Caveman Learn Token Fixes
JuliusBrussee/caveman
Acts on a Caveman learn report: reviews ranked token sinks, applies cost-lowering edits one at a time with your consent, and reports what each fix returned.
Visualize and diagnose OpenClaw context window usage. An agent skill from jzOcb/context-doctor.
Install Context Doctor
$ npx skills add jzOcb/context-doctor --skill context-doctor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jzOcb/context-doctor context-doctor --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "context-doctor" agent skill from https://github.com/jzOcb/context-doctor/tree/main into .claude/skills/context-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-doctor", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jzOcb/context-doctor --skill context-doctor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jzOcb/context-doctor context-doctor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "context-doctor" agent skill from https://github.com/jzOcb/context-doctor/tree/main into .agents/skills/context-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-doctor", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jzOcb/context-doctor --skill context-doctor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jzOcb/context-doctor context-doctor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "context-doctor" agent skill from https://github.com/jzOcb/context-doctor/tree/main into .cursor/skills/context-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-doctor", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jzOcb/context-doctor --skill context-doctor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jzOcb/context-doctor context-doctor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "context-doctor" agent skill from https://github.com/jzOcb/context-doctor/tree/main into .gemini/skills/context-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-doctor", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jzOcb/context-doctor context-doctorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jzOcb/context-doctor --skill context-doctor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "context-doctor" agent skill from https://github.com/jzOcb/context-doctor/tree/main into .github/skills/context-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-doctor", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jzOcb/context-doctor --skill context-doctor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jzOcb/context-doctor context-doctor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "context-doctor" agent skill from https://github.com/jzOcb/context-doctor/tree/main into .opencode/skills/context-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "context-doctor", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
context-doctor- GitHub stars
- 119
- Token cost
- ~642 tokens
- SKILL.md length
- 240 words
- Files
- 5 (incl. scripts, assets)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Visualize and diagnose OpenClaw context window usage. An agent skill from jzOcb/context-doctor.
- Works in 3 steps: Workspace Files → Installed Skills → Token Budget
- User asks about context window health
- SKILL.md covers Quick Start, Output Sections, Diagnostic Signals and Image Output (for chat /…
- Runs Python scripts from its folder; calls python3
What it does
Context Doctor is an agent skill from jzOcb/context-doctor. Visualize and diagnose OpenClaw context window usage. Generates a terminal-rendered breakdown showing workspace files (status, chars, tokens), installed skills inventory, and token budget allocation across bootstrap components. Use when: (1) user asks about context window health or token usage, (2) debugging agent quality degradation ("agent got dumber"), (3) after editing workspace files to verify impact, (4) auditing bootstrap overhead. NOT for: conversation history analysis, model selection, or cost tracking.
Its SKILL.md is about 640 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and assets (for example `README.md` and `scripts/context-doctor.py`).
It sits in Agent Workflows, covering LLM cost and token optimization and Context engineering. The repository describes itself as: 🧠 Visualize and diagnose OpenClaw context window usage — terminal, PNG, or JSON. The licence is MIT.
When your agent uses it
- User asks about context window health
- Debugging agent quality degradation (agent got dumber)
- After editing workspace files to verify impact
- Auditing bootstrap overhead
Example prompts
- “agent got dumber”
- “/context-doctor”
Requirements
- Python 3
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit d622768. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Context Doctor loads about 642 tokens when it runs. Until then it costs about 133 tokens; SKILL.md has 240 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from jzOcb/context-doctor at commit d622768, republished under its MIT licence (© jzOcb). 240 words, ~642 tokens.
Download SKILL.mdSave it as
.claude/skills/context-doctor/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- context-doctor
- description
- Visualize and diagnose OpenClaw context window usage. Generates a terminal-rendered breakdown showing workspace files (status, chars, tokens), installed skills inventory, and token budget allocation across bootstrap components. Use when: (1) user asks about context window health or token usage, (2) debugging agent quality degradation ("agent got dumber"), (3) after editing workspace files to verify impact, (4) auditing bootstrap overhead. NOT for: conversation history analysis, model selection, or cost tracking.
Context Doctor
Diagnose and visualize how the context window budget is allocated.
Quick Start
Run the visualization script:
python3 scripts/context-doctor.pyThe script auto-detects:
- Workspace path (
~/.openclaw/workspaceorOPENCLAW_WORKSPACEenv) - 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 <10% | 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.pngThe 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.
© jzOcb, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (scripts, assets) in the repository root of jzOcb/context-doctor.
- SKILL.md
- LICENSE
- README.md
- assets/screenshot.png
- scripts/context-doctor.py
Open the folder on GitHubat commit d622768
Compare with similar skills
Context Doctor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Context Doctor this skilljzOcb/context-doctor | 119 | — | ~642 | Automated safety check: Pass | MIT | |
| Caveman Learn Token FixesJuliusBrussee/caveman | 111k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| OmniRoute Context CLIdiegosouzapw/OmniRoute | 75k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Subagent Brief DisciplineLichAmnesia/lich-skills | 234 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Compact Guidejh941213/my-cc-harness | 125 | — | ~621 | Automated safety check: Pass | None | |
| Omh Context Budget Reviewrlaope/oh-my-hermes | 3.2k | — | ~2k | Automated safety check: Pass | MIT |
Similar skills
OmniRoute Context CLI
diegosouzapw/OmniRoute
Manage context engineering configurations, RTK filter sets, and conversation sessions from the CLI. Apply context-relay settings and inspect active context…
Subagent Brief Discipline
LichAmnesia/lich-skills
Checks every subagent prompt before spawning, swapping pasted files and context for paths and short summaries and trimming the brief, to avoid multiplied token cost.
Compact Guide
jh941213/my-cc-harness
Context window management and token optimization guide. An agent skill from jh941213/my-cc-harness.
Omh Context Budget Review
rlaope/oh-my-hermes
[omh] Context window or token budget at risk: plan compact context, token/cost budgets, summarization checkpoints, and overflow recovery before long agent work.
Context Engine
borghei/Claude-Skills
Context management engine for AI coding agents. An agent skill from borghei/Claude-Skills.
Related
Categories
Questions about Context Doctor
What does Context Doctor do?
Visualize and diagnose OpenClaw context window usage. An agent skill from jzOcb/context-doctor. Context Doctor is an agent skill from jzOcb/context-doctor. Visualize and diagnose OpenClaw context window usage.
When should I use Context Doctor?
Context Doctor fits situations like: user asks about context window health; debugging agent quality degradation (agent got dumber); after editing workspace files to verify impact; auditing bootstrap overhead.
How do I install Context Doctor in Claude Code?
Run `npx skills add jzOcb/context-doctor --skill context-doctor -a claude-code`. Or copy the skill folder (the jzOcb/context-doctor repository) into .claude/skills/context-doctor in your project. Claude Code loads it when a task matches its description.
How do I install Context Doctor in Codex?
Run `npx skills add jzOcb/context-doctor --skill context-doctor -a codex`. Or copy the skill folder (the jzOcb/context-doctor repository) into .agents/skills/context-doctor in your project. Codex loads it when a task matches its description.
Can I use Context Doctor in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jzOcb/context-doctor --skill context-doctor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/context-doctor, .gemini/skills/context-doctor, .github/skills/context-doctor and .opencode/skills/context-doctor in your project.
What does Context Doctor need to run?
Going by SKILL.md and its folder, Context Doctor needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Context Doctor access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Context Doctor safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Context Doctor use?
Context Doctor is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Context Doctor use?
About 642 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Context Doctor?
Skills that share tags, products or a category with Context Doctor: Caveman Learn Token Fixes (JuliusBrussee/caveman, 111k stars), OmniRoute Context CLI (diegosouzapw/OmniRoute, 75k stars), Subagent Brief Discipline (LichAmnesia/lich-skills, 234 stars) and Compact Guide (jh941213/my-cc-harness, 125 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Context Doctor?
jzOcb (a GitHub user) maintains it in jzOcb/context-doctor, which has 119 GitHub stars. The repository was last updated on March 16, 2026.
Source: jzOcb/context-doctor on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.