token-optimizer
SolidAudit your OpenClaw setup for token waste, context bloat, and cost optimization opportunities
Install
Quality Score: 81/100
Skill Content
Details
- Author
- alexgreensh
- Repository
- alexgreensh/token-optimizer
- Created
- 6 months ago
- Last Updated
- yesterday
- Language
- Python
- License
- NOASSERTION
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
token-optimiser
Deliver any task at the lowest token cost that still clears the quality bar. Opens with a fast triage that scores the request and recommends which Claude model to run it on, with a one-action switch line, then executes on a tool and output budget matched to that tier. Use this skill on virtually every substantive task — research, coding, analysis, document creation, agent pipelines, multi-step workflows — and especially when the user says 'token efficient', 'which model should I use', 'reduce my API costs', 'this is burning tokens', 'cheap', 'quick', or gives a terse instruction. Also use it when designing or reviewing anything that calls the Claude API or runs an agent loop, because routing, caching and batching decisions are cheapest to make at design time.
token-coach
Plan a token-efficient Claude Code or Codex setup, or get a quick health check. Coaching, not the full audit (use token-optimizer for that).
token-optimizer
Cut wasted tokens on every Claude interaction. Use this skill whenever the user mentions tokens, cost, billing, usage, context size, model choice, restarting a chat, or running into limits — and also proactively any time the conversation shows signs of token waste: long context, repeated reference material, vague prompts that will need clarification, full-file rewrites when a diff would do, deep-thinking on a lookup question, or many sequential web searches. Apply this skill across claude.ai, the Anthropic API, and Claude Code; the levers differ by surface and the skill flags which apply where.