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.
npx agentmods add skills/spacegrowth/claude-relay/closenpx skills add spacegrowth/claude-relay --skill closegit clone --depth 1 https://github.com/spacegrowth/claude-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/close)<a href="https://agentmods.dev/skills/spacegrowth/claude-relay/close"><img src="https://agentmods.dev/badge/skills/spacegrowth/claude-relay/close.svg" alt="Measured on agentmods" 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 | $0.00061 | $0.00499 |
| Opus 5 | $0.00030 | $0.00249 |
| Sonnet 5 | $0.00012 | $0.00100 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
close 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 5d 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
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.
Stepping down from lead mode (no executor session_id — this session stops being a lead and the
routing gate deactivates for it): run ${CLAUDE_PLUGIN_ROOT}/bin/relay close --self "$CLAUDE_CODE_SESSION_ID".
If just closing an executor session: run ${CLAUDE_PLUGIN_ROOT}/bin/relay close $session_id
(Usually unnecessary: finished executors are auto-closed — once their report has been seen by
you and their claimed files are clean in the worktree, or after auto_close_idle_minutes idle —
and relay send to a closed session resumes it with full context. Close by hand only when you
want it gone now; relay keep <sid> pins one against auto-close.)
If superseding (e.g. a session's model wasn't strong enough and you spawned a replacement): run
${CLAUDE_PLUGIN_ROOT}/bin/relay close $session_id --supersede $superseded_by
If you're closing a session whose territory someone will pick up again — it got heavy, or it
finished a phase and more work is coming to the same area — use /relay:retire instead. Same
teardown, but it also leaves a successor-seed.md behind so the next session inherits what this one
learned for the cost of one packet-read.
A session's model is fixed at launch — there's no way to change it mid-session. "Upgrading the
model" always means spawning a fresh session (via /relay:spawn) with a stronger --model, then
closing the old one with --supersede so /relay:list shows it was replaced rather than looking
like stale, still-awaiting-review work.
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.
- 5d ago First seen · 35 lines · 61 tokens per session scan A f79abb8becf7
close is a skill published in the GitHub repository spacegrowth/claude-relay (1 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 499 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
6つの専門レビュアーロールを並列実行し、consensusLevel（複数ロールの合意度）と Tech Lead レポート（top3指摘・blindSpots・consensusSummary）で結果を統合する マルチエージェントレビュー entry skill。 Parallel multi-role review with consensus scoring (consensusLevel) and Tech Lead report. Use when a major release needs exhaustive multi-angle review, or when a single-perspective review…
grok-cli-runtime
Internal helper contract for calling the grok-companion runtime from Claude Code.
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.
panel
Convenes a blind Codex and Grok panel on one neutral brief and adjudicates the verdicts.
stats
Aggregates delegation statistics and records semantic acceptance. Use after collecting and verifying a delegated result to record it as accepted or rejected, or when asked how the lanes are performing.
grok-prompting
Brief writing guidance for composing self contained Grok briefs for coding, review, diagnosis, and second opinion tasks.