agentleFS
Sign inStart free
moabualruzmoabualruz/fulcrum/skills/macro-subagent-orchestration/SKILL.md

macro-subagent-orchestration

Skill4 starsChanged 7 months agoMITView on GitHub

Use when orchestrating broad or multi-issue subagent work where agents, lanes, reviews, or PRs may become too small; use for CuraOS waves, owner-path bundles, local issue queues, many-agent execution, or requests to run more lanes without wasting work in micro PRs.

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
  1. Distinctive:

    If a lane has only one tiny file, one review nit, or one local child row, repack it unless it has a recorded split reason.

    line 35

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Macro Subagent Orchestration

Use this standalone skill for broad orchestration. It covers the macro versions of subagent selection, lane planning, worker dispatch, review loops, verification, and integration. Do not also load subagent-orchestration or subagent-driven-development for the same broad wave unless you are deliberately switching a single lane into a narrow micro task.

When to use

See references/when-to-use.md. Load this skill for broad orchestration, owner-path bundles, local issue queues, many-agent execution, or any request to increase lanes without repeating micro PR waste.

Invocation

See references/invocation.md. Before spawning agents, write a lane plan with:

  • Bundle id and parent issue.
  • Included local issue rows.
  • Owner path, checkout, target branch, and verification surface.
  • Expected PR scope.
  • Split reason for any tiny lane.
  • Parallel-safe proof for every lane scheduled together.

Patterns

See references/patterns.md. Core rule: lane size before lane count.

Local issue rows, checklist rows, and verification rows may stay small. Worker lanes and PRs should not. A macro lane bundles compatible work that one agent can own, test, review, and PR as a coherent deliverable.

Anti-patterns

See references/anti-patterns.md. Increasing agent count before packing compatible work repeats the Wave 0 failure mode.

If a lane has only one tiny file, one review nit, or one local child row, repack it unless it has a recorded split reason.

Cross-refs

This skill covers the macro-level cases from subagent-orchestration and subagent-driven-development. Do not load those micro skills for the same broad wave. Use them only after deliberately narrowing one lane into a small standalone task.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free