agent-health SKILL.md skillB
agent-health from jimyag/dotfiles is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jimyag/dotfiles/agent-health@git:20261019.0e15234Pins git:20261019.0e15234 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jimyag/dotfiles
- Path
skills/agent-health/SKILL.md- Versions recorded
- 9
- Latest version
- git:20261019.0e15234, committed Oct 19, 2026
- First version recorded
- Sep 5, 2026
- Size
- 12,692 bytes
- Repository stars
- 11
- License
- MIT
在审计 AGENTS/CLAUDE 指令、MCP、hooks、工具权限、验证入口、跨工作流配置漂移，或技能库的规范、可移植性、触发重叠、上下文加载、脚本和评测时使用；不用于创建技能，不因普通任务涉及配置就触发。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 代理配置健康检查 ## 目标 找出代理工作流里会让后续执行变差的配置漂移：规则冲突、技能触发错误、钩子过宽、MCP 权限不清、验证命令失真、持久上下文过期。 ## 何时使用 - 检查 `AGENTS.md`、`CLAUDE.md`、技能、钩子、MCP、代理配置 - 用户觉得 Codex/Claude 没按规则执行 - 新增或迁移一批技能后，需要确认边界是否清楚 - 长期项目里验证命令、生成物规则或上下文文档可能已经过期 如果范围只包含一个或多个 Agent Skills 的规范、打包、描述、脚本和评测，按 [技能库审计](references/skill-library-audit.md) 执行，不展开下面的完整配置审计；技能需要和更广的指令、工具、权限或运行时配置一起审查时，两部分都做。 ## 审计层次 按下面顺序检查，先做概要检查，只有发现高风险或用户要求深入时再扩展： 1. `指令入口`：`AGENTS.md`、`CLAUDE.md`、项目 README、技能头部元数据是否冲突 2. `技能路由`：description/when_to_use 是否过宽、互相抢触发、缺少禁用边界 3. `工具与钩子`：钩子、MCP、允许使用的工具、脚本是否有过宽权限或隐式副作用 4. `验证入口`：测试、静态检查、构建、应用配置、生成物检查是否真实可运行；代理能否从启动、最小变更走到可观察结果 5. `持久上下文`：计划、交接、记忆、文档是否过期、重复或包含私有路径 6. `可维护性`：是否有重复规则、薄技能、无人维护的脚本、公共/私有边界混乱 先确定四类证据，再判断问题；文件大、技能多、TODO 多或缺少文档本身只是信息，只有和下面某一类证据挂钩时才算问题： | 证据 | 问题 | |---|---| | 风险 | 哪些路径会丢数据、花钱、发布或部署、跨越信任边界、留下难以恢复的状态？ | | 不易发现的约束 | 哪些稳定决定无法从代码或 manifest 低成本还原，相关任务能否在需要时读到？ | | 失败证据 | 哪些用户纠正、反复修复、过期生成物、失效引用或空跑的验证证明了当前缺口？ | | 验证覆盖 | 重要结果在它真正会失败的那一层是否有可执行检查？ | 概要检查没有发现具体冲突、失效入口或权限风险时停止，不为了“完整”遍历所有插件、历史文件和敏感目录。进入深度检查时记录触发它的证据和具体范围。 ## 检查规则 - 证据优先：每个问题必须引用具体文件、命令输出或配置项 - 当前仓库状态优先于记忆和旧总结 - 不把缺少“完美治理”当问题；按项目复杂度校准 - 钩子和自动触发规则要重点看副作用、权限范围和是否可关闭 - 静态检查、编译通过或工具返回成功，不自动等于用户可观察行为正确；需要区分源码、测试、集成、运行面和人工证据 …
Read the whole file at its exact version.
How to install
mdr add jimyag/dotfiles/agent-health@sha256:99af9f2d866b3cc9The line at the top of this page pins the label git:20261019.0e15234, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_xkj6sqal3kdpnlhj)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 9 versions of this file, between Sep 5, 2026 and Oct 19, 2026, about one every 6 days. Its first recorded version is graded A and its latest B.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261019.0e15234 latest | 2026-10-19 | 0e15234 | 12,692 B | B | view · diff |
| git:20261015.f79eac0 | 2026-10-15 | f79eac0 | 12,468 B | B | view · diff |
| git:20261015.b377f6b | 2026-10-15 | b377f6b | 10,169 B | B | view · diff |
| git:20261015.2c8093f | 2026-10-15 | 2c8093f | 4,770 B | A | view · diff |
| git:20260920.81a3f42 | 2026-09-20 | 81a3f42 | 3,994 B | A | view · diff |
| git:20260920.878daed | 2026-09-20 | 878daed | 3,419 B | A | view · diff |
| git:20260919.7add278 | 2026-09-19 | 7add278 | 3,362 B | A | view · diff |
| git:20260919.361331b | 2026-09-19 | 361331b | 2,666 B | A | view · diff |
| git:20260905.751659e | 2026-09-05 | 751659e | 2,300 B | A | view |
Audit of the latest version
- fail: No curl or wget piped into a shell (matched: curl ... | sh)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (12692 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 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
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
jimyag/dotfiles · 11 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xkj6sqal3kdpnlhj GET https://markdownregistry.com/api/v1/resolve?ref=jimyag/dotfiles/agent-health GET https://markdownregistry.com/api/v1/blob/99af9f2d866b3cc994c34a0339c7da787d899b5f051a39db967bbd606fdbb33c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.