cco-anatomy
Generate a compact project map so Claude understands the codebase without opening every file
Show detailed token ROI report across all tracked sessions
$ npx -y skills add egorfedorov/claude-context-optimizer --skill cco-report --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/cco-reportContext preview
The summary Claude sees to decide when to auto-load this skill.
Show detailed token ROI report across all tracked sessions
name: cco-report description: Show detailed token ROI report across all tracked sessions license: MIT allowed-tools: [Bash, Read]
Generate and display a comprehensive token usage report across all tracked sessions.
Run:
node ${CLAUDE_PLUGIN_ROOT}/src/report.js fullPresent the full report to the user. After showing it, provide actionable insights:
1. If the waste trend is WORSENING, warn the user and suggest specific changes 2. If there are top wasted files, suggest the user avoid reading those files in future sessions or use more targeted reads (offset/limit) 3. If average tokens per session is high, suggest task splitting strategies 4. Calculate the estimated monthly cost savings if the user maintains current improvement trends
Also run:
node ${CLAUDE_PLUGIN_ROOT}/src/tracker.js suggest "$(pwd)"And present the smart suggestions (files to preload, files to avoid) for the current project directory.
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