claude-context-optimizer

v4.10.0

Claude 5-aware context optimization (Fable 5.1 / Opus 5 / Sonnet 5 pricing, 1h-cache-aware real costs & cache-break detection), SKILL.state-style task state that survives /compact, session baseline audit (/cco-overhead), auto .contextignore, self-calibrating estimates, delegation advisor, ru/en prompt coach, per-language token estimation, tunable thresholds via /cco-config, self-learning tool costs, team pattern sharing

Claude Code22 Skills

By Egor FedorovLicense: MIT111 GitHub starsUpdated last week

Directory evidence

Runtimes: Claude Code
Parsed components: 22 skill or MCP entries
Source updated: Sep 15, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install claude-context-optimizer for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install claude-context-optimizer@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/egorfedorov/claude-context-optimizer

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

claude-context-optimizer/

├── .claude-plugin/plugin.json
├── skills/cco/SKILL.md
├── skills/cco-anatomy/SKILL.md
├── skills/cco-budget/SKILL.md
├── skills/cco-claudemd/SKILL.md
├── skills/cco-clean/SKILL.md
├── skills/cco-coach/SKILL.md
├── skills/cco-config/SKILL.md
├── skills/cco-digest/SKILL.md
├── skills/cco-doctor/SKILL.md
├── skills/cco-export/SKILL.md
├── skills/cco-git/SKILL.md
├── skills/cco-overhead/SKILL.md
├── skills/cco-pack/SKILL.md
├── skills/cco-patterns/SKILL.md
├── skills/cco-replay/SKILL.md
├── skills/cco-report/SKILL.md
├── skills/cco-roi/SKILL.md
├── skills/cco-shield/SKILL.md
├── skills/cco-task/SKILL.md
├── skills/cco-templates/SKILL.md
├── skills/cco-tools/SKILL.md
└── skills/smart-loader/SKILL.md

Included Skills22

ccoskills/cco/SKILL.md

Context Control Center — one screen for budget, $ spent, tokens saved, waste, last prompt grade, the active task, and ready-to-run optimization actions

cco-anatomyskills/cco-anatomy/SKILL.md

Generate a compact project map so Claude understands the codebase without opening every file

cco-budgetskills/cco-budget/SKILL.md

Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Claude 5 lineup, Opus 5 default fallback, full 1M context at standard price)

cco-claudemdskills/cco-claudemd/SKILL.md

Analyze CLAUDE.md files for token bloat and suggest optimizations

cco-cleanskills/cco-clean/SKILL.md

Clean up old tracking data and reset statistics

cco-coachskills/cco-coach/SKILL.md

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-configskills/cco-config/SKILL.md

View and tune CCO's behavior thresholds — re-read warnings, cache staleness, prompt-coach length bands, and the /cco-pack budget cap

cco-digestskills/cco-digest/SKILL.md

Show weekly/daily efficiency digest with score and trends

cco-doctorskills/cco-doctor/SKILL.md

Health check for the context-optimizer plugin install — verifies versions, hooks, data dir, model config, and reports any issues

cco-exportskills/cco-export/SKILL.md

Export context report as Markdown or HTML

cco-gitskills/cco-git/SKILL.md

Show git-aware context suggestions for current working directory

cco-overheadskills/cco-overhead/SKILL.md

Audit the fixed context overhead every session starts with — system prompt, MCP tools, agents, CLAUDE.md, memory — measured from real transcript usage

cco-packskills/cco-pack/SKILL.md

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-patternsskills/cco-patterns/SKILL.md

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-replayskills/cco-replay/SKILL.md

Show recent session summaries for quick context recovery

cco-reportskills/cco-report/SKILL.md

Show detailed token ROI report across all tracked sessions

cco-roiskills/cco-roi/SKILL.md

Calculate monthly token savings and ROI by model

cco-shieldskills/cco-shield/SKILL.md

Show ContextShield status and waste protection stats; suggest or apply .contextignore rules from historical waste

cco-taskskills/cco-task/SKILL.md

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 mark the active one done. Pairs with /cco-pack to load minimal context per task.

cco-templatesskills/cco-templates/SKILL.md

Manage context templates for common task types

cco-toolsskills/cco-tools/SKILL.md

Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses

smart-loaderskills/smart-loader/SKILL.md

Automatically suggests optimal files to preload based on the user's task description and historical context patterns. Activates when the user starts a new task, mentions reading files, or when session context is being set up.

Plugin manifests1

.claude-plugin/plugin.json

{
  "name": "claude-context-optimizer",
  "version": "4.10.0",
  "description": "Claude 5-aware context optimization (Fable 5.1 / Opus 5 / Sonnet 5 pricing, 1h-cache-aware real costs & cache-break detection), SKILL.state-style task state that survives /compact, session baseline audit (/cco-overhead), auto .contextignore, self-calibrating estimates, delegation advisor, ru/en prompt coach, per-language token estimation, tunable thresholds via /cco-config, self-learning tool costs, team pattern sharing",
  "author": {
    "name": "Egor Fedorov"
  },
  "repository": "https://github.com/egorfedorov/claude-context-optimizer",
  "license": "MIT",
  "keywords": [
    "claude-code",
    "claude-5",
    "claude-fable-5.1",
    "claude-opus-5",
    "context-optimization",
    "token-tracking",
    "prompt-engineering",
    "1m-context"
  ]
}