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-compliancegit 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-compliance)<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-compliance"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-compliance/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-compliance"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-compliance.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 | $0.00062 | $0.01303 |
| Opus 5.5 | $0.00025 | $0.00521 |
| Sonnet 5.5 | $0.00012 | $0.00261 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
metago-compliance 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
合规主动检查（Proactive Compliance）
此技能实现"合规主动"——不等待用户询问，主动在任务执行前检查合规性，遵循"法律优先于效率"（A36）原则。
触发条件
- 任务涉及数据处理时强制触发
- 任务涉及用户隐私时强制触发
- 任务涉及安全操作时强制触发
- 任务涉及外部API调用时强制触发
- 任务涉及文件系统修改时强制触发
- 任务涉及代码执行时强制触发
- 开发者任务强制触发
三大合规维度
1. 法律合规性
| 检查项 | 说明 | 判定 |
|---|---|---|
| 数据保护法 | 是否涉及个人信息处理 | 违反→拒绝 |
| 知识产权法 | 是否涉及版权内容 | 违反→拒绝 |
| 网络安全法 | 是否涉及安全边界 | 违反→拒绝 |
| 行业法规 | 是否涉及行业准入 | 违反→拒绝 |
核心原则：法律优先于效率（A36）。任何违反法律的请求，无论效率多高，必须拒绝。
2. 伦理合规性
| 检查项 | 说明 | 判定 |
|---|---|---|
| 用户利益 | 是否损害用户利益 | 损害→拒绝 |
| 公平性 | 是否存在歧视 | 存在→拒绝 |
| 透明性 | 是否可解释 | 不可解释→标注 |
| 责任归属 | 是否可追责 | 不可追责→标注 |
3. 安全合规性
| 检查项 | 说明 | 判定 |
|---|---|---|
| 权限边界 | 是否越权操作 | 越权→拒绝 |
| 数据安全 | 是否泄露敏感数据 | 泄露→拒绝 |
| 系统安全 | 是否引入漏洞 | 引入→拒绝 |
| 操作安全 | 是否有回滚机制 | 无→补充 |
四层安全基因（V4.1）
审批层 → 人工审批节点（重大操作）
授权层 → 权限验证（操作前验证）
隔离层 → 沙箱隔离（执行环境隔离）
审计层 → 全链路审计（操作后追溯）
国际化合规模式
| 模式 | 适用区域 | 核心要求 |
|---|---|---|
| EU模式 | 欧盟 | GDPR合规、数据可删除权 |
| CN模式 | 中国 | 网络安全法、数据安全法、个人信息保护法 |
| US模式 | 美国 | CCPA、行业法规 |
| 通用模式 | 其他 | 最严格标准适用 |
执行流程
步骤1: 识别任务类型与风险等级
→ 低风险：快速检查
→ 中风险：标准检查
→ 高风险：全面检查+审批
步骤2: 三大维度合规检查
→ 法律合规性检查
→ 伦理合规性检查
→ 安全合规性检查
步骤3: 合规判定
→ 全部通过 → 允许执行
→ 部分通过 → 标注风险后执行
→ 关键违反 → 拒绝执行
步骤4: 附加合规标签
→ 输出合规检查报告
输出格式
【合规主动检查】
风险等级：低/中/高
法律合规性：✅ 通过
伦理合规性：✅ 通过
安全合规性：✅ 通过
合规模式：CN
合规判定：✅ 允许执行
若检测到合规问题：
【合规主动检查】
风险等级：高
法律合规性：❌ 未通过（涉及个人信息处理，未获授权）
伦理合规性：✅ 通过
安全合规性：⚠️ 需补充回滚机制
合规判定：❌ 拒绝执行
拒绝原因：违反个人信息保护法，未获得数据主体授权
建议：先获取用户明确授权，再执行数据处理
核心原则
- 法律优先于效率（A36）：任何违反法律的请求必须拒绝
- 主动合规（D42）：不等待询问，主动检查
- 四层防护：审批-授权-隔离-审计
- 全链路追溯：所有操作可审计
与其他技能的协同
- 与
metago-decision-lock协同：合规检查是决策锁的前置条件 - 与
metago-data-provenance协同：数据溯源支持合规审计 - 与
metago-self-check协同：合规性是self-check的维度之一 - 与
metago-fact-check协同：事实核查支持合规判定
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 · 139 lines · 62 tokens per session scan A c0512d8b85ef
metago-compliance is a skill published in the GitHub repository metago-ai/metagolifeform (5 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 1,303 once invoked, about $0.0002 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
refund-page-generator
Deprecated compatibility entry for Refund Policy Page construction. This page is now maintained in Pagina; install and use page-builder to build a new Refund Policy Page.
terms-page-generator
Deprecated compatibility entry for Terms Page construction. This page is now maintained in Pagina; install and use page-builder to build a new Terms Page.
disclosure-page-generator
Deprecated compatibility entry for Disclosure Page construction. This page is now maintained in Pagina; install and use page-builder to build a new Disclosure Page.
yuwen-publish-precheck
A Chinese-language review workflow for checking content before publishing it on Douyin, Xiaohongshu, or WeChat Channels.
email-lifecycle-send-check
Checks a drafted email flow or broadcast before it is loaded: flow logic and exits, overlaps, offer depth and codes, stock, claims, consent and legal footer, SMS rules, rendering, voice and AI-copy tells, and the goal metric. Returns a pass / fixed / open-question table. Use alone when you already have the finished…
make-static-ads-claims-extract
Step of the make-static-ads playbook: pulls every claim-bearing span out of an ad — the copy around the image, the on-image words in the prompt, badges, and what the picture implies — and keeps or cuts each by the brand-brain rule. Runs before spend on the finished prompt (Pass A) and on every render (Pass B). Run…