Token efficiency router
Skill w3rdist-creator/agent-intelligence-economy/skills/token-efficiency-router
Route context, tools, and reports by usefulness per token and review burden.From its SKILL.md
npx -y skills add w3rdist-creator/agent-intelligence-economy --skill token-efficiency-routerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
0.6 KB, 103 tokens by cl100k_base, as published. Nobody here has run it
Token Efficiency Router
Use when a workflow is large, recurring, expensive, or chat-heavy.
Rules:
- Start with the smallest router skill or source map.
- Load detailed references only when needed.
- Use hash logs and compact maps before raw full reads.
- Put full evidence in files; send compact summaries to chat.
- Prefer deterministic scripts for repeated checks.
- Kill or merge loops that do not change decisions/artifacts.
- Optimize by mode/profile/job, not by globally weakening the agent.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.