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 skills add sonichi/sutando --skill claude-routergit clone --depth 1 https://github.com/sonichi/sutandoWrote 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/sonichi/sutando/claude-router)<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>- NVIDIA SkillSpector warn
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.
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 | $0.00048 | $0.00706 |
| Opus 5 | $0.00024 | $0.00353 |
| Sonnet 5 | $0.00010 | $0.00141 |
| Haiku 4.5 | $0.00005 | $0.00071 |
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.
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.
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: $ARGUMENTS
Routing Rules
-
Route to
codexfor:- code review
- bug hunting in a small or medium code slice
- implementation requests
- patch validation on current changes
-
Route to
geminifor:- repo-wide scans
- architecture and dependency tracing
- large-context summarization
- multimodal or structured JSON output requests
-
Route to
piwhen:- the request names
piorkimi - the user wants a Kimi-family second opinion
- the request names
If the request explicitly names codex, gemini, or pi, honor that directly.
When NOT to Use
-
Interactive code review or task hand-off from this Claude Code session → use the
/codex:*plugin commands directly (/codex:review,/codex:adversarial-review,/codex:rescue,/codex:status). The router is for programmatic delegation from scripts, cron, and bridges — it goes through theclaude-codexskill's bash wrapper, not the plugin.If you don't see
/codex:*slash-commands, install the plugin via the 4 commands documented inskills/claude-codex/SKILL.md("When NOT to Use" section).
Default Behavior
- Default review-oriented prompts to Codex.
- Default broad analysis prompts to Gemini in
planapproval mode. - Keep execution in the current workspace unless the user requested a different directory.
Quick Checks
bash "$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"
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.
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 · 80 lines · 48 tokens per session scan A d4e2ae28cc34
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.
Other skills, from other repositories
contacts
Manage contacts, communication channels, access control, and invite links.
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
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…
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…
guardian-verify-setup
Set up channel verification for phone, Telegram, Slack, Discord, or email channels via outbound verification flow.
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.