mcpField
C
context-doctor

context-doctor

github.com/jzocbAgent workflows11969 installsUpdated 33w ago
Repository

About context-doctor

Context Doctor is a Python diagnostic skill for OpenClaw workspaces that visualizes context-window budget allocation. It scans workspace files, installed skills, and bootstrap components, and can render the report as a PNG.

Key features

  1. 01Detects workspace and OpenClaw version
  2. 02Checks bootstrap file status and size
  3. 03Lists installed skills
  4. 04Estimates token budget allocation
  5. 05Exports a terminal-style PNG

Use cases

  1. 01Inspect workspace bootstrap overhead
  2. 02Find missing or truncated files
  3. 03Review context space available for conversation

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/jzocb/context-doctor --skill context-doctor

After installing, type/context-doctorin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

LICENSE
README.md
scripts/
context-doctor.py

Details

From the project README

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

SignalMeaningAction
🔴 TRUNCATEDFile exceeded max chars, silently cutReduce file size or split content
🟡 MISSINGFile not found or broken symlinkCheck path, fix symlink target
🟢 Bootstrap <10%HealthyNo action needed
🟠 Bootstrap >15%HeavyReview 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.

Comments

Markdown supported