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/retire)<a href="https://agentmods.dev/skills/spacegrowth/claude-relay/retire"><img src="https://agentmods.dev/badge/skills/spacegrowth/claude-relay/retire/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/retire"><img src="https://agentmods.dev/badge/skills/spacegrowth/claude-relay/retire.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 | $0.00074 | $0.00673 |
| Opus 5 | $0.00037 | $0.00336 |
| Sonnet 5 | $0.00015 | $0.00135 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
retire 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
Call relay as ${CLAUDE_PLUGIN_ROOT}/bin/relay (Claude Code substitutes the plugin's absolute path
when this skill loads) — not bare relay, which often isn't on the Bash tool's non-interactive PATH.
Run: ${CLAUDE_PLUGIN_ROOT}/bin/relay retire $session_id
That closes the session (as superseded by its seed, tab and all — same teardown as
/relay:close) and writes a successor seed to its state dir: an index of every packet it was
sent, with each report's outcome line, Status, Risk flags and UNVERIFIED — plus the worktree
and topic it owned. The seed is an INDEX, not a transcript: the detail stays in the linked reports.
Then spawn the successor with the seed, exactly as the retire message tells you:
${CLAUDE_PLUGIN_ROOT}/bin/relay spawn $worktree $topic $packet --seed $retired_session_id --lead "$CLAUDE_CODE_SESSION_ID"
The seed is appended to the fresh executor's packet as inherited context (task first, seed second, GATES last), so the successor starts knowing what happened on this territory without reading anything else. You can also pass a path to the seed file instead of the retired session's id.
When to reach for this instead of /relay:send. A long-lived executor accumulates context; a
fresh one starts sharp. Retire when a session is getting heavy, has finished a phase of work, or is
dead/stalled with useful history behind it — the seed is what makes respawning cheap enough to
actually do, so don't keep piling packets onto a heavy session just to avoid the rebuild cost.
Heaviness is not degradation, though: a disciplined executor can do fine work deep in a session, so
this is a judgement call, not a rule.
Refusals you may hit:
- still busy on packet NNN and has not reported — retiring now kills that packet's work
unreported, and the seed can't summarise a report that was never written. Wait for it
(
/relay:check), or pass--forceto retire anyway (that packet is then seeded asNO REPORT). A session that is busy but provably stuck — its transcript hasn't been written for longer thanstall_threshold_seconds, the shape an executor waiting on an unanswerable OS prompt takes — is accepted without--force: there is nothing live left to interrupt. - already retired — the seed already exists; the message prints its path. Just spawn with it.
(--keep-tab retires but leaves the terminal tab open, same as /relay:close.)
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 2c677e23a63c
- 9d ago First seen · 43 lines · 74 tokens per session scan A 9a5e2a83e521
retire is a skill published in the GitHub repository spacegrowth/claude-relay (1 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 673 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.