agent-swarm-economics
Skill1 starsChanged 4 months agoNo licenceView on GitHub
Two modes. ADVISE — architecture and cost-optimization guidance for multi-agent / subagent systems, distilled from Cursor's agent-swarm model-economics research (July 2026); use whenever the user is designing, building, reviewing, or debugging any multi-agent setup, or asks which model to use for which agent role, how to cut multi-agent costs, why agents conflict or churn, or how to scale agent parallelism. EXECUTE — actually run the planner/worker split on the current task: plan with a strong model, delegate code-writing to cheaper worker subagents; use whenever the user asks to "swarm this", "plan with X and code with Y", "use cheap workers", "delegate to haiku", or hands over a large decomposable coding task and wants it done cost-efficiently. Also trigger on mentions of "swarm", "orchestrator", "subagent strategy", "agent economics", or "cheap model vs frontier model", even without the word "multi-agent". Users can pass planner=<model> and worker=<model> options.
In this repository5 other files it gives its agents.
- code-as-promptSkill
- explain-diff-htmlSkill
- onboard-agentSkill
- token-saverSkill
- video-briefSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.