← 返回 Skills 市场
jzocb

Context Doctor

作者 jzOcb · GitHub ↗ · v1.2.0
cross-platform ✓ 安全检测通过
1926
总下载
1
收藏
30
当前安装
4
版本数
在 OpenClaw 中安装
/install context-doctor
功能描述
Visualize and diagnose OpenClaw context window usage. Generates a terminal-rendered breakdown showing workspace files (status, chars, tokens), installed skil...
使用说明 (SKILL.md)

Context Doctor

Diagnose and visualize how the context window budget is allocated.

Quick Start

Run the visualization script:

python3 scripts/context-doctor.py

The script auto-detects:

  • Workspace path (~/.openclaw/workspace or OPENCLAW_WORKSPACE env)
  • OpenClaw version (via openclaw --version)
  • Installed skills (system + workspace)
  • Bootstrap file sizes and status

Output Sections

1. Workspace Files

Shows each bootstrap file with:

  • Status: ✓ OK / ✗ MISSING / ⚠ TRUNCATED (symlink target missing = MISSING)
  • Characters & Tokens: Raw size and estimated token count (chars/4)
  • Visual bar: Proportional to file size

2. Installed Skills

Lists all discovered SKILL.md files from system and workspace skill directories. Skills are loaded on-demand, not in bootstrap — shown for awareness only.

3. Token Budget

Breaks down bootstrap overhead:

  • System Prompt (framework)
  • Workspace Files (from scan)
  • Skills List (metadata descriptions)
  • Tool Schemas + Summaries

Shows total bootstrap % vs free conversation space.

Diagnostic Signals

Signal Meaning Action
🔴 TRUNCATED File exceeded max chars, silently cut Reduce file size or split content
🟡 MISSING File not found or broken symlink Check path, fix symlink target
🟢 Bootstrap \x3C10% Healthy No action needed
🟠 Bootstrap >15% Heavy Review workspace files for bloat

Image Output (for chat / sharing)

Generate a PNG image directly — no terminal screenshot needed:

python3 scripts/context-doctor.py --png /tmp/context-doctor.png

The script renders a colored terminal-style image via Rich SVG export. Requires: rich (pip3 install rich) + one of: rsvg-convert (brew install librsvg) or cairosvg (pip3 install cairosvg).

Agent workflow: When a user asks about context health in chat, run with --png and send the image directly. The output path is printed to stdout on success.

安全使用建议
Install this if you want a local OpenClaw context-usage report. Review any terminal, JSON, PNG, or SVG output before sharing it, because it may reveal local workspace paths, installed skill names, and the presence or size of personal context files.
能力评估
Purpose & Capability
The Python script’s behavior matches the stated purpose: it detects an OpenClaw workspace, checks fixed bootstrap files, inventories installed SKILL.md files, estimates token usage, and optionally renders text, JSON, or PNG output.
Instruction Scope
The skill asks the agent to run a local script and optionally generate a PNG; this is disclosed and user-directed, but reports may expose local paths, file status, file sizes, and installed skill names.
Install Mechanism
There is no hidden installer or automatic setup. PNG export may require optional local dependencies such as rich, rsvg-convert, or cairosvg.
Credentials
Use of OPENCLAW_WORKSPACE, openclaw config/version commands, local file reads, and optional PNG writes is proportionate to context diagnostics; no network access or credential collection was found.
Persistence & Privilege
No background process, privilege escalation, credential/session handling, destructive mutation, or automatic persistence was found. PNG mode writes only to the requested output path and removes its temporary SVG when conversion succeeds.
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 context-doctor
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /context-doctor 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
v1.2.0
feat: --summary flag for concise text output (emoji, health verdict, top files, budget). --png --summary combo for agent chat workflow. Fix: ANSI leak in PNG mode. Add --png/--json mutual exclusion.
v1.1.1
Codex review fixes: PTY robustness (timeout, fd cleanup, no zombies), nested ANSI color handling, path validation, sys.executable compat
v1.1.0
Add --png flag: render colored terminal visualization as PNG image directly, no terminal needed. Agents can generate and send context health images in chat.
v1.0.0
Initial release: terminal visualization of OpenClaw context window usage, workspace file health checks, token budget breakdown, JSON output mode
元数据
Slug context-doctor
版本 1.2.0
许可证
累计安装 30
当前安装数 30
历史版本数 4
常见问题

Context Doctor 是什么?

Visualize and diagnose OpenClaw context window usage. Generates a terminal-rendered breakdown showing workspace files (status, chars, tokens), installed skil... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1926 次。

如何安装 Context Doctor?

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

Context Doctor 是免费的吗?

是的,Context Doctor 完全免费(开源免费),可自由下载、安装和使用。

Context Doctor 支持哪些平台?

Context Doctor 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 Context Doctor?

由 jzOcb(@jzocb)开发并维护,当前版本 v1.2.0。

💬 留言讨论