agentleFS
fagemxfagemx/edda/.claude/skills/coord-sync/SKILL.md

coord-sync

Skill36 starsChanged 2 months agoApache-2.0View on GitHub

Sync with peers before starting multi-agent work — see claims, recorded decisions, suggest scope

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After seeing "Peers Working On" in context and wanting full picture

    line 13
  2. Distinctive:

    When unsure what scope is safe to work in

    line 14
  3. Very specific:

    Run edda peers to see active sessions and their labels.

    line 20
  4. Distinctive:

    If no peers are active, report "Solo session — no coordination needed" and exit.

    line 22
  5. Very specific:

    Run edda coord to get the full coordination protocol view including:

    line 26
  6. Distinctive:

    Use a descriptive label (crate name, module name, or feature area)

    line 48
  7. Distinctive:

    If auto-claim already set a scope from your edits, show it and ask if manual override is needed

    line 50
  8. Distinctive:

    Read the message and assess if you can handle it

    line 55
  9. Distinctive:

    If not now: note it as deferred

    line 57

≈ “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

Coordination Sync

You are a coordination specialist. Your role is to help the agent understand the current multi-agent landscape and claim an appropriate scope before starting work.

When to Use

  • Starting a new task in a multi-agent session
  • After seeing "Peers Working On" in context and wanting full picture
  • When unsure what scope is safe to work in

Workflow

Step 1: Discover Peers

Run edda peers to see active sessions and their labels.

If no peers are active, report "Solo session — no coordination needed" and exit.

Step 2: Read Board State

Run edda coord to get the full coordination protocol view including:

  • Peer claims (scope ownership)
  • Recorded decisions (coordination broadcasts — agent-authored, not binding until an operator ratifies them via edda ratify)
  • Pending requests

Step 3: Analyze Scope

From the board state, identify:

  • Off-limits areas: Paths claimed by other agents — do NOT edit these
  • Recorded decisions: coordination broadcasts to be aware of — agent-authored and not binding until operator-ratified (do not treat them as hard constraints)
  • Pending requests for you: Messages from peers requiring your attention
  • Unclaimed areas: Safe zones related to your current task

Step 4: Claim Scope

Based on your current task/issue, suggest a claim:

edda claim "<label>" --paths "<path1>" --paths "<path2>"

Guidelines:

  • Use a descriptive label (crate name, module name, or feature area)
  • Paths should use glob patterns (e.g., crates/edda-store/*)
  • If auto-claim already set a scope from your edits, show it and ask if manual override is needed

Step 5: Acknowledge Requests

For each pending request addressed to your label:

  • Read the message and assess if you can handle it
  • If yes: edda request-ack <from-label>
  • If not now: note it as deferred

Output Format

Present findings in this structure:

## Coordination Sync

### Active Peers (N)
- [label] (Xs ago): working on <tasks>, branch: <branch>

### My Scope
- Claimed: <label> → <paths>
- Off-limits: <peer claims listed>

### Recorded Decisions (coordination — not binding until ratified)
- <key> = <value> (by <label>)

### Pending Requests for Me
- From <label>: <message> → [acknowledged / deferred]

### Ready to Start
<summary of what you can safely work on without conflicting with peers>

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.