可判定的四重门禁」。任何 AI 接到任务时按同一套流程执行，从机制上杜绝「验证全绿但形态没做」。任何一项 FAIL 禁止宣告完成。
触发条件
用户说「按 UDGK 执行」、收到「任务完成」类指令、或任何代码交付请求时必须激活。本技能是 UDGK 套件的能力层，配合 AGENTS.md 规则（引导）、MCP 工具 delivery_gate_check（强制）、记忆注入（跨会话）、脚本套件（可执行）使用。
本套件包含 5 个可复用资产
| 资产 | 文件 | 作用 |
|---|---|---|
| ① RTM 模板 | templates/requirements-traceability.md |
需求逐条翻译成「要求→代码→断言→证据」映射表 |
| ② 形态断言模板 | templates/form-assertions.spec.ts |
把「长什么样」翻译成 DOM 断言 |
| ③ 视觉基线器 | scripts/visual-regression.cjs |
截图 + 像素 diff，量化「变了没有」 |
| ④ 通用门禁脚本 | scripts/verify-delivery.cjs |
一键扫描 RTM + 跑断言 + 跑 diff + 汇总报告 |
| ⑤ 使用手册 | METHODOLOGY.md |
教会 AI 和人类：怎么用这套件 |
脚本套件位于本包
scripts/udgk/（全局安装后为~/.trae-cn/scripts/或项目scripts/udgk/）。
AI 使用流程（6 步，必须按序执行）
任何一步系统判定 FAIL，回到对应步骤修复，禁止「宣布完成但不做」。
1. init-delivery.cjs 初始化
→ node scripts/init-delivery.cjs 生成 delivery.config.json + RTM 空表 + 目录骨架
（已初始化则跳过）
2. 逐字读需求文档 → 填满 RTM
→ 打开 docs/requirements.md 逐条拆解，填入 docs/rtm.md
→ 一条需求缺失 = 禁止往下
3. 实现 → 每条需求写形态断言
→ 按 RTM「代码位置」实现功能
→ 复制 templates/form-assertions.spec.ts 到 e2e/asserts/<feature>.spec.ts，
每条需求写 DOM 断言（P0 阻断）
4. 截图基线 → 视觉 diff
→ node scripts/visual-regression.cjs --snapshot --urls=<页面>
→ node scripts/visual-regression.cjs --baseline 建立基线
5. verify-delivery.cjs → 出报告
→ node scripts/verify-delivery.cjs [--strict]
→ 四重门禁：RTM 完整性 / 形态断言 / 视觉 diff / 报告生成
6. 报告全绿 + 证据截图 → 才允许宣告完成
→ 报告 docs/delivery-report.md 全部 PASS + 视觉基线证据存在
→ 任一 FAIL → 回到步骤 2/3/4 修复 → 重跑步骤 5
四重门禁（任何一道不过 = 系统判定「未完成」）
| 门禁 | 判定 | 考查对象 |
|---|---|---|
| 门禁 1 RTM 完整性 | 表头四列齐备 + 无空要求 + 无空证据 | 「需求有没有逐条翻译」 |
| 门禁 2 形态断言 | e2e/asserts/ 全部断言通过 | 「长什么样有没有做出来」 |
| 门禁 3 视觉 diff | current/ 与 baseline/ 像素差 ≤ 阈值 | 「界面真的变了没有」 |
| 门禁 4 报告生成 | delivery-report.md 全绿 | 「证据链是否完整」 |
每道门都是机器可判定、可一票否决的。考查的不是「我认不认为做完了」，而是「断言过没过、diff 差不差、RTM 有没有空」。
配置驱动（换项目只改配置不改代码）
所有脚本读 delivery.config.json：指定需求文档在哪、断言目录、截图目录、允许的 diff 阈值。换项目只需重新 init 或改 config。
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 97 lines · 81 tokens per session scan A 02df8d0432e5
metago-delivery-gate is a skill published in the GitHub repository metago-ai/metagolifeform (4 stars, last pushed 11d ago), licensed MIT. It adds 81 tokens to every session and 1,549 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
validate
Validate Semantica pipelines, extraction quality, graph schemas, and ontology consistency. Returns structured error/warning checklists. Uses PipelineValidator, PipelineBuilder.validatepipeline(), GraphValidator, and OntologyValidator. Sub-commands: pipeline, step, dependencies, extraction, graph, ontology, performance.
plugin-test
A testing guide for Zhin.js plugins using Vitest, a JavaScript and TypeScript testing framework. It focuses on checking command and tool behavior, ordinary business logic, and the plugin package’s required structure.
workflow-design
A method for designing and testing multi-step computer workflows, including their inputs, actions, conditions, and error handling.
issue-to-pr
Implement one bounded repository issue with normal host tools, prove the tested change through one scafld finalize wall, and optionally publish the exact pull request through scoped provider authority with readback.
deploy-registry-server-with-otel
Deploy the ToolHive Registry Server to a Kind cluster with telemetry enabled. Use when you need to deploy the registry server for testing with OTEL metrics and tracing.
thread-outbox-provider-fetch
Fetch fixture thread readback through the Rust thread-outbox-provider front.