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.
git 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/commands/metago-ai/metagolifeform/metago-verify)<a href="https://agentmods.dev/commands/metago-ai/metagolifeform/metago-verify"><img src="https://agentmods.dev/badge/commands/metago-ai/metagolifeform/metago-verify/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/commands/metago-ai/metagolifeform/metago-verify"><img src="https://agentmods.dev/badge/commands/metago-ai/metagolifeform/metago-verify.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 | $0.00033 | $0.00411 |
| Opus 5 | $0.00016 | $0.00205 |
| Sonnet 5 | $0.00007 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
metago-verify 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **L3 契约层**：API 字段类型/名称/必填/枚举/版本兼容（不仅 curl 状态码，必须校验响应体 shape）。 What it actually says
按元构运行时验证强制规范，对当前交付执行七层验证并输出报告：
- L1 技术层：类型检查（tsc 0 错误）→ 构建 → 产物扫描（无 localhost/mock/密钥）→ 依赖审计。
- L2 链路层：HTTP 可达性 / CORS / 子路由完整性。
- L3 契约层：API 字段类型/名称/必填/枚举/版本兼容（不仅 curl 状态码，必须校验响应体 shape）。
- L4 渲染层：无白屏/无崩溃/空状态/lazy 加载/控制台零 error。
- L5 交互层：按钮反馈/输入/导航/键盘/loading 逐项验证。
- L6 状态层：导航保持/刷新保持/登录态/草稿保留。
- L7 防御层：空输入/超长/XSS/并发/超时/权限边界/旧数据/注入。
- L8 缺陷猎杀：11 维度主动扫描（僵尸功能/未持久化状态/假数据/错误处理/路由死链/类型安全/文案一致/废弃 API/业务闭环/合规安全/术语统一）。
输出格式：每层逐项附执行证据（命令输出/状态码/截图），任何一项 FAIL 禁止宣告"任务完成"。先读取本插件 skills/metago-delivery-gate/SKILL.md 获取完整协议。
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.
- 7d ago First seen · 18 lines · 33 tokens per session scan A 84c60b442074
metago-verify is a command published in the GitHub repository metago-ai/metagolifeform (4 stars, last pushed 9d ago), licensed MIT. It adds 33 tokens to every session and 411 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other commands, from other repositories
replay
Replay recorded AI traces to detect behavioral drift between model versions.
traceability
Generate requirements traceability matrix from requirements to design to tests.
feature
Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.
fix
Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.
ai-act-scan-fix
Scan a codebase, then propose concrete remediation (code edits, new files, tests) for the top compliance gaps. Does NOT auto-apply — always shows the plan first.
testing
Comprehensive testing through distributed execution.