restart-all

A command that stops and starts every currently running agent in a fleet, while skipping stopped agents and the system agent. An agent is a configured worker that can perform tasks or hold chats.

In plain words
What is it for?
Use it for a coordinated platform restart and to receive a report showing which agents stopped and started successfully.
Why use it?
It restores availability after platform maintenance, configuration changes, or several agents becoming stuck. Active chats are interrupted briefly, but agent context is preserved.

Command for Claude Code

▶ Build an AI Recruiter Agent with Trinity + Claude Code (Live Workshop) Eugene Vyborov · about Abilityai/trinity · on YouTube →
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/abilityai/trinity/restart-all
Clone the repo
git clone --depth 1 https://github.com/Abilityai/trinity

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 295 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00295
Opus 5 $0.00000 $0.00148
Sonnet 5 $0.00000 $0.00059
Haiku 4.5 $0.00000 $0.00030

Measured 2d ago against content hash 5194dbbd7bcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

restart-all scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

config/agent-templates/trinity-system/.claude/commands/ops/restart-all.md · 59 lines

What it actually says

Restart All Agents

Restart all agents in the fleet. Use with caution!

Instructions

  1. Confirm the action - This is a significant operation

  2. Get all agents using mcp__trinity__list_agents

  3. Filter to running agents (no point restarting stopped ones)

  4. Exclude trinity-system (yourself - never restart yourself)

  5. For each agent:

    • Stop the agent
    • Wait 2 seconds
    • Start the agent
    • Record success/failure
  6. Report results:

## Fleet Restart Report
Generated: {timestamp}

### Summary
- Agents Restarted: X
- Successful: X
- Failed: X
- Skipped (stopped): X

### Results

| Agent | Previous | Stop | Start | Final |
|-------|----------|------|-------|-------|
| ... | running | OK | OK | running |
| ... | running | OK | FAIL | stopped |

### Failures
{Details of any failures}

### Notes
- Trinity-system was skipped (cannot restart self)
- {Any other notes}

Warning

This operation will:

  • Interrupt any active chat sessions
  • Briefly make agents unavailable
  • NOT reset context (context persists across restarts)

Only use this for:

  • Platform maintenance
  • After configuration changes
  • When multiple agents are stuck
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 59 lines · 0 tokens per session scan A 5194dbbd7bcc

Subscribe to this mod's changes

restart-all is a command published in the GitHub repository Abilityai/trinity (496 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 295 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.