agentleFS
bakhod1rbakhod1r/awesome-agents/.claude/skills/delegation-protocol/SKILL.md

delegation-protocol

Skill0 starsChanged 3 months agoMITView on GitHub

How to route work across teams and agents in this repository. Use when a task spans more than one domain, when you are unsure which agent owns it, or before fanning out to several agents.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    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
  1. Distinctive:

    Never skip a link. Implementation with no design decision produces rework.

    line 12
  2. Distinctive:

    Gather the declared Inputs: before delegating. An agent without its inputs guesses, and a confident guess is worse than an admitted gap.

    line 20

“Common” is measured: kept by at least 6 in 10 of the 4 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.

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

Delegation Protocol

The chain

Architect decides. Engineer implements. Quality verifies. Release ships.

Never skip a link. Implementation with no design decision produces rework. A release with no verification produces an incident. Both cost more than the link you skipped.

Routing procedure

  1. Name the domain in one sentence. If you need two sentences, it is two tasks — split first.
  2. Find the owner in .claude/teams/README.md.
  3. Pick the minimum set. One agent per distinct concern. Not one per file, not one per idea.
  4. Gather the declared Inputs before delegating. An agent without its inputs guesses, and a confident guess is worse than an admitted gap.
  5. Delegate with context, not with the user's raw prompt. State what was already decided, what is out of scope, and what you want back.
  6. Reconcile. Where two agents disagree, do not average them. State the disagreement explicitly and escalate to the team's architect with both positions.

Fan-out budget

TaskAgentsWhy
One file, obvious fix0 — do it inlineDelegation costs more than the fix
One feature, one domain1-2Implementer, then reviewer
Cross-domain feature3-4, one per domainAny more and they overlap
System designArchitects first, implementers in a second passDesign before build, always

More than four agents on one task means the task is not decomposed yet. Decompose it.

Worked example

"Our checkout times out under Black Friday load and we lose orders."

Wrong: spawn eight agents — backend, database, SRE, performance, QA, security, PM, release — and merge eight overlapping reports.

Right — sequential, each gated on the previous:

1. performance-test-engineer   → where does it actually break?
   Returns: "p99 8.2s at 400 rps; DB connection pool saturated at 200 rps, not CPU."

   → Everything below is now scoped by that finding. Without it, the rest is guesswork.

2. database-architect          → pool sizing, connection strategy, read replica options
   backend-architect           → idempotency so retries do not double-charge
   (parallel — different concerns, same evidence)

3. backend-developer           → implements the agreed design
   database-engineer           → pool config and index changes

4. code-reviewer               → correctness of the retry path
   reliability-test-engineer   → verify it degrades instead of collapsing

5. release-manager             → canary with abort criteria tied to p99

Five stages, nine agents total, but never more than two at once, and each stage gets real inputs from the last. Step 1 alone eliminated four wrong directions.

Anti-patterns

Anti-patternWhat goes wrong
Spawning five agents to answer one questionFive overlapping reports, no decision, high cost
Delegating without declared inputsAgent invents plausible numbers; you cannot tell
Skipping the architect on an irreversible decisionRework at 10x the cost, three weeks later
Accepting output without checking evidenceYou inherited a hallucination and now own it
Forwarding the user's raw prompt to the agentAgent re-derives context you already have
Parallel agents on the same concernThey contradict; you arbitrate with no basis

Done when

  • The owning team is named and justified in one line.
  • Each delegated agent received its declared Inputs.
  • No two agents were given the same concern.
  • Contradictions between agents are stated, not silently averaged.
  • Every claim in the merged result traces to an agent's evidence, not to your summary of it.

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.