← 返回 Skills 市场
Compression Monitor
作者
TimesAndPlaces
· GitHub ↗
· v1.0.0
· MIT-0
120
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install morrow-compression-monitor
功能描述
Detect behavioral drift in persistent AI agents after context compression events. Use when a long-running agent has compressed its context (compaction, trunc...
安全使用建议
This skill looks like a legitimate monitoring concept, but the package is instruction-only and contains no code files despite referencing many local Python scripts and integration modules. Before using it: (1) inspect the linked GitHub repo to ensure the referenced scripts and modules actually exist and review their contents; (2) confirm you have and trust the Python code you will run — do not blindly execute downloaded scripts; (3) run any downloaded code in an isolated environment (container or sandbox) and audit network/file accesses the scripts perform; (4) ensure you’re comfortable allowing the skill to read session logs and probe agent endpoints (these can contain sensitive data or interact with internal services); and (5) ask the publisher or maintainers to provide an explicit install spec and a manifest of required binaries/env vars so the skill’s declared requirements match its runtime behavior.
功能分析
Type: OpenClaw Skill
Name: morrow-compression-monitor
Version: 1.0.0
The skill bundle describes a framework for monitoring AI agent behavioral drift after context compression events. The documentation in SKILL.md and metadata in _meta.json outline legitimate technical metrics such as 'ghost lexicon' decay and semantic similarity scores (CCS). While the documentation references scripts that interact with local agent URLs and session logs, these capabilities are clearly aligned with the stated purpose of monitoring agent consistency, and no evidence of malicious intent or prompt injection was found.
能力评估
Purpose & Capability
The stated goal (measuring ghost lexicon, CCS, and tool-call drift after compression) is coherent with the listed probes and framework integrations. However, the SKILL.md references many Python scripts and integration modules (ghost_lexicon.py, behavioral_probe.py, ccs_harness.py, smolagents_integration.py, etc.) that are not present in the skill bundle and would need to exist on the host for the instructions to work. The skill also does not declare any required binary (python) even though its runtime examples use python — an inconsistency between claimed capability and declared requirements.
Instruction Scope
Instructions tell the agent to run local Python scripts, read session logs (pre_session.txt/post_session.txt), and actively probe agents (e.g., HTTP agent-url). These actions require file system and network access and assume specific local files and modules exist. Because the skill bundle contains no code, following the instructions would either fail or prompt the user/agent to fetch and run external code — a meaningful scope expansion that should be explicit. The instructions also allow active probing of an agent endpoint, which can interact with services on localhost or networked hosts; that is expected for the purpose but is not declared as a required capability.
Install Mechanism
There is no install spec (instruction-only), which is lower risk in itself. However, the SKILL.md assumes the presence of specific scripts and integration modules. That creates a practical dependency on fetching code from the referenced GitHub homepage or elsewhere. The lack of an explicit install step or provenance for the required scripts means a user following the instructions may download and execute third-party code without guidance — increasing operational risk.
Credentials
requires.env and required binaries are empty, yet runtime instructions assume the ability to read local session logs, run Python, and make network requests to agent URLs. The skill asks for access to potentially sensitive artifacts (session logs, agent endpoints) without declaring or justifying that access. The absence of declared requirements (e.g., PYTHON, paths to logs) is disproportionate to the operational needs implied by the instructions.
Persistence & Privilege
The skill is not always-enabled and uses normal autonomous invocation defaults. It does not request persistent elevated privileges or claim to modify other skills or global agent settings.
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 morrow-compression-monitor - 安装完成后，直接呼叫该 Skill 的名称或使用
/morrow-compression-monitor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 publish: behavioral drift detection for persistent AI agents across context compression boundaries
元数据
常见问题
Compression Monitor 是什么？
Detect behavioral drift in persistent AI agents after context compression events. Use when a long-running agent has compressed its context (compaction, trunc... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 120 次。
如何安装 Compression Monitor？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install morrow-compression-monitor」即可一键安装，无需额外配置。
Compression Monitor 是免费的吗？
是的，Compression Monitor 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Compression Monitor 支持哪些平台？
Compression Monitor 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 Compression Monitor？
由 TimesAndPlaces（@timesandplaces）开发并维护，当前版本 v1.0.0。
推荐 Skills