fleet-runs — Claude Code skill: Workflow fleet monitoring
fleet-runs — a skill for Claude Code and Codex that reads Workflow fleet run journals from the Agent Monitor and displays run status with per-agent breakdown.
MIT ★ 1,198 updated 2026-10-23
/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor
/plugin install ccam-workflows@claude-code-agent-monitor-pluginsWhat fleet-runs does
Fleet-runs summarises Workflow fleet runs that don't generate hooks—data comes from on-disk journals instead. The skill offers two modes: list recent runs with agent counts and status, or drill into one run in detail. Each agent shows its type, duration, status, and error notes.
Data comes from four API endpoints: fleet list with timing, one run in detail, live fleet state, and individual agent state. The skill reconciles journals against live state, flagging any drift. If the Dashboard is unreachable, start it with npm start from the repo root.
Duration displays in readable units (e.g. 3m 04s). The skill reports only runs and agents returned by the API. If no fleet runs exist, it says so plainly.
What it helps with
- see all agent statuses in a Workflow fleet at once
- find which agent is running longest and diagnose why
- verify fleet journals match the live run-state API
- troubleshoot errors in batch runs without hooks
Example prompts for the agent
- Show me the recent fleet runs
- Drill into run
run-2024-11-15-001— which agents failed - What was the status of the last run, with timing per agent
How to install fleet-runs
1Plugin marketplace
/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor/plugin install ccam-workflows@claude-code-agent-monitor-pluginsThis installs the whole ccam-workflows plugin with all its skills
2Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill fleet-runs -a claude-code3Manually: put the files in place
~/.claude/skills/fleet-runs/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/fleet-runs/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill fleet-runs -a codex2Manually: put the files in place
.agents/skills/fleet-runs/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill fleet-runs -a cursor2Manually: put the files in place
.cursor/skills/fleet-runs/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install hoangsonww/Claude-Code-Agent-Monitor plugins/ccam-workflows/skills/fleet-runs2Manually: put the files in place
.github/skills/fleet-runs/SKILL.md1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill fleet-runs -a gemini-cli2Platform CLI
gemini skills install https://github.com/hoangsonww/Claude-Code-Agent-Monitor --path plugins/ccam-workflows/skills/fleet-runsManually: put the files in place
.devin/skills/fleet-runs/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about fleet-runs
How do I install fleet-runs in Claude Code?
Run in order: /plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor, then /plugin install ccam-workflows@claude-code-agent-monitor-plugins, then npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill fleet-runs -a claude-code. The skill will be at ~/.claude/skills/fleet-runs/SKILL.md.
What does fleet-runs do?
It reads Workflow fleet run journals from Agent Monitor (the ones without hooks), lists recent runs or shows details for a single run broken down by agent. Each agent record includes type, status, duration, and errors if any.
Why check journals if there's a live API?
Workflow() fleets don't emit hooks, so data lives only in disk journals. The skill compares journals to live state to catch any inconsistencies.
Source text
SKILL.md · MIT
---
name: fleet-runs
description: >
Summarize Workflow-tool fleet runs from the Agent Monitor — these fleets emit
no hooks and are ingested from on-disk run journals. List recent runs with
status and agents-per-run, then drill into a single run's per-agent detail.
Reconciles against the live run-state endpoints. Use when reviewing Workflow()
fleets rather than hook-instrumented interactive sessions.
---
# Fleet Runs
Summarize Workflow-tool (Workflow()) fleet runs and drill into one run's agents.
## Input
The user provides: **$ARGUMENTS**
- Empty → list the most recent fleet runs.
- A run ID → drill into that single run.
- `latest` → drill into the most recent run.
These fleets emit **no hooks**; the dashboard ingests them from on-disk Workflow-tool run journals, so this data is independent of the hook event stream.
## Data Sources
| Endpoint | Returns |
|----------|---------|
| `GET /api/workflows/runs` | List of ingested fleet run journals: run id, status, agent count, timing |
| `GET /api/workflows/runs/{runId}` | One run in detail: per-agent status, timing, type, and outputs |
| `GET /api/run` | Live run state across the fleet (current/active runs) |
| `GET /api/run/{id}` | Live state for one run, to reconcile against the journal |
## Report Sections
### 1. Runs Overview (when listing)
| Run ID | Status | Agents | Started | Duration |
|--------|--------|--------|---------|----------|
Sort most recent first. Add a one-line status mix below (e.g. `8 runs: 5 completed, 2 running, 1 error`).
### 2. Run Detail (when a run ID / `latest` is given)
From `GET /api/workflows/runs/{runId}`, reconciled with `GET /api/run/{id}`:
- Header: run id, status, total agents, wall-clock duration.
- Per-agent table:
| Agent | Type | Status | Duration | Notes |
|-------|------|--------|----------|-------|
- Call out the longest-running agent and any agent with an error/failed status.
### 3. Status & Health
Completion rate (completed / total agents), any stalled or errored agents, and whether the journal and the live run-state endpoint agree (flag drift if they do not).
## Output
- Markdown tables; status mix as a single summary line.
- Durations in human units (e.g. `3m 04s`).
- Make explicit that these runs come from run journals (no hooks), so hook-derived metrics do not apply.
- Cite only runs and agents returned by the API; never invent runs.
- If there are no fleet runs, say so plainly.
- If the dashboard is unreachable, tell the user to start it with `npm start` from the repo root.
© Son Nguyen · MIT · hoangsonww/Claude-Code-Agent-Monitor