Context Control Center — one screen for budget, $ spent, tokens saved, waste, last prompt grade, the active task, and ready-to-run optimization actions
Install
npx skillscat add egorfedorov/claude-context-optimizer/cco Install via the SkillsCat registry.
Here's a thinking process: 1. **Analyze the Request:** - **Goal:** Write a 2-3 sentence plain-text summary in English - **Subject:** An AI agent skill called "Context Control Center" (cco) - **Source material:** Provided description and SKILL.md excerpt - **Constraints:** - Objective, factual tone only - No marketing language, no superlatives, no calls to action - Natural prose, no bullet points, no headings, no markdown formatting - Do not wrap the answer in quotes - At most 60 words - **Output:** ONLY the summary text 2.
Context Control Center
The all-in-one view of the current session. Show the user the live board, then
the per-file heatmap if they want detail.
1. Show the board
node ${CLAUDE_PLUGIN_ROOT}/src/dashboard.js boardThis renders, in one screen:
- Budget — % of the effective context window used + $ spent this session
- Saved — tokens the Read Cache blocked → the effectiveness multiplier (e.g. "1.4x")
- Waste — cold context (read but never edited) you can drop to free budget
- Prompt — grade of the last prompt (from Prompt Coach)
- Task — the active task and its token/$ cost (per-task attribution)
- Actions — concrete next steps: what to drop →
/compact, what to/cco-pack
Present the board as-is. Then, based on what it shows:
- If an action line suggests dropping cold files, offer to run
/compact. - If no task is active, suggest
/cco-task add "<what they're working on>"so
the board can attribute tokens per task. - If the prompt grade is low (C/D/F), suggest
/cco-coach.
2. (Optional) per-file heatmap
If the user wants the file-by-file breakdown:
node ${CLAUDE_PLUGIN_ROOT}/src/tracker.js heatmapHighlight files read but never used (waste), files that were edited (high-value),
and the total token usage / waste percentage.
If there is no data yet, tell the user:
"No data in this session yet — keep working. Reads, edits, prompts and cache
savings are tracked automatically; run /cco again to see the board fill in."