agentleFS
3orionkings3orionkings/forge/skills/forge-orchestrate/SKILL.md

forge-orchestrate

Skill0 starsChanged 19 days agoMITView on GitHub

Use when an approved plan contains multiple bounded units that need dependency ordering, isolated worktrees, or parallel execution. Use forge-build for one work order and forge when the plan is not yet approved. Do not use for trivial or single-system work where orchestration overhead exceeds the task.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. tonmoy007/forge-plugins★ 2same 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 repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Route first: Read ../forge/SKILL.md, resolve the active profile, and use ../forge/ENGINE.md for preflight before any launch.

    line 14
  2. Very specific:

    Before product execution, read ../forge/SKILL.md and the one selected file in ../forge/profiles/.

    line 35
  3. Distinctive:

    Don't hand-wave concurrency — the guard decides, per lane.

    line 49
  4. Distinctive:

    Don't restate Act-3/4 cadence here.

    line 50
  5. Very specific:

    Don't wait at Gate 2 under sprint — apply the overlay/default and record one line.

    line 51
  6. Very specific:

    Don't call a same-model subagent review cross-model (and under sprint there is no per-unit review at all).

    line 52

≈ “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.

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

FORGE-ORCHESTRATE — Split a Frozen Spec Across Models

Act 4 standalone: decompose an APPROVED spec into units, run independent ones concurrently in isolated worktrees, integrate in dependency order. For a single-track build use /forge-build; to plan first use /forge.

Unique to this skill

  1. Route first. Read ../forge/SKILL.md, resolve the active profile, and use ../forge/ENGINE.md for preflight before any launch. The steps below do not override that profile.
  2. Preconditions. Plan APPROVED; clean base tree. If the repo has a protocol (AGENTS.md / .ai/COLLAB_PROTOCOL.md), follow its branch/worktree naming.
  3. Decompose into the smallest units that each have a clear done-condition, a proof (declared targeted or broad), and a knowable file set. Classify each pair independent (disjoint files → may run in parallel) or dependent (shared files or ordering → serial). When unsure, serialize.
  4. Worktrees. One isolated worktree per concurrent unit; one writing agent per tree. To widen a unit's file set mid-flight, use one guarded re-admission (--admission-action expand) — same lane, no restart, still rejects overlap.
  5. Execute independent units together within the guard's caps.
  6. Integrate passing units in dependency order, then run the profile's validation. The driver merges and commits — never the executor.

Tunables: SPEC_FILE=PLAN.md · MAX_FIX_ROUNDS=2 · LOG_FILE=PLAN-REVIEW-LOG.md. Concurrency is the guard's, not this file's: three lanes total, one HEAVY lease.

Execution profile

Before product execution, read ../forge/SKILL.md and the one selected file in ../forge/profiles/. Those sources alone own cadence, review, proof, routing, and integration. Do not reconstruct or add ceremony here. Every lane still passes ../forge/dispatch-guard.sh.

Canonical references

../forge/ROUTING-POLICY.md (routing) · ../forge/profiles/ (cadence) · ../forge/ENGINE.md (engine, templates, admission) · ../forge/references/ (detail, on demand)

What NOT to do

  • Don't hand-wave concurrency — the guard decides, per lane.
  • Don't restate Act-3/4 cadence here; the profile owns it.
  • Don't wait at Gate 2 under sprint — apply the overlay/default and record one line.
  • Don't call a same-model subagent review cross-model (and under sprint there is no per-unit review at all).

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.