runs — Claude Code command: what it does, how to install
Pulls recent Workflow-tool fleet runs from the local Agent Monitor and prints a status summary plus a compact table of the latest ones.
MIT ★ 1,198 updated 2026-10-23
/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor
/plugin install ccam-workflows@claude-code-agent-monitor-pluginsWhat runs does
The command reads run journals off the dashboard on http://localhost:4820 with one request: curl -s http://localhost:4820/api/workflows/runs. Each record carries a run id, status, agent count and timing. Output stays short: a single line mixing the statuses, then a table of the newest runs, freshest first.
Workflow-tool fleets send no hooks, so this data never passes through the hook event stream; the dashboard builds it from journals written to disk. The dashboard has to be up. When port 4820 does not answer, the command tells the user to run npm start from the repository root. Nothing else produces a list.
Only runs the API returns make it into the table, and an empty fleet list is reported as empty. For a per-agent breakdown of one run, the command hands off to the fleet-runs skill.
What it helps with
- see how many fleet runs are still in flight
- grab the run id of a failed run
- check agent counts across recent runs
- get a one-line status breakdown
- compare durations of the latest runs
Example prompts for the agent
- Show me the latest Workflow-tool fleet runs from Agent Monitor
- How many runs are still going? Give me the status mix
- Table the recent runs with agent counts and durations
How to install runs
1Plugin marketplace
/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor/plugin install ccam-workflows@claude-code-agent-monitor-plugins2Manually: put the files in place
.claude/commands/runs.mdCall it with /runs. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/runs.mdCall it with /prompts:runs. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/runs.prompt.mdManually: put the files in place
.gemini/commands/runs.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about runs
How do I install runs in Claude Code?
Add the marketplace with /plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor, then install the plugin: /plugin install ccam-workflows@claude-code-agent-monitor-plugins. The command file itself sits at .claude/commands/runs.md.
What does runs do?
It asks Agent Monitor for Workflow-tool fleet run journals and prints a status summary line plus a table of recent runs with id, status, agent count, start time and duration.
Why does the command return nothing?
The dashboard on http://localhost:4820 is probably down. Start it with npm start from the repository root and run the command again.
Source text
runs.md · MIT
--- description: List recent Workflow-tool fleet runs with status and agent counts. --- List recent Workflow-tool (Workflow()) fleet runs from the Agent Monitor at `http://localhost:4820`. These fleets emit **no hooks** — the dashboard ingests them from on-disk run journals, so this is independent of the hook event stream. If the dashboard is unreachable, tell the user to start it with `npm start` from the repo root. Fetch the run journals: ``` curl -s http://localhost:4820/api/workflows/runs ``` Each run has a run id, status, agent count, and timing. Print, concisely: 1. **Status mix** — one summary line, e.g. `8 runs: 5 completed, 2 running, 1 error`. 2. **Recent runs** — a compact table, most recent first: | Run ID | Status | Agents | Started | Duration | |--------|--------|--------|---------|----------| Keep it terse. Cite only runs returned by the API; never invent runs. If there are no fleet runs, say so. To drill into one run's per-agent detail, point the user at the `fleet-runs` skill.
© Son Nguyen · MIT · hoangsonww/Claude-Code-Agent-Monitor