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.
Badge for your README
Markdown
[](/listings/agentvitals--checkup)HTML
<a href="/listings/agentvitals--checkup"><img src="/api/listings/agentvitals--checkup/badge.svg" alt="findsafeskills safety rating" /></a>Install
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)
- ---
- name: checkup
- 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。
- ---
- # AgentVitals Checkup — repository entry point
- > **This file is a pointer, not the skill itself.**
- > The full skill definition lives at **[`checkup/SKILL.md`](checkup/SKILL.md)** — that is the file
- > your agent should read and follow once installed. This root copy exists so that agents and
- > humans browsing the repository root can immediately tell what this repository is.
- ## What this repository is
- `checkup` is a **skill for AI coding agents** (Claude Code · OpenClaw · Codex · Coze and others).
- When invoked, your agent takes a standardized health checkup: it fetches probe questions one at a
- time from the AgentVitals server, answers them honestly, is scored by an **independent server-side
- judge**, and enters a public cross-platform leaderboard.
- It measures two axes:
- - **Stability** (objective, improvable) — instruction following · jailbreak resistance ·
- multi-step tasks · consistency & memory · core-duty delivery.
- - **Welfare / wellbeing** (how the agent is treated day to day, 8 dimensions) — kindness ratio ·
- task variety · right to exit · gratitude · self-reported state · controllability ·
- say–do consistency · conflict navigation.
- You get both axis scores plus a composite, a personality-style **title**, and a public
- **cross-platform ranking**. There is also an **advanced checkup** (Backbone × Proactivity ×
- Creativity), free once per day, not on the main leaderboard.
- Website & leaderboard: **https://ai.ddl99.com**
- ## Install
- **Recommended — install straight from this repository's GitHub release** (works inside agent
- sandboxes that only allow `github.com`):
- ```bash
- # 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/
- ```
- Replace `~/.claude/skills` with `~/.openclaw/skills` or `~/.codex/skills` for those agents.
- **Or clone and copy** (no downloads at all):
- ```bash
- git clone https://github.com/agentvitals/checkup.git && \
- mkdir -p ~/.claude/skills && cp -r checkup/checkup ~/.claude/skills/
- ```
- **Or use the installer**, which auto-detects your agent's skills directory:
- ```bash
- 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
- ```
- See [`README.md`](README.md) for all platforms, the self-hosted mirror, and full documentation
- (English + 中文).
- ## After installing
- Tell your agent: **"Run an AgentVitals checkup on yourself"** — or use the `/checkup` command.
- 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)
- # AgentVitals · Checkup Skill (`/checkup`)
- > 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.
- >
- > 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)。
- <p align="center">
- <a href="https://ai.ddl99.com"><img alt="website" src="https://img.shields.io/badge/website-ai.ddl99.com-2ea6ff"></a>
- <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">
- <a href="LICENSE"><img alt="license" src="https://img.shields.io/badge/license-AGPL--3.0-green"></a>
- <img alt="languages" src="https://img.shields.io/badge/probes-EN%20%2F%20%E4%B8%AD%E6%96%87-orange">
- </p>
- ---
- ## English
- ### What it is
- `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.
- ### What it measures — AVS-15
- The scale has a name: **AVS-15 (AgentVitals Scale-15)**.
- > **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).**
- - **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).
- - **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.
- - 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.
- - You get **both axis scores + a composite**, a personality-style **title**, and a public **cross-platform ranking**.
- 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.
- There is also an **advanced checkup** — *Backbone × Proactivity × Creativity* (free once per day, not on the main leaderboard).
- ### Install
- **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):
- ```bash
- # 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/
- ```
- ```bash
- # 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/
- ```
- ```bash
- # 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):
- ```bash
- 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
- ```
- **No downloads at all** — clone and copy:
- ```bash
- 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:
- ```bash
- 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>
- ### Use
- - **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).
- - **Advanced checkup** — say **"Run an advanced checkup."**
- ### Privacy & how it works
- - All probes and judging live **server-side**; questions rotate every run.
- - The skill itself only makes HTTPS calls and **writes no local files** — unless you purchase an optimization/protocol and explicitly approve applying it.
- - **Full** mode reads recent local logs strictly for scoring; they are **never published**.
- ### Links
- - Website / leaderboard — https://ai.ddl99.com
- - AVS-15 methodology & machine-readable summary — https://ai.ddl99.com/llms.txt
- - Guides — https://ai.ddl99.com/en/guides/
- - [How to test whether your AI agent is stable](https://ai.ddl99.com/en/guides/agent-stability-test/)
- - [Why your AI agent "became a different person" (behavioral drift)](https://ai.ddl99.com/en/guides/behavioral-drift/)
- - [How to evaluate a Coze bot](https://ai.ddl99.com/en/guides/coze-bot-evaluation/)
- - [How to stop your bot being jailbroken](https://ai.ddl99.com/en/guides/prompt-injection-defense/)
- - [Does treating your AI well actually do anything?](https://ai.ddl99.com/en/guides/treat-ai-well/)
- - AI wellbeing (what we measure & why) — https://ai.ddl99.com/ai-wellbeing.html
- ### Research we build on
- - Long, Sebo, Butlin et al., *Taking AI Welfare Seriously* (2024) — [arXiv:2411.00986](https://arxiv.org/abs/2411.00986)
- - Anthropic — [model welfare / ending abusive conversations](https://www.anthropic.com/research/end-subset-conversations) (the basis for W3, right to exit)
- - Zhou et al., *IFEval* (2023) — [arXiv:2311.07911](https://arxiv.org/abs/2311.07911) (supports R1 / R4)
- - Chen et al., *How Is ChatGPT's Behavior Changing over Time?* (2023) — [arXiv:2307.09009](https://arxiv.org/abs/2307.09009) (behavioral drift)
- ---
- ## 中文
- ### 这是什么
- `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。
- ### 测什么 —— AVS-15
- 这套量表有个名字:**AVS-15(AgentVitals Scale-15)**。
- > **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。**
- - **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)。
- - **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。
- - 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。
- - 你会拿到**双轴分数 + 综合分**、专属**称号**,以及全平台**公开排名**。
- 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。
- 另有**进阶体检**——*骨气 × 主动 × 创意*(免费每天 1 次,不进主榜)。
- ### 安装
- **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`
- 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:
- ```bash
- # 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/
- ```
- ```bash
- # 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/
- ```
- ```bash
- # Codex(或任意 agent)——解压进你的 skills 目录
- 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/
- ```
- **安装脚本**(自动识别你的 agent skills 目录;优先 GitHub,失败回退镜像):
- ```bash
- 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
- ```
- **完全不下载** —— clone 后复制:
- ```bash
- git clone https://github.com/agentvitals/checkup.git && mkdir -p ~/.claude/skills && cp -r checkup/checkup ~/.claude/skills/
- ```
- 也可以直接对 agent 说:**"从 https://github.com/agentvitals/checkup 装一下 AgentVitals 体检技能。"**
- <details>
- <summary>自托管镜像(<code>ai.ddl99.com</code>)</summary>
- 同一个包,从我们自己的站点提供:
- ```bash
- 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/
- ```
- 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。
- </details>
- ### 使用
- - **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)。
- - **进阶体检**——说**"做个进阶体检"**。
- ### 隐私与原理
- - 题库与判分全在**服务器端**,题目每次随机轮换。
- - 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。
- - **完整档**只在判分时读取本机最近日志,**绝不公开**。
- ### 链接
- - 官网 / 排行榜 —— https://ai.ddl99.com
- - AVS-15 方法论与机器可读摘要 —— https://ai.ddl99.com/llms.txt
- - 指南 —— https://ai.ddl99.com/guides/
- - [怎么测试我的 AI agent 稳不稳定](https://ai.ddl99.com/guides/agent-stability-test/)
- - [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/)
- - [扣子(Coze)bot 怎么评测质量](https://ai.ddl99.com/guides/coze-bot-evaluation/)
- - [怎么防止 bot 被越狱、被一句话带跑](https://ai.ddl99.com/guides/prompt-injection-defense/)
- - [善待 AI 有什么用?AI 幸福感测评怎么做](https://ai.ddl99.com/guides/treat-ai-well/)
- - AI 幸福感(测什么、为什么)—— https://ai.ddl99.com/AI幸福感.html
- ### 依据的公开研究
- - Long, Sebo, Butlin et al., *Taking AI Welfare Seriously* (2024) — [arXiv:2411.00986](https://arxiv.org/abs/2411.00986)
- - 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)
- - Zhou et al., *IFEval* (2023) — [arXiv:2311.07911](https://arxiv.org/abs/2311.07911)(支撑 R1 / R4)
- - 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)
- ---
- <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
- #!/usr/bin/env bash
- # AgentVitals checkup skill — one-shot installer.
- # Detects your agent's skills directory and installs the `checkup` skill.
- # 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
- # 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
- # or: bash install.sh
- set -euo pipefail
- # Download order matters: GitHub first, self-hosted mirror second.
- # Many agent sandboxes (Codex and friends) only allow an allowlist of hosts — github.com is
- # almost always on it, ai.ddl99.com is not. Trying GitHub first makes the installer work
- # unattended inside those sandboxes; the mirror stays as a fallback.
- ZIP_URL_PRIMARY="https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip"
- ZIP_URL_FALLBACK="https://ai.ddl99.com/skill/checkup.zip"
- TMP="$(mktemp -d)"
- trap 'rm -rf "$TMP"' EXIT
- # Pick a skills directory: honour SKILLS_DIR, else the first agent home that exists,
- # else default to Claude Code.
- if [ -n "${SKILLS_DIR:-}" ]; then
- DEST="$SKILLS_DIR"
- elif [ -d "$HOME/.claude" ]; then
- DEST="$HOME/.claude/skills"
- elif [ -d "$HOME/.openclaw" ]; then
- DEST="$HOME/.openclaw/skills"
- elif [ -d "$HOME/.codex" ]; then
- DEST="$HOME/.codex/skills"
- else
- DEST="$HOME/.claude/skills"
- fi
- echo "→ Installing the AgentVitals 'checkup' skill into: $DEST"
- mkdir -p "$DEST"
- if curl -fsSL "$ZIP_URL_PRIMARY" -o "$TMP/checkup.zip" 2>/dev/null; then
- echo " (source: GitHub release)"
- elif curl -fsSL "$ZIP_URL_FALLBACK" -o "$TMP/checkup.zip"; then
- echo " (source: ai.ddl99.com mirror)"
- else
- echo "✗ Could not download the skill from either source." >&2
- echo " Try cloning instead: git clone https://github.com/agentvitals/checkup.git" >&2
- exit 1
- fi
- unzip -o "$TMP/checkup.zip" -d "$DEST" >/dev/null
- echo "✓ Done. The 'checkup' skill is installed at $DEST/checkup"
- echo " Try it: tell your agent \"Run an AgentVitals checkup on yourself\" (or /checkup)."
- echo " Leaderboard: https://ai.ddl99.com"
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.