agentleFS
matt82198matt82198/aesop/skills/fleet/SKILL.md

fleet

Skill2 starsChanged 31 days agoMITView on GitHub

One-shot fleet snapshot (agents, heartbeats, tracker lanes, orchestrator status).

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use loop, learn and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • HeshamFSSkill

    loop

    Run a command or check on a recurring interval

    Also in 4 projects that use this

  • genomewalkerSkill

    learn

    Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.

    Also in 3 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Run the fleet snapshot tool and parse the JSON output:

    line 13
  2. Very specific:

    All missing state files produce explicit unavailable: "<reason>" entries rather than crashing:

    line 38

“Common” is measured: kept by at least 6 in 10 of the 16 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

Fleet — Snapshot of live fleet state

One-line status summary for aesop fleet operations, showing active agents, daemon health, tracker backlog, and orchestrator phase.

Procedure

Run the fleet snapshot tool and parse the JSON output:

aesop fleet

Output format

JSON object with:

  • timestamp: ISO 8601 when snapshot was taken
  • aesop_root: Fleet root directory (from AESOP_ROOT env or process.cwd())
  • heartbeats: Object with watchdog and monitor pulse status
    • watchdog: age_seconds, status (OK/STALE/MISSING), threshold_seconds
    • monitor: age_seconds, status (OK/STALE/MISSING), threshold_seconds
  • agents: Array of active agents OR unavailable message
    • Each agent: id, project, status, age_s, hint, startedAt, lastActivity, runtimeSeconds, tokensUsed, taskLabel, promptFull
  • tracker: Tracker backlog counts by lane OR unavailable message
    • total_items: sum of all items
    • by_lane: object mapping lane names to counts
  • orchestrator: Current orchestrator status OR unavailable message
    • activity, phase, timestamp (from state/orchestrator-status.json)

Graceful degradation

All missing state files produce explicit unavailable: "<reason>" entries rather than crashing:

  • watchdog heartbeat missing → unavailable: "MISSING"
  • monitor heartbeat missing → unavailable: "MISSING"
  • dash-extra.mjs not found → agents: { unavailable: "dash-extra.mjs not found" }
  • tracker.json missing/malformed → tracker: { unavailable: "tracker.json not found or malformed" }
  • orchestrator-status.json missing → orchestrator: { unavailable: "orchestrator-status.json not found or malformed" }

Example output

{
  "timestamp": "2024-07-17T14:32:05.123Z",
  "aesop_root": "/path/to/aesop",
  "heartbeats": {
    "watchdog": {
      "age_seconds": 42,
      "status": "OK",
      "threshold_seconds": 300
    },
    "monitor": {
      "age_seconds": 1203,
      "status": "OK",
      "threshold_seconds": 3600
    }
  },
  "agents": {
    "count": 2,
    "agents": [
      {
        "id": "a1b2c3d4e5f6g7h",
        "project": "aesop",
        "status": "running",
        "age_s": 35,
        "hint": "Implement /fleet CLI feature",
        "startedAt": "2024-07-17T14:31:30Z",
        "lastActivity": "2024-07-17T14:32:05Z",
        "runtimeSeconds": 35,
        "tokensUsed": 45000,
        "taskLabel": "FEATURE — fleet skill CLI part",
        "promptFull": "..."
      }
    ]
  },
  "tracker": {
    "total_items": 8,
    "by_lane": {
      "ranked": 3,
      "in-progress": 2,
      "proposed": 3
    }
  },
  "orchestrator": {
    "activity": "dispatching",
    "phase": "wave-14",
    "timestamp": "2024-07-17T14:32:00Z"
  }
}

Integration with orchestrators

Orchestrators invoke aesop fleet (instead of ad-hoc state reads) to stay coupled to this canonical format. All data is read-only; the command never mutates state.

Machine-readable parsing

Parse the JSON and check for unavailable fields at each level:

const fleet = JSON.parse(output);
if (fleet.heartbeats.watchdog.unavailable) {
  console.log('Watchdog is', fleet.heartbeats.watchdog.unavailable);
} else {
  console.log('Watchdog is', fleet.heartbeats.watchdog.status, 'age', fleet.heartbeats.watchdog.age_seconds + 's');
}

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.