ooooooooooooooooooop/personal-ai · skills/subagent-execution-governance/SKILL.md

subagent-execution-governance skillA

subagent-execution-governance is agent-read markdown (skill) from ooooooooooooooooooop/personal-ai: 把子代理派发从"监督型治理"升级为"契约型治理"：探查/实现/验证角色分离、契约快照（含负空间）、三级有界读取、单写者文件所有权、行动门槛替代轮次门槛、结构化 BLOCKED、token/工具/轮次预算、结构化结果回收与 repair-contract 恢复。用于派发实现型子代理（写代码/写文件类任务）、设计"谁读什么/谁写什么/何时算阻塞"的执行协议、审计子代理空转（反复探查不产出、并行写冲突、上下文膨胀）、或复盘"子代理烧了大量 token 却没产出"的会话。不用于纯问答、单轮小修改、或已有成熟任务流程的普通委派。.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add ooooooooooooooooooop/personal-ai/subagent-execution-governance@v0.2.0
Exact content
mdr add ooooooooooooooooooop/personal-ai/subagent-execution-governance@sha256:db3ba9c54c446be2

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7rqkyeqgre3vasfw.svg)](https://markdownregistry.com/a/art_7rqkyeqgre3vasfw)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v0.2.0 latest2026-09-01 b19d0f5 19,915 BA view · diff
v0.2.02026-08-28 1542fea 17,309 BA view · diff
v0.1.02026-08-25 b9e9eac 15,856 BA view · diff
v0.1.02026-08-23 b75d679 14,851 BA view · diff
v0.1.02026-08-23 063ac80 14,852 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (19915 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

ooooooooooooooooooop/personal-ai · 3 stars · license MIT · pushed 2026-09-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7rqkyeqgre3vasfw
GET https://markdownregistry.com/api/v1/resolve?ref=ooooooooooooooooooop/personal-ai/subagent-execution-governance
GET https://markdownregistry.com/api/v1/blob/db3ba9c54c446be2985d64654bc5f388aaddac48e2734f6ccc4e9b8296735bf9

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.