egorfedorov/claude-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.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ npx degit egorfedorov/claude-context-optimizer/agents ./rig-claude-context-optimizer/agents $ npx degit egorfedorov/claude-context-optimizer/skills ./rig-claude-context-optimizer/skills $ npx degit egorfedorov/claude-context-optimizer/hooks ./rig-claude-context-optimizer/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit egorfedorov/claude-context-optimizer/skills/cco-anatomy .claude/skills/cco-anatomy $ npx degit egorfedorov/claude-context-optimizer/skills/cco-budget .claude/skills/cco-budget $ npx degit egorfedorov/claude-context-optimizer/skills/cco-claudemd .claude/skills/cco-claudemd $ npx degit egorfedorov/claude-context-optimizer/skills/cco-clean .claude/skills/cco-clean $ npx degit egorfedorov/claude-context-optimizer/skills/cco-coach .claude/skills/cco-coach $ npx degit egorfedorov/claude-context-optimizer/skills/cco-config .claude/skills/cco-config $ npx degit egorfedorov/claude-context-optimizer/skills/cco-digest .claude/skills/cco-digest $ npx degit egorfedorov/claude-context-optimizer/skills/cco-doctor .claude/skills/cco-doctor $ npx degit egorfedorov/claude-context-optimizer/skills/cco-export .claude/skills/cco-export $ npx degit egorfedorov/claude-context-optimizer/skills/cco-git .claude/skills/cco-git $ npx degit egorfedorov/claude-context-optimizer/skills/cco-overhead .claude/skills/cco-overhead $ npx degit egorfedorov/claude-context-optimizer/skills/cco-pack .claude/skills/cco-pack $ npx degit egorfedorov/claude-context-optimizer/skills/cco-patterns .claude/skills/cco-patterns $ npx degit egorfedorov/claude-context-optimizer/skills/cco-replay .claude/skills/cco-replay $ npx degit egorfedorov/claude-context-optimizer/skills/cco-report .claude/skills/cco-report $ npx degit egorfedorov/claude-context-optimizer/skills/cco-roi .claude/skills/cco-roi $ npx degit egorfedorov/claude-context-optimizer/skills/cco-shield .claude/skills/cco-shield $ npx degit egorfedorov/claude-context-optimizer/skills/cco-task .claude/skills/cco-task $ npx degit egorfedorov/claude-context-optimizer/skills/cco-templates .claude/skills/cco-templates $ npx degit egorfedorov/claude-context-optimizer/skills/cco-tools .claude/skills/cco-tools $ npx degit egorfedorov/claude-context-optimizer/skills/cco .claude/skills/cco $ npx degit egorfedorov/claude-context-optimizer/skills/smart-loader .claude/skills/smart-loader
$ curl -fsSL --create-dirs -o .claude/agents/context-analyzer.md https://raw.githubusercontent.com/egorfedorov/claude-context-optimizer/main/agents/context-analyzer.md This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (22)
cco-anatomycco-budgetcco-claudemdcco-cleancco-coachcco-configcco-digestcco-doctorcco-exportcco-gitcco-overheadcco-packcco-patternscco-replaycco-reportcco-roicco-shieldcco-taskcco-templatescco-toolsccosmart-loader
Subagents (1)
| context-analyzer | Analyzes context usage patterns, identifies waste, and provides optimization recommendations. Use when the user asks about token usage, context efficiency, or wants to optimize their Claude Code workf |
Similar rigs
ammonkc/dotfiles
.dotfiles, including macos.sh script — sensible hacker defaults for macOS
MCP Hoarder 26.3k tok ·
obra/superpowers
An agentic skills framework & software development methodology that works.
Skill Collector 3.0k tok ·
anthropics/skills
Public repository for Agent Skills
Skill Collector 1.3k tok ·
anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Skill Collector 1.4k tok ·