cco-anatomy
Generate a compact project map so Claude understands the codebase without opening every file
Show weekly/daily efficiency digest with score and trends
$ npx -y skills add egorfedorov/claude-context-optimizer --skill cco-digest --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/cco-digestContext preview
The summary Claude sees to decide when to auto-load this skill.
Show weekly/daily efficiency digest with score and trends
name: cco-digest description: Show weekly/daily efficiency digest with score and trends license: MIT argument-hint: "[7|14|30] (days, default 7)" allowed-tools: [Bash]
Generate and display an efficiency digest for the specified time period.
Parse $ARGUMENTS for the number of days (default: 7).
Run:
node ${CLAUDE_PLUGIN_ROOT}/src/digest.js $ARGUMENTSPresent the digest to the user. Highlight: 1. Their efficiency grade (S/A/B/C/D/F) and what it means 2. Which score components are weakest and how to improve them 3. Cost savings opportunities 4. Trend over time — is efficiency improving or declining?
If grade is C or below, provide 3 specific actionable tips. If grade is A or above, congratulate them and suggest advanced techniques.
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
Generate a compact project map so Claude understands the codebase without opening every file
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