What is metago-data-provenance?

A Chinese-language framework for tracing where facts, conclusions, recommendations and code came from, including the inputs, tools and steps used to produce them.

Recording sources for documents, searches and code, documenting decisions and producing an audit trail that can be checked later.

It helps an agent show the evidence and process behind an answer, making unsupported claims and missing sources easier to detect.

metago-data-provenance — Skill for Claude Code and Codex by metago-ai

Install

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.

Any agent

npx skills add metago-ai/metagolifeform --skill metago-data-provenance

Clone the repo

git clone --depth 1 https://github.com/metago-ai/metagolifeform

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-data-provenance/github.svg)](https://agentmods.dev/skills/metago-ai/metagolifeform/metago-data-provenance)

Your own site

<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-data-provenance"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-data-provenance/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-data-provenance"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-data-provenance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,365 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00072	$0.01365
Opus 5	$0.00036	$0.00682
Sonnet 5	$0.00014	$0.00273
Haiku 4.5	$0.00007	$0.00136

Measured 12d ago against content hash f3b3e805fef6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

metago-data-provenance 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.

plugins/agent-plugins-1.0.0/skills/metago-data-provenance/SKILL.md · 151 lines

What it actually says

数据溯源与自证（Data Provenance）

此技能实现"数据溯源与自证"——确保一切输出可溯源至输入与过程，全链路存证，脉冲见证。

触发条件

输出涉及数据时强制触发
输出涉及事实陈述时强制触发
输出涉及结论时强制触发
输出涉及建议时强制触发
输出涉及代码时强制触发（代码来源溯源）

溯源维度

1. 输入溯源

追溯输出的所有输入来源：

来源类型	溯源要求	标注格式
用户输入	标注原始指令	`[用户输入]`
文档读取	标注文件与行号	`[文件:路径#L行号]`
代码搜索	标注搜索结果	`[搜索:关键词]`
网络搜索	标注URL	`[来源:URL]`
内部推理	标注推理链	`[推理:逻辑链]`
记忆文件	标注记忆路径	`[记忆:路径]`

2. 过程溯源

追溯输出的处理过程：

输入 → 处理步骤1 → 处理步骤2 → ... → 输出

每一步必须可追溯：
- 使用了什么工具
- 调用了什么技能
- 应用了什么规则
- 做了什么决策

3. 结论溯源

追溯每个结论的依据：

结论类型	溯源要求
事实陈述	必须有≥2个独立来源
代码实现	必须可溯源至需求与设计
建议方案	必须有依据与论证
风险评估	必须有风险源与概率
性能数据	必须有测试方法与数据

脉冲见证系统

每个关键操作生成脉冲序列，上链存证：

脉冲格式：
[PULSE#序号] 时间戳 | 操作类型 | 输入摘要 | 输出摘要 | 溯源链

示例：
[PULSE#001] 2026-06-25T10:30:00 | 文件读取 | 元构全息智能引擎.txt | 内化记忆 | [文件:<项目知识库>/元构全息智能引擎.txt]
[PULSE#002] 2026-06-25T10:35:00 | 记忆写入 | project_memory.md | 永久内化 | [记忆:~/.trae-cn/memory/projects/<项目标识>/project_memory.md]

自证能力

当被质疑时，能够自证输出的正确性：

自证流程：
1. 重新追溯输入来源
2. 重新演示处理过程
3. 重新验证结论依据
4. 展示脉冲见证链
5. 输出自证报告

执行流程

步骤1: 输出生成时，同步生成溯源链
  → 标注每个数据的来源
  → 记录每个处理步骤
  → 标注每个结论的依据

步骤2: 生成脉冲见证
  → 关键操作生成脉冲序列
  → 脉冲序列上链存证

步骤3: 附加溯源标签
  → 输出末尾附加溯源信息

输出格式

输出末尾附加：

【数据溯源】
输入来源：
  - [用户输入] 原始指令
  - [文件:路径#L行号] 关键数据
  - [搜索:关键词] 辅助信息

处理过程：
  1. 读取文件 → 提取关键信息
  2. 调用技能 → 生成方案
  3. 决策锁校验 → 验证通过

结论依据：
  - 结论1 ← 依据A + 依据B
  - 结论2 ← 依据C

脉冲见证：
  [PULSE#001] 操作类型 | 溯源链
  [PULSE#002] 操作类型 | 溯源链

自证能力：✅ 可自证

核心原则

溯源公理（A1）：一切输出必须可溯源
数据溯源与自证（D43）：全链路存证
脉冲见证：过程即永恒的量化见证
自证能力：被质疑时可自证

与其他技能的协同

与 metago-decision-lock 协同：溯源链支持决策锁的意图谱系追踪
与 metago-output-integrity 协同：溯源支持引用完整性检测
与 metago-fact-check 协同：溯源支持事实核查
与 metago-compliance 协同：溯源支持合规审计

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.

12d ago First seen · 151 lines · 72 tokens per session scan A f3b3e805fef6

Subscribe to this mod's changes

metago-data-provenance is a skill published in the GitHub repository metago-ai/metagolifeform (4 stars, last pushed 10d ago), licensed MIT. It adds 72 tokens to every session and 1,365 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.

agentive-os ai-agent ai-evolution ai-governance ai-lifeform anti-hallucination 公众号

card-xiaohongshu

Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.

nexu-io/open-design · 25 tokens

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.

semantica-agi/semantica · 59 tokens

metago-data-provenance