restart

A command that stops and starts a named software agent to bring it back online. An agent is a program that performs tasks on a platform.

In plain words
What is it for?
Restarting a specific agent, confirming its final status, and reporting whether stopping and starting it succeeded.
Why use it?
It provides a defined recovery procedure when an agent is stopped or malfunctioning, including status checks before and after the restart. It does not reset the agent's working context.

Command for Claude Code

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
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 312 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 $0.00312
Opus 5 $0.00000 $0.00156
Sonnet 5 $0.00000 $0.00062
Haiku 4.5 $0.00000 $0.00031

Measured 2d ago against content hash 1d46555a3fb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

restart 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.md · 53 lines

What it actually says

Restart Agent

Restart a specific agent by stopping and starting it.

Usage

/ops/restart <agent-name>

Instructions

  1. Validate the agent name - Check it exists using mcp__trinity__get_agent

  2. Check current status - Is it running, stopped, or in error state?

  3. If running:

    • Stop the agent using mcp__trinity__stop_agent
    • Wait 2-3 seconds for clean shutdown
    • Verify it stopped
  4. Start the agent using mcp__trinity__start_agent

  5. Verify the restart:

    • Check agent is running
    • Confirm agent server is responding
  6. Report the result:

## Agent Restart: {agent-name}

**Previous Status**: {running/stopped}
**Stop Result**: {success/failed}
**Start Result**: {success/failed}
**Final Status**: {running/stopped}

{Any notes or warnings}

Safety Checks

  • Do NOT restart trinity-system (yourself)
  • If agent was stopped, just start it (no need to stop first)
  • If restart fails, report the error clearly
  • If agent has high context, note that restart will NOT reset context

Arguments

The agent name should be provided after the command. For example:

  • /ops/restart research-agent
  • /ops/restart content-production-writer
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 · 53 lines · 0 tokens per session scan A 1d46555a3fb1

Subscribe to this mod's changes

restart 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 312 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.