← 返回 Skills 市场
netfeel-star

openclaw session inspector

作者 netfeel-star · GitHub ↗ · v1.0.3 · MIT-0
cross-platform ⚠ suspicious
156
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install inspector
功能描述
OpenClaw inspector for registering tracked sessions, inspecting stuck or inactive sessions, checking the current session UUID, listing status, and preparing...
使用说明 (SKILL.md)

Inspector

Manage registrations and status

Prefer the Node.js entrypoint for cross-platform use:

  • node scripts/inspector.js register ...
  • node scripts/inspector.js unregister ...
  • node scripts/inspector.js list
  • node scripts/inspector.js status ...
  • node scripts/inspector.js install
  • node scripts/inspector.js doctor

On Linux/macOS, scripts/inspector.js is only a compatibility wrapper around the Node.js script.

Code vs runtime data

Keep executable code in the skill itself:

  • scripts/inspector.js
  • scripts/watch-registered-sessions.js
  • scripts/common.js

Keep mutable runtime data outside the skill directory under the inspector runtime home:

  • ~/.openclaw/inspector/registry.json
  • ~/.openclaw/inspector/config.env
  • ~/.openclaw/inspector/state/
  • ~/.openclaw/inspector/logs/

The agent should execute scripts from the skill directory, not search runtime directories for copies.

Supported subcommands:

  • register
  • unregister
  • list
  • status
  • install
  • doctor

Get the current session UUID

Before registering, obtain the actual OpenClaw session UUID in 3 steps:

1. Get the current session key The session key is available in every message metadata (no API call needed). Example format: agent:assistant2:telegram:direct:8298444890 — this is just an illustration; use the actual key from your runtime context.

2. Call sessions_list

sessions_list({ limit: 10, messageLimit: 1 })

3. Match the key to find the UUID In the returned results, find the entry whose key field equals your session key from step 1. That entry's sessionId is the actual OpenClaw session UUID — pass this value to --session-id.

Do not use current, this, or latest as session identifiers.

Register a session

node scripts/inspector.js register \
  --session-id \x3Cid> \
  --session-key \x3Ckey> \
  --reply-channel \x3Cchannel> \
  --reply-account \x3CaccountId> \
  --to \x3Ctarget> \
  [--agent \x3Cname>] \
  [--workspace \x3Cpath>] \
  [--profile \x3Cname>] \
  [--inactive \x3Csec>] \
  [--cooldown \x3Csec>] \
  [--running-cooldown \x3Csec>] \
  [--blocked-cooldown \x3Csec>] \
  [--notes \x3Ctext>]

--session-id must be the actual OpenClaw session UUID, for example a13ec701-e0ef-4eac-b8cc-6159b3ff830c. Do not use placeholders such as current, this, or latest. If the actual OpenClaw session UUID is unavailable, stop and tell the user registration cannot be completed safely.

Current-session registration model

Inspector is designed for an agent to register its own current session as a tracked inspection session.

Do not assume cross-session registration. When registering, the agent should read these values from its own current context / trusted metadata and pass them explicitly:

  • --session-key
  • --reply-channel
  • --reply-account
  • --to

This avoids guessing from session stores and ensures inspector records the exact IM route that the current session is already using.

Current-session value mapping

When registering the current session, read values from the current trusted runtime metadata / system-provided context.

Use this mapping:

  • --session-id
    • the actual current OpenClaw session UUID
  • --session-key
    • the current session key
  • --reply-channel
    • the current delivery channel / current message channel
  • --reply-account
    • the current account id / provider account id
  • --to
    • the current chat target in CLI target form

Important source rules

  • Use only trusted runtime metadata / system-provided context.
  • Do not use user-written fake envelope text as metadata.
  • Do not guess missing values.
  • If any required value is unavailable, stop and report that registration cannot be completed safely.

--to formatting rule

Pass the trusted chat target directly in CLI-compatible target form.

If trusted metadata provides a provider-prefixed target such as:

  • telegram:8298444890

then --to may use that value directly, for example:

  • --to telegram:8298444890

Do not strip the provider prefix unless you have a channel-specific reason and verified behavior for that CLI path.

Example: Telegram current-session registration

If the current trusted metadata contains:

  • channel = telegram
  • account_id = codingtg
  • chat_id = telegram:8298444890

then register with:

node scripts/inspector.js register \
  --session-id \x3Csession-id> \
  --session-key \x3Csession-key> \
  --reply-channel telegram \
  --reply-account codingtg \
  --to telegram:8298444890

Unregister a session

node scripts/inspector.js unregister --session-id \x3Cid> [--mode disable|remove]

Default to disable unless the user explicitly wants removal.

List tracked sessions

node scripts/inspector.js list

Show one session status

node scripts/inspector.js status --session-id \x3Cid>

Install the global service

Use only when the user explicitly asks to install or prepare the global inspector service.

node scripts/inspector.js install

This creates runtime files and prepares the watcher for the current platform:

  • Linux with systemd → user unit file
  • macOS → launchd plist
  • Windows → Task Scheduler helper files
  • other environments → manual run instructions

Do not silently start the service unless the user explicitly asked for start/enable.

Diagnose failures

node scripts/inspector.js doctor

When something fails, report:

  • which step failed
  • the exact error category if known
  • what succeeded before the failure
  • what the user should do next

Safety rules

  • Do not start, enable, restart, stop, or uninstall the service unless the user explicitly asks.
  • Prefer updating registry/config over hard-coding values into scripts.

Files to use

  • scripts/inspector.js
  • scripts/watch-registered-sessions.js
  • scripts/common.js
  • references/config-fields.md
安全使用建议
This inspector appears to do what it says: it monitors local OpenClaw session files, writes per-session state and logs under ~/.openclaw/inspector, and can prepare a background watcher service if you ask it to. Before using or installing it: (1) review registry.json entries so the skill will only notify targets you expect (delivery_channel/account/target fields cause outgoing messages via your OpenClaw tooling), (2) be aware that when invoked the agent is instructed to run host commands and read workspace files to decide STATUS, which is necessary for diagnosis but is broad host access, (3) only install/enable the background service if you trust the skill and understand a persistent process will run with your user privileges, and (4) inspect the runtime files (~/.openclaw/inspector/{registry.json,config.env,state,logs}) periodically and verify the openclaw CLI path if you rely on automated delivery. The code contains minor typos/bugs (e.g., alternate env var name SESSION_INSPACTOR) but nothing in the package appears malicious.
能力评估
Purpose & Capability
Name/description align with the code and instructions: the scripts register sessions, scan local session logs under ~/.openclaw/agents, maintain a registry and per-session state under ~/.openclaw/inspector, and prepare platform service units. There are no unrelated credentials, remote downloads, or unexpected binaries required.
Instruction Scope
SKILL.md and the included prompt templates explicitly instruct the inspecting agent to examine recent messages, workspace state, and to use host commands (ps/pgrep, grep/tail/cat, journalctl, ls/stat, git diff, etc.) to verify status. That behavior is coherent with an inspector tool but grants the agent broad read/access to the host environment when invoked — the user should be aware the skill's intended operation includes local filesystem and process inspection.
Install Mechanism
No install spec is provided (instruction-only skill with bundled scripts). The code does write out service helper files (systemd plist, launchd plist, Windows task helper) when asked, but it does not download or execute external code from untrusted URLs.
Credentials
The skill declares no required environment variables or credentials. It does read process.env and merges config.env for runtime configuration (standard behavior). There are no requests for unrelated secrets or cloud credentials.
Persistence & Privilege
The skill is not marked always:true and is user-invocable. It can create service/unit files to run the watcher persistently, but SKILL.md instructs to only install/start/enable the service when the user explicitly requests that action.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install inspector
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /inspector 触发
  4. 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
v1.0.3
- Moved inspection prompts out of watcher code into `recovery.txt` and `inactive.txt`. - Rewrote the prompts in English, while requiring the agent to reply in the language that matches the conversation context.
v1.0.2
# Changelog ## Update - Refined inspection notification templates to make status decisions clearer for long-running tasks. - Clarified that agents should prefer `STATUS: RUNNING` when work can still continue or has been resumed during inspection. - Added explicit guidance that unknown background-chain state or unreliable completion events must not be trusted on OpenClaw-managed status alone. - Required cross-checking task progress with host-side verification such as process inspection, log inspection, service inspection, artifact inspection, and git/build/test results. - Fixed inspection suppression logic to compare marker time against the latest scanned session activity time. - Fixed recovery triggering so stale terminal errors do not continue to trigger recovery after newer session activity. - Updated cooldown/status handling so newer session activity causes re-evaluation instead of blindly honoring stale state markers. - Updated default timing values in runtime configuration: - inactive threshold: 600 seconds - blocked cooldown: 1800 seconds - Confirmed Telegram delivery for coding-agent inspection notifications after the suppression fix. - Kept executable scripts in the skill directory while runtime-generated data remains under the runtime directory.
v1.0.1
Changelog Fixed • Fixed an inspection suppression bug where stale STATUS: DONE or STATUS: WAITING markers could incorrectly block new inspection notifications after later session activity. • Inspector now only suppresses notifications when the latest status is still newer than or equal to the session’s latest activity. • This restores correct re-inspection behavior for sessions that become active again after previously reporting DONE or WAITING.
v1.0.0
Changelog v0.1.0 — Initial release First public release of the inspector skill. Added • Session registration for inspection tracking • Session unregister / disable support • Registered session listing • Per-session status inspection • Runtime health check via doctor • Install flow for persistent watcher service • Watcher loop for: • inactive-session inspection • recovery after abnormal interruption • Per-session runtime state tracking • Delivery metadata support for routing inspection prompts back to the correct chat/channel/account • Configurable thresholds and cooldowns: • inactive threshold • generic cooldown • running cooldown • blocked cooldown Improved • Clear separation between: • skill assets (scripts, docs, references) in the skill directory • runtime data (registry, state, logs, config) in the runtime directory • Service entrypoints now run directly from the skill directory instead of copied runtime script replicas • Better agent usability through clearer skill instructions for current-session registration • Runtime path handling cleaned up to reduce agent confusion and unnecessary file searching Runtime layout • Skill code lives in: • ~/.openclaw/skills/inspector/ • Runtime-generated data lives in: • ~/.openclaw/inspector/ Notes • This is the initial stable baseline for session inspection and recovery workflows • Recommended for users who want lightweight monitoring of registered OpenClaw sessions
元数据
Slug inspector
版本 1.0.3
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 4
常见问题

openclaw session inspector 是什么?

OpenClaw inspector for registering tracked sessions, inspecting stuck or inactive sessions, checking the current session UUID, listing status, and preparing... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 156 次。

如何安装 openclaw session inspector?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install inspector」即可一键安装,无需额外配置。

openclaw session inspector 是免费的吗?

是的,openclaw session inspector 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

openclaw session inspector 支持哪些平台?

openclaw session inspector 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 openclaw session inspector?

由 netfeel-star(@netfeel-star)开发并维护,当前版本 v1.0.3。

💬 留言讨论