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/resume)<a href="https://agentmods.dev/skills/spacegrowth/claude-relay/resume"><img src="https://agentmods.dev/badge/skills/spacegrowth/claude-relay/resume/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/resume"><img src="https://agentmods.dev/badge/skills/spacegrowth/claude-relay/resume.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 | $0.00077 | $0.00580 |
| Opus 5 | $0.00039 | $0.00290 |
| Sonnet 5 | $0.00015 | $0.00116 |
| Haiku 4.5 | $0.00008 | $0.00058 |
Grade A, and why
resume 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 9d 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
Run: ${CLAUDE_PLUGIN_ROOT}/bin/relay resume $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 running claude --resume <the executor's Claude session id> in its
worktree, so the executor comes back with its entire conversation/context and the worktree's
staged work intact, and picks up its packet where it left off. Prefer this over /relay:restart
whenever you want to keep what the executor already did.
Requires the Claude session id captured at spawn — only sessions spawned after that capture landed
have it. If relay says there's no captured id, use /relay:restart instead (re-runs the packet as
a fresh session, losing prior context). If the session still looks alive, relay refuses unless you
pass --force (avoid two live instances of the same conversation).
Ownership follows the resume. Resuming an executor also adopts it — re-points its auto-wake
to the acting lead — which matters after a handoff (an inherited executor otherwise keeps waking
its old, retired lead, silently, forever). If it's currently owned by a live other lead, relay
warns instead of stealing it; relay adopt <session_id> --force takes it explicitly.
Restoring a crashed lead. /relay:resume <session-id> also brings back a crashed lead — pass
the lead's session id (find it in the LEADS section of /relay:list). Because a lead's session_id
is its own Claude Code session id, restore is claude --resume <lead_sid>: the lead's conversation
reopens in the marker's cwd with full context. The routing marker survived the crash on disk, so
the restored lead is still armed — no need to re-run /relay:mode. relay reopens its own tab,
refreshes the marker's last_active (so it looks fresh in relay list), and writes no executor
state. The restored lead should run /relay:list to reconstruct what executors are in flight.
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.
- 9d ago First seen · 37 lines · 77 tokens per session scan A 68c49daa27fb
resume is a skill published in the GitHub repository spacegrowth/claude-relay (1 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 580 once invoked, about $0.0004 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.