starlight-queen-queue
Skill0 starsChanged 3 months agoMITView on GitHub
Define bounded Starlight swarm queue jobs, queen/worker lanes, handoff packets, safety gates, and validation evidence for multi-agent or cross-repo work. Use when a user asks for a swarm, council, fanout, queen queue, multi-agent execution, long-running agent wave, context-preserving handoff, or Starlight automation operating model.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- automation-tool-routerSkill
- codex-automation-operatorSkill
- make-com-operationsSkill
- mcp-governanceSkill
- n8n-operationsSkill
- starlight-excellenceSkill
- xquik-public-x-dataSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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 8
Use a Starlight queue when one linear automation is the wrong shape and work needs bounded multi-agent execution with a synthesis owner.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Starlight Queen Queue
Use a Starlight queue when one linear automation is the wrong shape and work needs bounded multi-agent execution with a synthesis owner.
Queue Job Contract
Every job needs:
- objective
- repo or workspace
- source context
- worker lanes
- allowed tools
- write scopes
- stop condition
- validation evidence
- risk gates
- handoff format
Lane Types
- Doctrine lane: decision rules, docs, memory.
- Build lane: code, repo, plugin, skill changes.
- Safety lane: secrets, private/public split, policy gates.
- Verification lane: tests, validation scripts, release checks.
- Synthesis lane: final decision and user handoff.
Safety Spine
- One coordinator owns the final risk call.
- Workers do not revert each other's changes.
- Public releases pass a private-memory and secret scan.
- Human approval is required for irreversible external actions.
- Payments and spend actions are verify-only unless the human explicitly approves.
Handoff Format
Return:
- swarm objective
- worker lanes
- context packet
- execution waves
- validation evidence
- risks
- next handoff
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.

