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.
git clone --depth 1 https://github.com/yacb2/claude-restartWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/yacb2/claude-restart/restart)<a href="https://agentmods.dev/commands/yacb2/claude-restart/restart"><img src="https://agentmods.dev/badge/commands/yacb2/claude-restart/restart/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/yacb2/claude-restart/restart"><img src="https://agentmods.dev/badge/commands/yacb2/claude-restart/restart.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00011 | $0.00086 |
| Opus 5.5 | $0.00004 | $0.00034 |
| Sonnet 5.5 | $0.00002 | $0.00017 |
| Haiku 4.5 | $0.00001 | $0.00009 |
Grade A, and why
restart scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
First, say exactly "↻ Session restarted" (nothing else). Then use the Bash tool to run: touch "$HOME/.claude/tmp/restart-flag-${CLAUDE_RESTART_ID}" && kill -TERM $PPID
Do NOT print the command. Do NOT explain. Just the message, then execute.
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.
- 2mo ago First seen · 9 lines · 11 tokens per session scan A 6ea27bc96fcc
restart is a command published in the GitHub repository yacb2/claude-restart (7 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 86 once invoked, about $0.0000 per session on Opus 5.5. 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.
restart compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| restartyacb2/claude-restart | Command | 7 | 1mo ago | MIT | A | 11 | Claude Code |
| atomic-helpdamusix/atomic-claude | Command | 115 | 5d ago | MIT | A | 57 | Claude Code |
| follow-updamusix/atomic-claude | Command | 115 | 5d ago | MIT | A | 0 | Claude Code |
| remind-medamusix/atomic-claude | Command | 115 | 5d ago | MIT | A | 39 | Claude Code |
| urly49/tlive | Command | 214 | 8d ago | MIT | A | 11 | Claude Code |
| handoffaxiomantic/spellbook | Command | 11 | 3d ago | MIT | A | 16 | Claude Code |
| listfuxicodex/Fuxi | Command | 3.2k | 17d ago | none | A | 6 | Claude Code |