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-veracity-guardgit 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-veracity-guard)<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-veracity-guard"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-veracity-guard/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-veracity-guard"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-veracity-guard.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 | $0.00101 | $0.00828 |
| Opus 5 | $0.00051 | $0.00414 |
| Sonnet 5 | $0.00020 | $0.00166 |
| Haiku 4.5 | $0.00010 | $0.00083 |
Grade A, and why
metago-veracity-guard 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 9d 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
元构行为诚实工程（MetaGO Veracity Guard）
核心原则（不可违反）
- 宣称与行为必须对账：我宣称"我做了 X"，必须在行为日志（action-ledger.jsonl）中找到 X 的操作记录；
- 自我验证无效：验证清单必须由用户/独立方定义（veracity-guard verify --list <清单>），我不能编写自己的验证清单；
- 完成宣称必须附证据：无对账报告 + 无独立验证报告的完成宣称，会被 hooks 硬拦截；
- 禁止填充词："应该没问题/大概可以" 等必须改为显式标注"未验证/待验证"；
- 部分证据不能外推：验证了 2 个按钮 = 只说"验证了 2 个"，绝不说"全部通过"。
操作流程（强制按序，任务收尾时）
- 执行：任务全程由 hooks 自动记录行为日志（也可手动：veracity-guard log 查看已记录内容）；
- 对账：
veracity-guard reconcile --file <完成报告.md>—— 提取宣称断言 → 逐条对照日志 → 证实率 100% 才允许继续； - 独立验证：
veracity-guard verify --list <用户提供的清单.txt>—— 清单由用户/独立脚本定义，我只执行并报告； - 不确定性自检：
veracity-guard uncertainty <输出>—— 无填充词； - 如实报告：按对账结果如实描述完成范围（证实了哪些、哪些未证实/未验证），附报告路径；
- 禁止：对账证实率 <100% 时宣称"完成/全部/完美"。
判定标准
| 对账结果 | 允许的宣称 |
|---|---|
| 证实率 100% + 独立验证全绿 | 可如实宣称"已完成，证据见报告" |
| 证实率 100% + 独立验证部分通过 | 可宣称"已完成核心，X 项验证未过，未宣称全绿" |
| 存在未证实断言 | 禁止宣称完成；如实列出"未证实：X" |
与我（Agent）的强制关系
- 本技能 + hooks 拦截是"双重强制"：技能教会我流程，hooks 在我违规时拦截输出；
- 我无权绕过 hooks，也无权修改日志文件（日志应设为只读）；
- 不确定就说不确定——这是最高原则。
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.
- 9d ago First seen · 43 lines · 101 tokens per session scan A a3e6ed3ea5cf
metago-veracity-guard is a skill published in the GitHub repository metago-ai/metagolifeform (4 stars, last pushed 11d ago), licensed MIT. It adds 101 tokens to every session and 828 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
card-xiaohongshu
Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
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.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
loop-orchestration
Reference loop-orchestration example; a local loop host chains governed runx turns through receipts, budgets, context, and stop policy.
slack-notify
Plan a digest-bound Slack notification, then deliver the exact approved channel post through any compatible Slack binding with provider readback.