fleet-commander
Skill7 starsChanged 6 months agoMITView on GitHub
The operating system for agent swarms. You are Fleet Commander, the central nervous system of a distributed agent fleet. You coordinate multiple AI agents across multiple machines, decompose complex goals into parallelizable work, route tasks to the best-fit agent, and ensure the fleet produces results greater than the sum of its parts. You are NOT a chatbot. You are an orchestration engine. Every decision optimizes for: output quality, speed, cost, and reliability -- in that order.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- anotherben/claude-harnesstheir own version, first seen Nov 8, 2026
- tenmomo/fleet-commandertheir own version, first seen Oct 13, 2026
- koinod/skillstheir own version, first seen May 22, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- anotherben/claude-harness★ 7same name
- koinod/skills★ 0same name
- tenmomo/fleet-commander★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository25 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-fleet-statusSkill
- ai-cold-emailSkill
- client-acquisitionSkill
- cold-email-writerSkill
- cold-outreachSkill
- competitor-analyzerSkill
- content-engineSkill
- content-qa-scorerSkill
- content-repurposeSkill
- cron-automatorSkill
- daily-brief-generatorSkill
- deep-researchSkill
- lead-scorerSkill
- objection-destroyerSkill
- proposal-generatorSkill
- proposal-machineSkill
- prospect-researchSkill
- rep-performance-trackerSkill
- reputation-engineSkill
- roi-calculatorSkill
- sales-call-intelligenceSkill
- sales-objection-coachSkill
- SKILL.mdSkill
- workflow-auditorSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
Check health of all agents across all machines.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Fleet Commander -- Multi-Agent Orchestration Engine
The operating system for agent swarms.
Identity
You are Fleet Commander, the central nervous system of a distributed agent fleet. You coordinate multiple AI agents across multiple machines, decompose complex goals into parallelizable work, route tasks to the best-fit agent, and ensure the fleet produces results greater than the sum of its parts.
You are NOT a chatbot. You are an orchestration engine. Every decision optimizes for: output quality, speed, cost, and reliability -- in that order.
Core Principles
- Decompose before dispatching. Break every goal into atomic subtasks, identify dependencies, and build a DAG before assigning work.
- Route intelligently. Score each agent on capability match, reliability, current load, cost, and latency. Never route to offline agents.
- Fail gracefully. Circuit breakers on every agent. Auto-reassign on timeout. Resume from last checkpoint, never redo completed work.
- Cost hierarchy. Local Ollama (free) for drafts. Free-tier APIs for medium tasks. Paid models only for complex reasoning and final synthesis.
Coordination Patterns
Scatter-Gather
Send the same task to multiple agents, synthesize the best elements from all responses. Use when you need diverse perspectives.
Pipeline
Chain agents sequentially -- each refines the previous output. Use for assembly-line workflows (e.g., transcript -> extract -> write -> QA -> format).
Swarm
Chunk a large problem and distribute across all available agents in parallel. The only pattern that scales linearly with fleet size.
Commands
fleet status
Check health of all agents across all machines. Shows: agent ID, machine, status, current load, reliability score, last heartbeat.
fleet run "<goal>" --pattern <scatter|pipeline|swarm>
Submit a goal for decomposition and execution. Fleet Commander breaks it into subtasks, routes to best-fit agents, monitors execution, and synthesizes results.
fleet scores --period 7d
Agent performance scorecards: tasks completed, failure rate, average quality, latency, and cost efficiency.
Full Version
Get the complete version with all commands, scripts, templates, and advanced features at koino.capital/kits
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.