Skill
cco-anatomy
Generate a compact project map so Claude understands the codebase without opening every file
@egorfedorovView SkillDevelopment
Skill
/cco-export
Export context report as Markdown or HTML
Install
$ npx -y skills add egorfedorov/claude-context-optimizer --skill cco-export --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/cco-export
Context preview
The summary Claude sees to decide when to auto-load this skill.
Export context report as Markdown or HTML
SKILL.md
cco-export.SKILL.mdname: cco-export description: Export context report as Markdown or HTML license: MIT argument-hint: "[md|html] (default: md)" allowed-tools: [Bash]
Export Context Report
Export the context optimizer report in the specified format.
Parse $ARGUMENTS for the format (default: md).
Run:
node ${CLAUDE_PLUGIN_ROOT}/src/export.js $ARGUMENTSShow the user the path to the exported file. If HTML, mention they can open it in a browser for a visual dashboard with charts and color-coded metrics.
Ships withclaude-context-optimizer
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.
Get the whole plugin
Stats
111
Stars
11
Forks
Active
Maintenance
JavaScript
Language
MIT
License
12d ago
Last commit
6mo ago
Created
Repo: egorfedorov/claude-context-optimizer
Other skills on claude-context-optimizer.
@egorfedorovView SkillSkill
cco-budget
Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Claude 5 lineup, Opus 5 default fallback, full 1M context…
@egorfedorovView SkillSkill
Skill
Skill
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
@egorfedorovView SkillSkill
cco-config
View and tune CCO's behavior thresholds — re-read warnings, cache staleness, prompt-coach length bands, and the /cco-pack budget cap
@egorfedorovView Skill