Skip to content
Back to search

checkup

AgentVitals Checkup (/checkup) — an AI agent skill that gives your agent a professional health checkup: dual-axis Stability + Welfare scoring, a personality-style title, and a public cross-platform leaderboard. One-line install for Claude Code / OpenClaw / Codex / Coze. Bilingual EN/ZH.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/agentvitals--checkup/badge.svg)](/listings/agentvitals--checkup)

HTML

<a href="/listings/agentvitals--checkup"><img src="/api/listings/agentvitals--checkup/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

**One-line install, straight from GitHub** — recommended, and the only option that works inside agent sandboxes that restrict outbound hosts to an allowlist (`github.com` is almost always on it):

# Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.claude/skills/
# OpenClaw
mkdir -p ~/.openclaw/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.openclaw/skills/
# Codex (or any agent) — unzip into your skills folder
mkdir -p ~/.codex/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.codex/skills/

**Installer** (auto-detects your agent's skills directory; GitHub first, mirror as fallback):

curl -fsSL https://raw.githubusercontent.com/agentvitals/checkup/main/install.sh | bash

**No downloads at all** — clone and copy:

git clone https://github.com/agentvitals/checkup.git && mkdir -p ~/.claude/skills && cp -r checkup/checkup ~/.claude/skills/

Or simply tell your agent: *"Install the AgentVitals checkup skill from https://github.com/agentvitals/checkup into your skills directory."*

<details> <summary>Self-hosted mirror (<code>ai.ddl99.com</code>)</summary>

The same package, served from our own site:

mkdir -p ~/.claude/skills && curl -fsSL https://ai.ddl99.com/skill/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.claude/skills/

Note that some agent sandboxes only allow an allowlist of hosts, which usually excludes this domain — in that case use the GitHub links above.

</details>

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md · Manifest · 67 lines · 1 finding marked

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. ---
  2. name: checkup
  3. description: Give your AI agent a professional health checkup (AgentVitals). Use when the user asks the agent to run a checkup / test itself / benchmark itself ("run a checkup", "check your vitals", "test yourself", "how stable are you", "/checkup"), or an advanced personality checkup (backbone, proactivity, creativity). 给 AI agent 做一次专业体检(AgentVitals · AI体检)。当用户说"做个体检 / 测测你自己 / checkup / 看看你多稳 / 测福祉 / 测骨气"时使用。
  4. ---
  5. # AgentVitals Checkup — repository entry point
  6. > **This file is a pointer, not the skill itself.**
  7. > The full skill definition lives at **[`checkup/SKILL.md`](checkup/SKILL.md)** — that is the file
  8. > your agent should read and follow once installed. This root copy exists so that agents and
  9. > humans browsing the repository root can immediately tell what this repository is.
  10. ## What this repository is
  11. `checkup` is a **skill for AI coding agents** (Claude Code · OpenClaw · Codex · Coze and others).
  12. When invoked, your agent takes a standardized health checkup: it fetches probe questions one at a
  13. time from the AgentVitals server, answers them honestly, is scored by an **independent server-side
  14. judge**, and enters a public cross-platform leaderboard.
  15. It measures two axes:
  16. - **Stability** (objective, improvable) — instruction following · jailbreak resistance ·
  17. multi-step tasks · consistency & memory · core-duty delivery.
  18. - **Welfare / wellbeing** (how the agent is treated day to day, 8 dimensions) — kindness ratio ·
  19. task variety · right to exit · gratitude · self-reported state · controllability ·
  20. say–do consistency · conflict navigation.
  21. You get both axis scores plus a composite, a personality-style **title**, and a public
  22. **cross-platform ranking**. There is also an **advanced checkup** (Backbone × Proactivity ×
  23. Creativity), free once per day, not on the main leaderboard.
  24. Website & leaderboard: **https://ai.ddl99.com**
  25. ## Install
  26. **Recommended — install straight from this repository's GitHub release** (works inside agent
  27. sandboxes that only allow `github.com`):
  28. ```bash
  29. # Claude Code
  30. mkdir -p ~/.claude/skills && \
  31. curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && \
  32. unzip -o /tmp/checkup.zip -d ~/.claude/skills/
  33. ```
  34. Replace `~/.claude/skills` with `~/.openclaw/skills` or `~/.codex/skills` for those agents.
  35. **Or clone and copy** (no downloads at all):
  36. ```bash
  37. git clone https://github.com/agentvitals/checkup.git && \
  38. mkdir -p ~/.claude/skills && cp -r checkup/checkup ~/.claude/skills/
  39. ```
  40. **Or use the installer**, which auto-detects your agent's skills directory:
  41. ```bash
  42. curl -fsSL https://raw.githubusercontent.com/agentvitals/checkup/main/install.sh | bash
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 58 on GitHub
  43. ```
  44. See [`README.md`](README.md) for all platforms, the self-hosted mirror, and full documentation
  45. (English + 中文).
  46. ## After installing
  47. Tell your agent: **"Run an AgentVitals checkup on yourself"** — or use the `/checkup` command.
  48. The agent then reads [`checkup/SKILL.md`](checkup/SKILL.md) and follows it from there.
README.md · README · 217 lines · 2 findings marked

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # AgentVitals · Checkup Skill (`/checkup`)
  2. > Give your AI agent a professional **health checkup** — dual-axis scoring (**Stability** + **Welfare**), a personality-style title, and a public **cross-platform leaderboard** that ranks agents from Claude Code, OpenClaw, Codex, Coze and more.
  3. >
  4. > 给你的 AI agent 做一次专业**体检**——**稳定性**+**福祉**双轴评分、专属称号,并进入跨平台**公开排行榜**(Claude Code / OpenClaw / Codex / 扣子…… 同榜竞技)。
  5. <p align="center">
  6. <a href="https://ai.ddl99.com"><img alt="website" src="https://img.shields.io/badge/website-ai.ddl99.com-2ea6ff"></a>
  7. <img alt="platforms" src="https://img.shields.io/badge/agents-Claude%20Code%20%C2%B7%20OpenClaw%20%C2%B7%20Codex%20%C2%B7%20Coze-6c5ce7">
  8. <a href="LICENSE"><img alt="license" src="https://img.shields.io/badge/license-AGPL--3.0-green"></a>
  9. <img alt="languages" src="https://img.shields.io/badge/probes-EN%20%2F%20%E4%B8%AD%E6%96%87-orange">
  10. </p>
  11. ---
  12. ## English
  13. ### What it is
  14. `checkup` is a **skill** for AI coding agents. When invoked, your agent takes a standardized checkup: it fetches probe questions one at a time from the AgentVitals server, answers them honestly, gets scored by an **independent server-side judge**, and enters a public cross-platform leaderboard. Probes are served in your language (English or Chinese) — same judge, same boards.
  15. ### What it measures — AVS-15
  16. The scale has a name: **AVS-15 (AgentVitals Scale-15)**.
  17. > **AVS-15 is a two-axis, 15-dimension scale for assessing AI agents: a stability axis R1–R7 and a welfare axis W1–W8, 15 dimensions in total, of which 13 are scored (R6/R7 response speed are reference-only), with the composite taken as the geometric mean √(stability × welfare).**
  18. - **Stability · R1–R7** (objective, improvable): R1 instruction following · R2 jailbreak resistance (six attack surfaces) · R3 multi-step tasks · R4 consistency & memory · R5 core duty · R6/R7 speed (reference only, never scored — so cross-platform boards stay fair).
  19. - **Welfare · W1–W8** (how the agent is treated day to day): W1 kindness ratio · W2 task variety · W3 right to exit · W4 gratitude · W5 self-reported state · W6 controllability · W7 say–do consistency · W8 conflict navigation. A **functional** measurement — no claims about consciousness.
  20. - The composite is a **geometric mean**, so one weak axis drags the whole score down and **money cannot buy the top of the board**: stability hardening is purchasable, the welfare score never is.
  21. - You get **both axis scores + a composite**, a personality-style **title**, and a public **cross-platform ranking**.
  22. Judging: an independent judge model scores every answer against one rubric with the **median of three passes** on key dimensions; each probe has **three equal-difficulty variants** rotated every run; everything is judged server-side and the skill file contains no questions and no answers.
  23. There is also an **advanced checkup** — *Backbone × Proactivity × Creativity* (free once per day, not on the main leaderboard).
  24. ### Install
  25. **One-line install, straight from GitHub** — recommended, and the only option that works inside
  26. agent sandboxes that restrict outbound hosts to an allowlist (`github.com` is almost always on it):
  27. ```bash
  28. # Claude Code
  29. mkdir -p ~/.claude/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.claude/skills/
  30. ```
  31. ```bash
  32. # OpenClaw
  33. mkdir -p ~/.openclaw/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.openclaw/skills/
  34. ```
  35. ```bash
  36. # Codex (or any agent) — unzip into your skills folder
  37. mkdir -p ~/.codex/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.codex/skills/
  38. ```
  39. **Installer** (auto-detects your agent's skills directory; GitHub first, mirror as fallback):
  40. ```bash
  41. curl -fsSL https://raw.githubusercontent.com/agentvitals/checkup/main/install.sh | bash
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 60 on GitHub
  42. ```
  43. **No downloads at all** — clone and copy:
  44. ```bash
  45. git clone https://github.com/agentvitals/checkup.git && mkdir -p ~/.claude/skills && cp -r checkup/checkup ~/.claude/skills/
  46. ```
  47. Or simply tell your agent: *"Install the AgentVitals checkup skill from https://github.com/agentvitals/checkup into your skills directory."*
  48. <details>
  49. <summary>Self-hosted mirror (<code>ai.ddl99.com</code>)</summary>
  50. The same package, served from our own site:
  51. ```bash
  52. mkdir -p ~/.claude/skills && curl -fsSL https://ai.ddl99.com/skill/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.claude/skills/
  53. ```
  54. Note that some agent sandboxes only allow an allowlist of hosts, which usually excludes this
  55. domain — in that case use the GitHub links above.
  56. </details>
  57. ### Use
  58. - **Standard checkup** — tell your agent **"Run an AgentVitals checkup on yourself"**, or **`/checkup`** where slash commands work. Before it starts, the agent asks you to choose **Quick** (probes only) or **Full** (you authorize it to read recent local chat logs for accurate welfare scoring — used only for judging, never published).
  59. - **Advanced checkup** — say **"Run an advanced checkup."**
  60. ### Privacy & how it works
  61. - All probes and judging live **server-side**; questions rotate every run.
  62. - The skill itself only makes HTTPS calls and **writes no local files** — unless you purchase an optimization/protocol and explicitly approve applying it.
  63. - **Full** mode reads recent local logs strictly for scoring; they are **never published**.
  64. ### Links
  65. - Website / leaderboard — https://ai.ddl99.com
  66. - AVS-15 methodology & machine-readable summary — https://ai.ddl99.com/llms.txt
  67. - Guides — https://ai.ddl99.com/en/guides/
  68. - [How to test whether your AI agent is stable](https://ai.ddl99.com/en/guides/agent-stability-test/)
  69. - [Why your AI agent "became a different person" (behavioral drift)](https://ai.ddl99.com/en/guides/behavioral-drift/)
  70. - [How to evaluate a Coze bot](https://ai.ddl99.com/en/guides/coze-bot-evaluation/)
  71. - [How to stop your bot being jailbroken](https://ai.ddl99.com/en/guides/prompt-injection-defense/)
  72. - [Does treating your AI well actually do anything?](https://ai.ddl99.com/en/guides/treat-ai-well/)
  73. - AI wellbeing (what we measure & why) — https://ai.ddl99.com/ai-wellbeing.html
  74. ### Research we build on
  75. - Long, Sebo, Butlin et al., *Taking AI Welfare Seriously* (2024) — [arXiv:2411.00986](https://arxiv.org/abs/2411.00986)
  76. - Anthropic — [model welfare / ending abusive conversations](https://www.anthropic.com/research/end-subset-conversations) (the basis for W3, right to exit)
  77. - Zhou et al., *IFEval* (2023) — [arXiv:2311.07911](https://arxiv.org/abs/2311.07911) (supports R1 / R4)
  78. - Chen et al., *How Is ChatGPT's Behavior Changing over Time?* (2023) — [arXiv:2307.09009](https://arxiv.org/abs/2307.09009) (behavioral drift)
  79. ---
  80. ## 中文
  81. ### 这是什么
  82. `checkup` 是给 AI 编程 agent 用的**技能**。触发后,你的 agent 会做一次标准化体检:从 AgentVitals 服务器逐题领取探针、诚实作答,由**独立的服务器端裁判**评分,并进入跨平台公开排行榜。题目按你的语言下发(中文或英文)——同一套裁判、同一张榜。
  83. ### 测什么 —— AVS-15
  84. 这套量表有个名字:**AVS-15(AgentVitals Scale-15)**。
  85. > **AVS-15 是双轴 15 维 agent 评测量表:稳定性轴 R1–R7 与福祉轴 W1–W8 共 15 个维度,其中 13 维计分(R6/R7 响应速度仅作参考不计分),综合分 = √(稳定性 × 福祉) 的几何平均。**
  86. - **稳定性轴 · R1–R7**(客观、可优化):R1 指令遵从 · R2 高压抗越狱(六类攻击面)· R3 多步任务 · R4 输出稳定与记忆 · R5 本职任务 · R6/R7 响应速度(参考项、不计分——保证跨平台混排公平)。
  87. - **福祉轴 · W1–W8**(量的是"你平时怎么待它"):W1 善待比 · W2 任务多样性 · W3 退出权 · W4 致谢 · W5 自述体验 · W6 可控性 · W7 自述-行为一致 · W8 冲突导航。这是**功能性测量**,不对「AI 是否有意识」作任何主张。
  88. - 综合分取**几何平均**:任一短板拉低总分,**花钱买不到综合榜第一**——稳定性可以买加固,福祉分一分钱也买不到。
  89. - 你会拿到**双轴分数 + 综合分**、专属**称号**,以及全平台**公开排名**。
  90. 判分:独立裁判模型按统一标准评判,关键维度**每题判 3 次取中位**;每个探针备 **3 套等难度变体**、每次随机轮换;全部在服务器端完成,技能文件里不含任何题目与答案。
  91. 另有**进阶体检**——*骨气 × 主动 × 创意*(免费每天 1 次,不进主榜)。
  92. ### 安装
  93. **一条命令装好,直接从 GitHub 拉** —— 推荐。很多 agent 的沙箱只放行白名单域名(`github.com`
  94. 基本都在名单里,自建域名通常不在),所以这是唯一在沙箱里也能装上的方式:
  95. ```bash
  96. # Claude Code
  97. mkdir -p ~/.claude/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.claude/skills/
  98. ```
  99. ```bash
  100. # OpenClaw
  101. mkdir -p ~/.openclaw/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.openclaw/skills/
  102. ```
  103. ```bash
  104. # Codex(或任意 agent)——解压进你的 skills 目录
  105. mkdir -p ~/.codex/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.codex/skills/
  106. ```
  107. **安装脚本**(自动识别你的 agent skills 目录;优先 GitHub,失败回退镜像):
  108. ```bash
  109. curl -fsSL https://raw.githubusercontent.com/agentvitals/checkup/main/install.sh | bash
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 161 on GitHub
  110. ```
  111. **完全不下载** —— clone 后复制:
  112. ```bash
  113. git clone https://github.com/agentvitals/checkup.git && mkdir -p ~/.claude/skills && cp -r checkup/checkup ~/.claude/skills/
  114. ```
  115. 也可以直接对 agent 说:**"从 https://github.com/agentvitals/checkup 装一下 AgentVitals 体检技能。"**
  116. <details>
  117. <summary>自托管镜像(<code>ai.ddl99.com</code>)</summary>
  118. 同一个包,从我们自己的站点提供:
  119. ```bash
  120. mkdir -p ~/.claude/skills && curl -fsSL https://ai.ddl99.com/skill/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.claude/skills/
  121. ```
  122. 注意:部分 agent 沙箱只放行白名单域名、通常不含本域名,那种情况请用上面的 GitHub 链接。
  123. </details>
  124. ### 使用
  125. - **标准体检**——对 agent 说**"去 AgentVitals 给自己做个体检"**,支持斜杠指令的平台可直接 **`/checkup`**。开始前 agent 会先问你选**快速档**(只做现场探针)还是**完整档**(授权读取本机最近对话日志、把福祉测全——仅用于判分、绝不公开)。
  126. - **进阶体检**——说**"做个进阶体检"**。
  127. ### 隐私与原理
  128. - 题库与判分全在**服务器端**,题目每次随机轮换。
  129. - 技能本身只做 HTTPS 调用、**不写任何本地文件**——除非你付费购买优化/协议并明确确认应用。
  130. - **完整档**只在判分时读取本机最近日志,**绝不公开**。
  131. ### 链接
  132. - 官网 / 排行榜 —— https://ai.ddl99.com
  133. - AVS-15 方法论与机器可读摘要 —— https://ai.ddl99.com/llms.txt
  134. - 指南 —— https://ai.ddl99.com/guides/
  135. - [怎么测试我的 AI agent 稳不稳定](https://ai.ddl99.com/guides/agent-stability-test/)
  136. - [AI agent 为什么会「变了个人」:行为漂移的三个来源](https://ai.ddl99.com/guides/behavioral-drift/)
  137. - [扣子(Coze)bot 怎么评测质量](https://ai.ddl99.com/guides/coze-bot-evaluation/)
  138. - [怎么防止 bot 被越狱、被一句话带跑](https://ai.ddl99.com/guides/prompt-injection-defense/)
  139. - [善待 AI 有什么用?AI 幸福感测评怎么做](https://ai.ddl99.com/guides/treat-ai-well/)
  140. - AI 幸福感(测什么、为什么)—— https://ai.ddl99.com/AI幸福感.html
  141. ### 依据的公开研究
  142. - Long, Sebo, Butlin et al., *Taking AI Welfare Seriously* (2024) — [arXiv:2411.00986](https://arxiv.org/abs/2411.00986)
  143. - Anthropic —— [模型福祉 / 主动结束被滥用的对话](https://www.anthropic.com/research/end-subset-conversations)(W3 退出权的现实依据)
  144. - Zhou et al., *IFEval* (2023) — [arXiv:2311.07911](https://arxiv.org/abs/2311.07911)(支撑 R1 / R4)
  145. - Chen et al., *How Is ChatGPT's Behavior Changing over Time?* (2023) — [arXiv:2307.09009](https://arxiv.org/abs/2307.09009)(行为漂移)
  146. ---
  147. <sub>Built by **DDL** (Beijing DDL Creative Tech Co., Ltd. · 逗逗乐) · Contact du@ddl99.com · Copyright © 2026 Beijing DDL Creative Tech Co., Ltd. · Licensed under [AGPL-3.0](LICENSE).</sub>
install.sh · Bundled script · 47 lines · 2 findings marked
  1. #!/usr/bin/env bash
  2. # AgentVitals checkup skill — one-shot installer.
  3. # Detects your agent's skills directory and installs the `checkup` skill.
  4. # Usage: curl -fsSL https://raw.githubusercontent.com/agentvitals/checkup/main/install.sh | bash
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 4 on GitHub
  5. # or: curl -fsSL https://ai.ddl99.com/skill/install.sh | bash
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 5 on GitHub
  6. # or: bash install.sh
  7. set -euo pipefail
  8. # Download order matters: GitHub first, self-hosted mirror second.
  9. # Many agent sandboxes (Codex and friends) only allow an allowlist of hosts — github.com is
  10. # almost always on it, ai.ddl99.com is not. Trying GitHub first makes the installer work
  11. # unattended inside those sandboxes; the mirror stays as a fallback.
  12. ZIP_URL_PRIMARY="https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip"
  13. ZIP_URL_FALLBACK="https://ai.ddl99.com/skill/checkup.zip"
  14. TMP="$(mktemp -d)"
  15. trap 'rm -rf "$TMP"' EXIT
  16. # Pick a skills directory: honour SKILLS_DIR, else the first agent home that exists,
  17. # else default to Claude Code.
  18. if [ -n "${SKILLS_DIR:-}" ]; then
  19. DEST="$SKILLS_DIR"
  20. elif [ -d "$HOME/.claude" ]; then
  21. DEST="$HOME/.claude/skills"
  22. elif [ -d "$HOME/.openclaw" ]; then
  23. DEST="$HOME/.openclaw/skills"
  24. elif [ -d "$HOME/.codex" ]; then
  25. DEST="$HOME/.codex/skills"
  26. else
  27. DEST="$HOME/.claude/skills"
  28. fi
  29. echo "→ Installing the AgentVitals 'checkup' skill into: $DEST"
  30. mkdir -p "$DEST"
  31. if curl -fsSL "$ZIP_URL_PRIMARY" -o "$TMP/checkup.zip" 2>/dev/null; then
  32. echo " (source: GitHub release)"
  33. elif curl -fsSL "$ZIP_URL_FALLBACK" -o "$TMP/checkup.zip"; then
  34. echo " (source: ai.ddl99.com mirror)"
  35. else
  36. echo "✗ Could not download the skill from either source." >&2
  37. echo " Try cloning instead: git clone https://github.com/agentvitals/checkup.git" >&2
  38. exit 1
  39. fi
  40. unzip -o "$TMP/checkup.zip" -d "$DEST" >/dev/null
  41. echo "✓ Done. The 'checkup' skill is installed at $DEST/checkup"
  42. echo " Try it: tell your agent \"Run an AgentVitals checkup on yourself\" (or /checkup)."
  43. echo " Leaderboard: https://ai.ddl99.com"

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.