Cuts wasted context in your AI Code and shows what each session really costs.
Model-aware for the your AI 5 lineup (Opus 5.5, Sonnet 5.5, Fable 5.1) with 1-hour-cache pricing and cache-break warnings; read dedup and file digests; auto .contextignore; a ru/en prompt coach; task state that survives /compact; and a one-screen /cco control center. Runs locally, no network calls.
Skills 22 in the Claude listing
cco Context Control Center — one screen for budget, $ spent, tokens saved, waste, last prompt grade, the active task, and ready-to-run optimization actions Cco anatomy Generate a compact project map so Claude understands the codebase without opening every file Cco budget Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Claude 5 lineup, Opus 5.5 default fallback, full 1M context at standard price) Cco claudemd Analyze CLAUDE.md files for token bloat and suggest optimizations Cco clean Clean up old tracking data and reset statistics 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 Cco config View and tune CCO's behavior thresholds — re-read warnings, cache staleness, prompt-coach length bands, and the /cco-pack budget cap Cco digest Show weekly/daily efficiency digest with score and trends Cco doctor Health check for the context-optimizer plugin install — verifies versions, hooks, data dir, model config, and reports any issues Cco export Export context report as Markdown or HTML Cco git Show git-aware context suggestions for current working directory Cco overhead Audit the fixed context overhead every session starts with — system prompt, MCP tools, agents, CLAUDE.md, memory — measured from real transcript usage Cco pack Build an optimal context pack for the user's task — ranked file list with offset/limit suggestions, based on git state, mentioned paths, and historical patterns Cco patterns Share learned file patterns across a team — export an anonymized digest of what's usually waste/useful/co-edited, and import a teammate's so a fresh clone benefits day one Cco replay Show recent session summaries for quick context recovery Cco report Show detailed token ROI report across all tracked sessions Cco roi Calculate monthly token savings and ROI by model Cco shield Show ContextShield status and waste protection stats; suggest or apply .contextignore rules from historical waste Cco task Organize work by task, track tokens/cost per task, and keep a small patchable execution state that is re-injected after /compact (SKILL.state-style) — start a task, patch its state, list tasks, or mar Cco templates Manage context templates for common task types Cco tools Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses Smart loader Automatically suggests optimal files to preload based on the user's task description and historical context patterns. 