Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Marcel-Bich/marcel-bich-claude-marketplace/plugin install credoWrote 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/marcel-bich/marcel-bich-claude-marketplace/self-restart)<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/self-restart"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/self-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/marcel-bich/marcel-bich-claude-marketplace/self-restart"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/self-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 | $0.00027 | $0.04439 |
| Opus 5.5 | $0.00011 | $0.01776 |
| Sonnet 5.5 | $0.00005 | $0.00888 |
| Haiku 4.5 | $0.00003 | $0.00444 |
Grade A, and why
self-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 15d 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.
How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Credo Self-Restart
Lets a running Claude Code session restart itself - typically to load plugin updates ("cc-up") - and come back as EXACTLY the same session in the SAME profile, continuing on its own without a human prompt.
Helper: ${CLAUDE_PLUGIN_ROOT}/scripts/credo-self-restart.py
| Action | What it does |
|---|---|
check (default) |
Dry run. Gathers and validates everything and prints the plan (target pid, config dir, cwd, session id, transcript, relaunch method, dialog guard, restored permission mode, relaunch command, update allowlist). Changes nothing. Exit 1 with a clear reason if any precondition fails. |
run --no-background-work (--user-confirmed | --announce S) [--update] [--reason TEXT] [--delay S] |
First the owner-rule guard (below), then the background guard (--no-background-work is required, see below): refused -> exit 3, nothing started. Then validates exactly like check. On any failure nothing is stopped, an ntfy push goes out (if configured) and it exits 1. Otherwise it spawns a fully detached worker and returns at once. With an announce period it prints the announcement and sends an ntfy push first. Refuses (exit 1) while another restart is still pending. |
cancel |
Marks the pending restart as cancelled and terminates its waiting worker; the session keeps running. Exit 1 with "nothing to cancel" when nothing is pending (also once the worker has started stopping the session - then it is too late). |
status |
Prints the state line (pending / cancelled / stopping / relaunched / failed: ...) with the scheduled stop time, the last marker (<configdir>/credo/self-restart.json) and the log tail. |
Owner rule - when the agent may use it
Owner rule: self-restarts may run without the Ask tool, but ONLY in credo autonomous mode and ONLY with a 5-minute announcement beforehand so the user can still react. Never self-restart on the agent's own initiative outside autonomous mode - the user may be typing a prompt that would be lost; outside autonomous mode always ask via the Ask tool.
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.
- 15d ago Changed · +49 lines 8a73ac64f020
- 16d ago First seen · 227 lines · 27 tokens per session scan A e6823f26739a
self-restart is a command published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (12 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 4,439 once invoked, about $0.0001 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 2026-10-09.
Other commands, from other repositories
context-stats
Display context window usage and token statistics.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.
help
Explain Ralph Wiggum technique and available commands.
cancel-ralph
Cancel active Ralph Wiggum loop.
session-log
Explain where session history lives now that the toolkit keeps no session log.
backup-config
Backup Claude Code configuration files.