By alexgreensh
Audits Claude Code context window usage, detects token waste from idle processes, config bloat, and model misrouting, and recovers 5-25%+ of tokens through automated cleanup, compaction, and session monitoring.
Audit token waste across agent systems (Claude Code, Codex, OpenClaw, Hermes, OpenCode). Detect idle burns, model misrouting, and config bloat with dollar savings.
Context window coach analyzing setup overhead, historical usage trends, and session habits. Use when building something new and wanting token efficiency from the start, existing sessions feel sluggish or context fills too fast, designing multi-agent systems, or wanting a quick health check with real numbers. Do NOT use for running the full audit and applying fixes (use /token-optimizer instead).
Open the Token Optimizer dashboard. Collects latest session data, regenerates the dashboard, and opens it in your browser.
Find the ghost tokens. Audit Claude Code or Codex setup, see where context goes, fix it. Use when context feels tight.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub alexgreensh/token-optimizer --plugin token-optimizerOffline security scanner for AI-agent repos, skills, plugins, and MCP servers
Delegate the grind, keep the glory. Offload grunt work to a cheaper or different engine (OpenRouter, Codex, keyless Gemini) while Claude orchestrates, or pull a stronger model in as an advisor. Per-model prompting, image gen, consensus second opinions, cost Tab.
Opus 4.8-aware context optimization: cache-aware real costs & cache-break detection, session baseline audit (/cco-overhead), auto .contextignore, self-calibrating estimates, delegation advisor, ru/en prompt coach
Evaluate and optimize .claude/ directory token efficiency. Reduce cost, improve response quality.
Resource optimization and performance monitoring toolkit for efficient Claude Code workflows
Analyze and reduce Claude Code token overhead
Token/cost meter + context-compaction proxy companion for Claude Code. Ships a lightweight metering hook that logs tool I/O sizes to ~/.tokdiet; the FULL token-saving proxy runs via `npx tokdiet start` + ANTHROPIC_BASE_URL (a plugin cannot set env vars for the Claude Code process).
Session intelligence for Claude Code — find why your sessions fail and fix them