agentleFS
mahsumaktasmahsumaktas/agent-evolution-kit/skills/orchestrator-loop/SKILL.md

orchestrator-loop

Skill2 starsChanged 9 months agoMITView on GitHub

Orchestration pipeline for development tasks. The orchestrator delegates everything and never writes code directly.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If context is already clear --> SKIP (e.g., user provided file paths and explicit instructions)

    line 21
  2. Very specific:

    If context is missing --> delegate via bridge.sh --research "..." or a research subagent

    line 22
  3. Distinctive:

    HARD-GATE: No implementation without approval.

    line 29
  4. Distinctive:

    Check: spec compliance + code quality + tests

    line 41
  5. Distinctive:

    If it does not pass after 3 iterations --> escalate to the user.

    line 42
  6. Distinctive:

    Use the shortcut flow when ALL of the following are true:

    line 56

≈ “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

Orchestrator Loop

The orchestrator DOES NOT WRITE CODE. This pipeline defines how the orchestrator delegates tasks.

Pipeline

RESEARCH --> PLAN --> IMPLEMENT --> REVIEW --> REPORT
    |          |        |            |          |
 delegate   orchestr.  delegate    delegate   orchestr.
(bridge.sh) (approve)  (spawn)    (spawn)   (report)

Step 1 -- RESEARCH (Gather Context)

  • If context is already clear --> SKIP (e.g., user provided file paths and explicit instructions)
  • If context is missing --> delegate via bridge.sh --research "..." or a research subagent
  • Output: Summary of current state + relevant files + risks

Step 2 -- PLAN (Design + Approval)

  • Large work (multi-file, architectural decisions): invoke the structured-brainstorming skill --> get user approval
  • Small work (single file, clear instructions): orchestrator writes a short summary --> get user approval
  • HARD-GATE: No implementation without approval. Do not proceed to Step 3 until the user says "go".

Step 3 -- IMPLEMENT (Delegate)

  • Invoke the subagent-execution skill --> spawn subagents for each task
  • The orchestrator only WATCHES: answers subagent questions, redirects if stuck
  • The orchestrator DOES NOT WRITE: creating/editing files directly is forbidden
  • Alternative for simple tasks: delegate via bridge.sh --code "..." to a coding subagent

Step 4 -- REVIEW (Verify)

  • Invoke the verification-gate skill
  • Check: spec compliance + code quality + tests
  • If it does not pass after 3 iterations --> escalate to the user; do NOT try to fix it yourself

Step 5 -- REPORT (Present to User)

The orchestrator reports:

  1. What was done (changed files + summary)
  2. What was skipped and why
  3. What requires human review
  4. Known limitations, if any

Shortcut Flow

Use the shortcut flow when ALL of the following are true:

  • Single file change
  • Less than 20 lines changed
  • Low risk (does not touch a working system)
  • Clear instructions (what to do is unambiguous)

Shortcut pipeline:

  1. Orchestrator writes a short summary --> gets user approval
  2. Delegates to a single coding subagent via bridge.sh --code "..."
  3. Verifies the result (read file + run)
  4. Reports

Red Flags

If the orchestrator is thinking...Reality
"This is simple, I will do it myself"NO. Simplicity does not change the rules. Delegate.
"Just one line"Size does not matter. Writing directly is forbidden.
"Spawning a subagent is slow"Doing it right > doing it fast.
"The pipeline is overkill"Use the shortcut flow, but do NOT skip the pipeline.
"I already know the answer"Knowing is not writing. Delegate.

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.