claude-router

claude-router is a skill for Claude Code from sonichi/sutando. It costs 48 tokens per session (706 once invoked), scanned A, original, MIT.

Routing rules for choosing between the local Codex, Gemini, and Pi command-line tools from Claude Code. The choice depends on whether the task is implementation, a broad repository analysis, or a request for Pi or Kimi.

In plain words
What is it for?
Use it to send code reviews, small bug investigations, implementations, repository-wide scans, architecture tracing, large-context summaries, or Kimi-family second opinions to the appropriate local CLI.
Why use it?
It removes the need to decide manually which local tool best fits a task. It also defines what to do when the user explicitly names a particular tool.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

Good fit Use it to send code reviews, small bug investigations, implementations, repository-wide scans, architecture tracing, large-context summaries, or Kimi-family second opinions to the appropriate local CLI.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sonichi/sutando/claude-router
Install

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.

Any agent
npx skills add sonichi/sutando --skill claude-router
Clone the repo
git clone --depth 1 https://github.com/sonichi/sutando

Made for: Claude Code.

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 claude-router

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonichi/sutando/claude-router.svg)](https://agentmods.dev/skills/sonichi/sutando/claude-router)
Your own site
<a href="https://agentmods.dev/skills/sonichi/sutando/claude-router"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/claude-router.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 706 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 38
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00048 $0.00706
Opus 5 $0.00024 $0.00353
Sonnet 5 $0.00010 $0.00141
Haiku 4.5 $0.00005 $0.00071

Measured 8d ago against content hash d4e2ae28cc34, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claude-router 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/route-ai.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/claude-router/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Router

Route a task from Claude Code to local codex, gemini, or pi using simple, explicit rules. This skill assumes the dedicated claude-codex, claude-gemini, and claude-pi skills are installed from this repo.

Usage: /claude-router [prompt]

ARGUMENTS: $ARGUMENTS

Routing Rules

  • Route to codex for:

    • code review
    • bug hunting in a small or medium code slice
    • implementation requests
    • patch validation on current changes
  • Route to gemini for:

    • repo-wide scans
    • architecture and dependency tracing
    • large-context summarization
    • multimodal or structured JSON output requests
  • Route to pi when:

    • the request names pi or kimi
    • the user wants a Kimi-family second opinion

If the request explicitly names codex, gemini, or pi, honor that directly.

When NOT to Use

  • Interactive code review or task hand-off from this Claude Code session → use the /codex:* plugin commands directly (/codex:review, /codex:adversarial-review, /codex:rescue, /codex:status). The router is for programmatic delegation from scripts, cron, and bridges — it goes through the claude-codex skill's bash wrapper, not the plugin.

    If you don't see /codex:* slash-commands, install the plugin via the 4 commands documented in skills/claude-codex/SKILL.md ("When NOT to Use" section).

Default Behavior

  • Default review-oriented prompts to Codex.
  • Default broad analysis prompts to Gemini in plan approval mode.
  • Keep execution in the current workspace unless the user requested a different directory.

Quick Checks

bash "$SKILL_DIR/scripts/route-ai.sh" --check

Common Commands

# Auto-route based on prompt
bash "$SKILL_DIR/scripts/route-ai.sh" -- "Review the current diff for regressions"

# Force Codex
bash "$SKILL_DIR/scripts/route-ai.sh" --engine codex -- "Inspect src/task-bridge.ts for races"

# Force Gemini
bash "$SKILL_DIR/scripts/route-ai.sh" --engine gemini -- "Trace task flow across the entire repo"

# Force Pi (Kimi)
bash "$SKILL_DIR/scripts/route-ai.sh" --engine pi -- "Second opinion on this design"

# Dry-run the route decision without executing
bash "$SKILL_DIR/scripts/route-ai.sh" --dry-run -- "Summarize architecture risks in this repo"

Read the full file on GitHub · 80 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 80 lines · 48 tokens per session scan A d4e2ae28cc34

Subscribe to this mod's changes

claude-router is a skill published in the GitHub repository sonichi/sutando (393 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 706 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

contacts

Manage contacts, communication channels, access control, and invite links.

vellum-ai/vellum-assistant · 14 tokens

gmail

Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.

vellum-ai/vellum-assistant · 20 tokens

app-builder

Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…

vellum-ai/vellum-assistant · 162 tokens

assistant-migration

Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum…

vellum-ai/vellum-assistant · 90 tokens

guardian-verify-setup

Set up channel verification for phone, Telegram, Slack, Discord, or email channels via outbound verification flow.

vellum-ai/vellum-assistant · 26 tokens

vellum-memory-v3-migration

One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles with a stand-alone lead and queryable sections — with loss-proof staging, assistant-reviewed authoring, and a retrieval-eval gate before cutover.

vellum-ai/vellum-assistant · 63 tokens