/triage
Launch a triage-mode agent team — diagnose an issue without changing it
> /plugin marketplace add DheerG/swarms > /plugin install swarm@swarms
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/triage
Context preview
What this command does when you run it.
Launch a triage-mode agent team — diagnose an issue without changing it
Command definition
triage.mddescription: Launch a triage-mode agent team — diagnose an issue without changing it
argument-hint: <issue to diagnose>
disable-model-invocation: true
/swarm:triage
Read `${CLAUDE_PLUGIN_ROOT}/commands/launch.md` and execute it in full — every step, in order — with these overrides:
- **Mode:** Triage, fixed. Skip mode inference and mode selection entirely; never ask about mode. If the user asks to change the mode at the Step 7 gate, say the mode is fixed for this command and point them to `/swarm:launch` (or the matching shortcut) — do not switch modes mid-command.
- **Outcomes question (Step 2):** "What do you want the team to diagnose? (Describe what you're seeing — the symptom, where it shows up, and any context. The team will identify the likely cause and the blast radius of fixing it, without making any change.)"
- **User-Provided Context:** the section below stands in for launch.md's `$ARGUMENTS` — launch.md's own context section is unsubstituted when read from disk.
**Triage changes nothing.** This mode diagnoses — it does not branch, commit, edit, or open a PR. The deliverable is a confidence-rated diagnosis presented in-session.
**No lead research unless enabled.** Unless the user explicitly enables lead research, do not read codebase files, spawn subagents, or perform research. Delegate all evidence-gathering to teammates.
User-Provided Context
$ARGUMENTS
Read more
description: Launch a triage-mode agent team — diagnose an issue without changing it argument-hint: <issue to diagnose> disable-model-invocation: true
/swarm:triage
Read `${CLAUDE_PLUGIN_ROOT}/commands/launch.md` and execute it in full — every step, in order — with these overrides:
- **Mode:** Triage, fixed. Skip mode inference and mode selection entirely; never ask about mode. If the user asks to change the mode at the Step 7 gate, say the mode is fixed for this command and point them to `/swarm:launch` (or the matching shortcut) — do not switch modes mid-command.
- **Outcomes question (Step 2):** "What do you want the team to diagnose? (Describe what you're seeing — the symptom, where it shows up, and any context. The team will identify the likely cause and the blast radius of fixing it, without making any change.)"
- **User-Provided Context:** the section below stands in for launch.md's `$ARGUMENTS` — launch.md's own context section is unsubstituted when read from disk.
**Triage changes nothing.** This mode diagnoses — it does not branch, commit, edit, or open a PR. The deliverable is a confidence-rated diagnosis presented in-session.
**No lead research unless enabled.** Unless the user explicitly enables lead research, do not read codebase files, spawn subagents, or perform research. Delegate all evidence-gathering to teammates.
User-Provided Context
$ARGUMENTS
Describe what you want. Get a reviewed, ship-ready PR — without babysitting the agent.
Other commands on swarm.
create-workflow
Scaffold a custom workflow — generates a mode skill and shortcut command
launch
Interactively launch an agent team with guided setup
onboard
Walk through swarm's core concepts and launch your first team
refine
Run recursive refinement on the current branch and PR
update-workflow
Regenerate an existing custom workflow's shortcut command wiring from the current swarm template

