cco-budget
Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Claude 5 lineup, Opus 5 default fallback, full 1M context…
Generate a compact project map so Claude understands the codebase without opening every file
$ npx -y skills add egorfedorov/claude-context-optimizer --skill cco-anatomy --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/cco-anatomyContext preview
The summary Claude sees to decide when to auto-load this skill.
Generate a compact project map so Claude understands the codebase without opening every file
name: cco-anatomy description: Generate a compact project map so Claude understands the codebase without opening every file license: MIT allowed-tools: [Bash, Read]
Generate a compact project map showing every file with its size, token estimate, and category. This lets Claude understand the codebase structure by reading one file instead of twenty.
Run the anatomy generator for the current working directory:
node ${CLAUDE_PLUGIN_ROOT}/src/anatomy.js "${CWD}"Present the output to the user. Highlight: 1. **Total token cost** if all files were read 2. **Heaviest files** that should use offset/limit 3. **Category breakdown** — where most tokens live (source, config, tests, docs)
Suggest saving the output to `PROJECT_ANATOMY.md` in the project root if the user wants to use it as persistent context.
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
Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Claude 5 lineup, Opus 5 default fallback, full 1M context…
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
View and tune CCO's behavior thresholds — re-read warnings, cache staleness, prompt-coach length bands, and the /cco-pack budget cap