← 返回 Skills 市场
swarm-self-heal
作者
Todd Kuehnl
· GitHub ↗
· v0.1.1
547
总下载
0
收藏
3
当前安装
2
版本数
在 OpenClaw 中安装
/install swarm-self-heal
功能描述
Swarm reliability watchdog for OpenClaw — validates gateway/channel and every lane, performs bounded recovery, and emits auditable receipts.
安全使用建议
This skill appears to implement the described watchdog behavior and uses only the OpenClaw CLI plus bash/jq, but review a few things before installing: 1) Inspect setup.sh and change/remove the hard-coded Telegram fallback '8563003761' (or ensure your $HOME/.openclaw/openclaw.json contains the correct channel target) to avoid sending alerts to an unexpected recipient. 2) Installing will copy scripts into ~/.openclaw/workspace-studio/scripts and register cron jobs that run autonomously and may restart the user-level openclaw-gateway service—make a backup of OpenClaw cron/jobs.json and openclaw.json first. 3) Run the scripts manually in a controlled environment (or review outputs from check.sh) to confirm behavior before enabling cron. If you want higher assurance, ask the author for an explanation of the fallback number or a configurable opt-in for external notifications.
功能分析
Type: OpenClaw Skill
Name: swarm-self-heal
Version: 0.1.1
The 'swarm-self-heal' skill is designed to monitor and self-heal an OpenClaw agent swarm. It uses standard OpenClaw CLI commands, `bash`, and `jq` to perform health checks, restart the gateway if needed, and ping agents. Persistence is established via cron jobs in `scripts/setup.sh`, which is a core, stated feature for a watchdog. The skill utilizes prompt engineering in `scripts/setup.sh` to instruct the agent running the cron job to execute a local script and format its output, and in `scripts/swarm_self_heal.sh` to send benign 'ping' messages to other agents. While these are instances of prompt injection, they are used for the skill's stated purpose and show no evidence of malicious intent, data exfiltration, or unauthorized actions. All operations are aligned with system maintenance and reliability.
能力评估
Purpose & Capability
Name/description align with the scripts: the files implement a passive-first swarm watchdog using the OpenClaw CLI, perform bounded recovery (gateway restart + re-probe), emit receipts, and set up cron lanes. Required binaries (bash, jq, openclaw) are appropriate.
Instruction Scope
Runtime instructions and scripts stay on task: they read OpenClaw status, call openclaw health/channels/agent commands, and install scripts into the OpenClaw workspace. They read $HOME/.openclaw/openclaw.json and cron/jobs.json (expected for cron wiring). One scope concern: setup.sh will create cron jobs that post messages via the OpenClaw Telegram channel—so telemetry/outputs will be sent externally via OpenClaw's channel if configured (see environment_proportionality).
Install Mechanism
No package download or remote install is performed by the registry metadata; the repo contains local shell scripts and the user-run setup.sh copies them into ~/.openclaw/workspace-studio/scripts and uses the OpenClaw CLI to register cron jobs. That is a low-risk, user-initiated install pattern, but it does write scripts into the user's OpenClaw workspace.
Credentials
The skill does not request extra credentials, but setup.sh falls back to a hard-coded Telegram recipient '8563003761' when it cannot derive a target from $HOME/.openclaw/openclaw.json. This means if the user's OpenClaw config lacks a telegram target, the skill will create cron jobs that send notifications to that number—potentially leaking incident output to an external party. The scripts also read OpenClaw config files (which may contain channel tokens) — this is expected for a notifier but should be acknowledged before installing.
Persistence & Privilege
The skill adds/edits OpenClaw cron jobs (primary and backup watchdog) so it becomes an autonomously-scheduled component via OpenClaw (normal for a watchdog). always:false, so it won't be force-included in all agents, but installing will create scheduled autonomous runs and restart the user-level openclaw-gateway service when needed. Users should be aware this gives the skill recurring execution via OpenClaw cron.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install swarm-self-heal - 安装完成后，直接呼叫该 Skill 的名称或使用
/swarm-self-heal触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.1
Anvil AI rebrand + labs.anvil-ai.io normalization.
v0.1.0
Initial release. Swarm reliability watchdog with passive-first detection, bounded recovery, and auditable receipts.
元数据
常见问题
swarm-self-heal 是什么？
Swarm reliability watchdog for OpenClaw — validates gateway/channel and every lane, performs bounded recovery, and emits auditable receipts. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 547 次。
如何安装 swarm-self-heal？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install swarm-self-heal」即可一键安装，无需额外配置。
swarm-self-heal 是免费的吗？
是的，swarm-self-heal 完全免费（开源免费），可自由下载、安装和使用。
swarm-self-heal 支持哪些平台？
swarm-self-heal 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 swarm-self-heal？
由 Todd Kuehnl（@tkuehnl）开发并维护，当前版本 v0.1.1。
推荐 Skills