route

route is a skill for Claude Code from spacegrowth/claude-relay. It costs 60 tokens per session (314 once invoked), scanned A, original, MIT.

A controlled exception for an editing workflow that normally sends larger code changes to another agent. It lets the lead agent make a small direct edit when the work genuinely cannot be packaged for delegation.

In plain words
What is it for?
Use it after the editing gate blocks a small final adjustment, such as finishing an executor's staged change. It is intended for exceptional lead work, not for implementing ordinary changes directly.
Why use it?
It preserves a documented way to finish narrowly scoped changes without silently bypassing the workflow. Each exception records a reason and opens only a short editing period.

Skill for Claude Code

Written for Claude Code: arguments in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the relay plugin — 18 skills, 1 agent, 4 hooks shipped together

Good fit Use it after the editing gate blocks a small final adjustment, such as finishing an executor's staged change. It is intended for exceptional lead work, not for implementing ordinary changes directly.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add spacegrowth/claude-relay
Claude Code
/plugin install relay

Made for: Claude Code.

Or install relay, the plugin that ships this one along with the rest of its 18 skills, 1 agent, 4 hooks.

Wrote 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.

agentmods badge for route

README.md
[![agentmods](https://agentmods.dev/badge/skills/spacegrowth/claude-relay/route.svg)](https://agentmods.dev/skills/spacegrowth/claude-relay/route)
Your own site
<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>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 314 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash 22427a6e9bca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

skills/route/SKILL.md · 27 lines

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.

Changes

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.

  1. 8d ago First seen · 27 lines · 60 tokens per session scan A 22427a6e9bca

Subscribe to this mod's changes

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.