egorfedorov/claude-context-optimizer
19 skills · 2,357 total installs
$npx skills add egorfedorov/claude-context-optimizerSkillInstalls
cco-claudemdAnalyze CLAUDE.md files for token bloat and suggest optimizationsccoContext Control Center — one screen for budget, $ spent, tokens saved, waste, last prompt grade, the active task, and ready-to-run optimization actionssmart-loaderAutomatically suggests optimal files to preload based on the user's task description and historical context patterns.cco-budgetConfigure token budget limits, auto-compact settings, and view current budget status (model-aware — Opus 4.8 default, full 1M context at standard price)cco-reportShow detailed token ROI report across all tracked sessionscco-anatomyGenerate a compact project map so Claude understands the codebase without opening every filecco-cleanClean up old tracking data and reset statisticscco-gitShow git-aware context suggestions for current working directorycco-digestShow weekly/daily efficiency digest with score and trendscco-exportExport context report as Markdown or HTMLcco-templatesManage context templates for common task typescco-shieldShow ContextShield status and waste protection stats; suggest or apply .contextignore rules from historical wastecco-replayShow recent session summaries for quick context recoverycco-roiCalculate monthly token savings and ROI by modelcco-doctorHealth check for the context-optimizer plugin install — verifies versions, hooks, data dir, model config, and reports any issuescco-packBuild an optimal context pack for the user's task — ranked file list with offset/limit suggestions, based on git state, mentioned paths, and historical patternscco-coachAnalyze the user's last prompt for clarity, scope and specificity — give a quality score and concrete suggestions to make the next prompt produce better resultscco-taskOrganize work by task and track tokens/cost per task — start a task, list tasks, or mark the active one done.cco-overheadAudit the fixed context overhead every session starts with — system prompt, MCP tools, agents, CLAUDE.md, memory — measured from real transcript usage