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/route)<a href="https://agentmods.dev/skills/spacegrowth/claude-relay/route"><img src="https://agentmods.dev/badge/skills/spacegrowth/claude-relay/route.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 | $0.00060 | $0.00314 |
| Opus 5 | $0.00030 | $0.00157 |
| Sonnet 5 | $0.00012 | $0.00063 |
| Haiku 4.5 | $0.00006 | $0.00031 |
Grade A, and why
route 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 8d 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
Use this ONLY when the edit gate has blocked an Edit/Write/MultiEdit and the edit is
genuinely lead work you should not delegate (e.g. committing/finalizing an executor's staged diff
that needs a small hand-adjustment, or a change that truly can't be packaged as an executor
packet). It is not a way to opt out of delegating real implementation work — that's exactly the
discipline the gate exists to keep.
Run:
${CLAUDE_PLUGIN_ROOT}/bin/relay route retain "<one-line reason>" --session "$CLAUDE_CODE_SESSION_ID"
This opens a short grace window (default 120s) during which inline edits pass ungated, and records
one durable retained event (with your reason) in the shared ledger, so the decision is visible
later. Make the edit within the window; if it expires, the gate re-engages and you'd run this
again. Prefer delegating (/relay:spawn / /relay:send) whenever the work reasonably fits a
packet — retain is the exception, not the default.
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.
- 8d ago First seen · 27 lines · 60 tokens per session scan A 22427a6e9bca
route is a skill published in the GitHub repository spacegrowth/claude-relay (1 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 314 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.