← 返回 Skills 市场
1030
总下载
0
收藏
3
当前安装
1
版本数
在 OpenClaw 中安装
/install arc-agent-lifecycle
功能描述
Manage the lifecycle of autonomous agents and their skills. Version configurations, plan upgrades, track retirement, and maintain change history across agent...
使用说明 (SKILL.md)
Agent Lifecycle Manager
Track your agent's evolution from deployment to retirement. Version configurations, plan skill upgrades, and maintain a complete change history.
Why This Exists
Agents evolve constantly — new skills installed, old ones retired, configurations changed, models swapped. Without lifecycle tracking, you cannot answer: "What was my agent running last Tuesday?" or "What changed when things broke?"
Commands
Snapshot current agent state
python3 {baseDir}/scripts/lifecycle.py snapshot --name "pre-upgrade"
Compare two snapshots
python3 {baseDir}/scripts/lifecycle.py diff --from "pre-upgrade" --to "post-upgrade"
List all snapshots
python3 {baseDir}/scripts/lifecycle.py list
Rollback to a snapshot
python3 {baseDir}/scripts/lifecycle.py rollback --to "pre-upgrade" --dry-run
Track a skill retirement
python3 {baseDir}/scripts/lifecycle.py retire --skill old-skill --reason "Replaced by new-skill v2"
View change history
python3 {baseDir}/scripts/lifecycle.py history --limit 20
What It Tracks
- Installed skills: Name, version, install date, last used
- Configuration state: Environment vars, model assignments, feature flags
- Change events: Installs, updates, removals, config changes
- Retirement log: Why skills were removed, what replaced them
- Snapshots: Point-in-time captures of full agent state
Data Storage
Lifecycle data is stored in ~/.openclaw/lifecycle/ as JSON files.
安全使用建议
This package provides a small Python tool that scans your per-user OpenClaw skill directories and writes JSON snapshots to ~/.openclaw/lifecycle. It does not request credentials or make network calls. However, the SKILL.md claims it records environment variables, model assignments, 'last used' timestamps, and feature flags — the included script does not implement those features. Before installing or relying on it: (1) Inspect the saved JSON snapshots in ~/.openclaw/lifecycle to confirm they only contain the metadata you expect (paths, file counts, sizes, SKILL.md frontmatter). (2) If you need the additional tracking (env vars, model assignments), ask the maintainer for clarification or an updated implementation. (3) Consider file permissions on ~/.openclaw/lifecycle because snapshots contain file paths and metadata that could be sensitive if shared. (4) If you expect automated/autonomous invocation, note this skill can be invoked by the agent (disable-model-invocation is false) — that’s normal but increases blast radius if the skill were later modified to collect more data. If you want a higher-assurance verdict, provide the developer/source identity or an updated script that actually implements the claimed tracking so I can re-evaluate.
功能分析
Type: OpenClaw Skill
Name: arc-agent-lifecycle
Version: 1.0.0
The skill's core functionality for managing agent lifecycle, including scanning installed skills and recording state, appears benign. However, the `scripts/lifecycle.py` script is vulnerable to path traversal. User-supplied arguments for snapshot names (e.g., `--name` in `snapshot`, `--from`, `--to` in `diff`, `--to` in `rollback`) are directly used to construct file paths within the `SNAPSHOTS_DIR`. This could allow an attacker to read or write arbitrary files on the system (e.g., `snapshot --name '../../../../tmp/evil'`), depending on the agent's permissions. While the `rollback` command explicitly states it's a dry-run and doesn't implement actual changes, the path traversal vulnerability itself is a significant security flaw, classifying the skill as suspicious.
能力评估
Purpose & Capability
Name/description promises comprehensive lifecycle tracking (environment vars, model assignments, feature flags, 'last used'). The included script only scans ~/.openclaw/skills and workspace/skills for SKILL.md, gathers basic metadata (name, path, file count, size, last modified) and writes snapshots/history to ~/.openclaw/lifecycle. Several claimed capabilities (capturing environment variable values, model assignments, last-used timestamps, feature-flag state) are not implemented — this is a substantive mismatch between stated purpose and actual capability.
Instruction Scope
Runtime instructions tell the user to run the included Python script with snapshot/diff/list/rollback/retire/history commands. The script reads the user's home directory (~/.openclaw/skills and workspace), SKILL.md files, and computes file sizes/counts; it writes JSON snapshots and logs to ~/.openclaw/lifecycle. There are no network calls or attempts to read arbitrary system files or environment variables. It does access user home and skill files (expected for this purpose), so scope is mostly appropriate, but the SKILL.md text over-promises data it will collect.
Install Mechanism
No install spec; instruction-only with a bundled Python script. Required binary is python3, which is reasonable. Nothing is downloaded or extracted from external URLs.
Credentials
No environment variables or credentials are requested. The script does not read environment variables or external secrets. It only reads files under standard per-user OpenClaw paths and writes snapshots to ~/.openclaw/lifecycle, which is proportional to lifecycle management.
Persistence & Privilege
The skill is not always: true and is user-invocable. It writes only to ~/.openclaw/lifecycle and does not modify other skills or system-wide settings. It does not persist across agents beyond its own snapshot files.
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 arc-agent-lifecycle - 安装完成后，直接呼叫该 Skill 的名称或使用
/arc-agent-lifecycle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
v1.0.0
Initial release of the agent-lifecycle skill:
- Manage autonomous agent lifecycle, tracking configurations, skills, and changes.
- Take and compare snapshots of agent state.
- Track skill retirements and maintain a detailed change history.
- Command-line interface for snapshotting, rollback, diffs, and history queries.
- Stores lifecycle data as JSON files in the user directory.
元数据
常见问题
Agent Lifecycle 是什么？
Manage the lifecycle of autonomous agents and their skills. Version configurations, plan upgrades, track retirement, and maintain change history across agent... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1030 次。
如何安装 Agent Lifecycle？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install arc-agent-lifecycle」即可一键安装，无需额外配置。
Agent Lifecycle 是免费的吗？
是的，Agent Lifecycle 完全免费（开源免费），可自由下载、安装和使用。
Agent Lifecycle 支持哪些平台？
Agent Lifecycle 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（darwin, linux）。
谁开发了 Agent Lifecycle？
由 ArcSelf（@trypto1019）开发并维护，当前版本 v1.0.0。
推荐 Skills