restart

A command that gracefully restarts the current Claudex terminal session and records why the restart happened.

In plain words
What is it for?
Restarting a Claudex tmux session, logging the reason, notifying the user through Telegram, and allowing the watchdog to bring the session back if needed.
Why use it?
It provides a controlled way to recover or refresh a running session, with a warning and saved state when possible.

Command

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/jansenanalytics/claudex/restart
Clone the repo
git clone --depth 1 https://github.com/JansenAnalytics/claudex
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 314 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 $0.00014 $0.00314
Opus 5 $0.00007 $0.00157
Sonnet 5 $0.00003 $0.00063
Haiku 4.5 $0.00001 $0.00031

Measured 2d ago against content hash 3ad3f848a397, 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.

commands/restart.md · 23 lines

What it actually says

Restart the current Claudex tmux session gracefully. The user may supply a reason as an argument; if so, log it.

Steps:

  1. Read the reason from the argument (default: "manual restart via /restart").
  2. Append a log line to ~/.claude-agent/logs/watchdog.log in the watchdog's format:
    [YYYY-MM-DD HH:MM:SS] 🔄 Restarting: <reason>
    
  3. Send the user a Telegram message confirming the restart is about to happen and giving them ~3 seconds to abort if they want (don't actually wait — just inform).
  4. Trigger the restart by running bash ~/.claude-agent/scripts/restart-claudex.sh (or, if that script doesn't exist, kill the tmux session — the watchdog cron will respawn within ~5 minutes via bash ~/.claude-agent/scripts/start-claudex.sh).

Notes:

  • If the session is mid-task (any agent activity indicator visible: ✻, Running, Executing), warn the user once and ask for confirmation before proceeding.
  • Save any in-flight state via bash ~/.claude-agent/scripts/session-shutdown.sh first if it exists.
  • Don't leave the user hanging — the next message after restart will arrive in the new session, so make the pre-restart message complete on its own.
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 · 23 lines · 14 tokens per session scan A 3ad3f848a397

Subscribe to this mod's changes

restart is a command published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 314 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.