/cco-doctor
Health check for the context-optimizer plugin install — verifies versions, hooks, data dir, model config, and reports any issues
$ npx -y skills add egorfedorov/claude-context-optimizer --skill cco-doctor --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/cco-doctor
Context preview
The summary Claude sees to decide when to auto-load this skill.
Health check for the context-optimizer plugin install — verifies versions, hooks, data dir, model config, and reports any issues
SKILL.md
cco-doctor.SKILL.mdname: cco-doctor
description: Health check for the context-optimizer plugin install — verifies versions, hooks, data dir, model config, and reports any issues
license: MIT
allowed-tools: [Bash, Read]
CCO Doctor
When the user runs `/cco-doctor` or reports the plugin "isn't working", run a quick health check.
How to use
Standard run (fast — under 1s):
node ${CLAUDE_PLUGIN_ROOT}/src/doctor.jsWith test suite (slower — runs all unit tests):
node ${CLAUDE_PLUGIN_ROOT}/src/doctor.js --testsWhat it checks
- Plugin manifest and `package.json` exist
- Versions are in sync (`plugin.json` and `package.json`)
- `hooks.json` is valid JSON with all expected event types
- All hook scripts present in `src/`
- Data directory `~/.claude-context-optimizer/` is writable
- `patterns.json` size is reasonable
- Global stats file is parseable
- User config has sane model + budget for the chosen model
- Node version meets the >=18 requirement
Presentation
Translate the doctor output into plain language. If anything is `fail`, walk the user through the fix:
- versions out of sync → `npm run sync-version`
- patterns.json too big → `/cco-clean`
- budget > model window → `/cco-budget set <smaller>` or pick a 1M-context model (e.g. `opus-4.8`)
- node too old → upgrade Node
If everything is `pass`, confirm "плагин в порядке, текущая версия Х.Y.Z" and stop.
Read more
name: cco-doctor description: Health check for the context-optimizer plugin install — verifies versions, hooks, data dir, model config, and reports any issues license: MIT allowed-tools: [Bash, Read]
CCO Doctor
When the user runs `/cco-doctor` or reports the plugin "isn't working", run a quick health check.
How to use
Standard run (fast — under 1s):
node ${CLAUDE_PLUGIN_ROOT}/src/doctor.jsWith test suite (slower — runs all unit tests):
node ${CLAUDE_PLUGIN_ROOT}/src/doctor.js --testsWhat it checks
- Plugin manifest and `package.json` exist
- Versions are in sync (`plugin.json` and `package.json`)
- `hooks.json` is valid JSON with all expected event types
- All hook scripts present in `src/`
- Data directory `~/.claude-context-optimizer/` is writable
- `patterns.json` size is reasonable
- Global stats file is parseable
- User config has sane model + budget for the chosen model
- Node version meets the >=18 requirement
Presentation
Translate the doctor output into plain language. If anything is `fail`, walk the user through the fix:
- versions out of sync → `npm run sync-version`
- patterns.json too big → `/cco-clean`
- budget > model window → `/cco-budget set <smaller>` or pick a 1M-context model (e.g. `opus-4.8`)
- node too old → upgrade Node
If everything is `pass`, confirm "плагин в порядке, текущая версия Х.Y.Z" and stop.
Claude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts, efficiency scores, git-aware suggestions — all local, zero config.
Repo: egorfedorov/claude-context-optimizer
Other skills on claude-context-optimizer.
- /cco-anatomy
Generate a compact project map so Claude understands the codebase without opening every file
Open skill - /cco-budget
Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Opus 4.8 default, full 1M context at standard price)
Open skill - /cco-claudemd
Analyze CLAUDE.md files for token bloat and suggest optimizations
Open skill - /cco-clean
Clean up old tracking data and reset statistics
Open skill - /cco-coach
Analyze the user's last prompt for clarity, scope and specificity — give a quality score and concrete suggestions to make the next prompt produce better results
Open skill - /cco-digest
Show weekly/daily efficiency digest with score and trends
Open skill

