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 spacegrowth/claude-relay/plugin install relayWrote 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/skills/spacegrowth/claude-relay/restart)<a href="https://agentmods.dev/skills/spacegrowth/claude-relay/restart"><img src="https://agentmods.dev/badge/skills/spacegrowth/claude-relay/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/skills/spacegrowth/claude-relay/restart"><img src="https://agentmods.dev/badge/skills/spacegrowth/claude-relay/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 | $0.00066 | $0.00298 |
| Opus 5 | $0.00033 | $0.00149 |
| Sonnet 5 | $0.00013 | $0.00060 |
| Haiku 4.5 | $0.00007 | $0.00030 |
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 yesterday.
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
Run: ${CLAUDE_PLUGIN_ROOT}/bin/relay restart $session_id (Claude Code substitutes the plugin's
absolute path when this skill loads — call it this way, not as bare relay, which often isn't on
the Bash tool's non-interactive PATH).
This opens a fresh iTerm tab and re-runs the session's current packet as a brand-new claude
conversation. It does NOT carry over the prior conversation — use /relay:resume for that. The
worktree (and any staged work) is untouched, so restarting re-does the packet on top of whatever is
already there; use it when the previous attempt was botched and you want a clean redo.
If the session still looks alive, relay refuses unless you pass --force — except when it is
provably stuck: a session whose transcript has not been written for longer than
stall_threshold_seconds (process alive, going nowhere) is exactly what restart is for, and is
accepted without --force.
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.
- yesterday Changed · +3 lines 7eb53cec31ed
- 9d ago First seen · 20 lines · 66 tokens per session scan A b805a9c486dc
restart is a skill published in the GitHub repository spacegrowth/claude-relay (1 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 298 once invoked, about $0.0003 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.
Other skills, from other repositories
review-team
A multi-reviewer code review process that checks a change from several specialist viewpoints and combines the results into one report. It can cover bugs, security, tests, dependencies, frontend behavior, and continuous-integration workflows.
panel
Convenes a blind Codex and Grok panel on one neutral brief and adjudicates the verdicts.
ultra
Fans the work out as a fleet of parallel Grok and Codex agents billed to their own subscriptions, then synthesizes one result. The peer engine equivalent of ultracode, adding intensity without spending Claude quota on the fleet. Use it for genuinely broad goals, not only explicit asks for intensity.
grok-prompting
Brief writing guidance for composing self contained Grok briefs for coding, review, diagnosis, and second opinion tasks.
grok-result-handling
Internal guidance for presenting Grok companion output back to the user.
smoke
Runs a three probe live smoke wave after a plugin update and reports gate chain health before real work rides it.