agentmods.dev

raven: Skill for Claude Code

.claude/skills/router/SKILL.md

router is a skill for Claude Code from giggsoinc/raven. It costs 51 tokens per session (311 once invoked), scanned A, original, MIT.

A command-based setting for Raven's model router, which decides whether simple prompts may be sent to a smaller helper model. It changes routing advice, not the main session model.

In plain words
What is it for?
Use /router, /router off, or /router status to manage or check routing. The setting resets to on when a new session starts.
Why use it?
It lets you turn helper-model delegation on or off and inspect the current setting. Prompts involving secrets remain local and are not sent to cloud helpers.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PROJECT_DIR variable. Also seen: mentions subagents; mentions Claude Code.

This is giggsoinc/raven's own configuration. It tells Claude Code how to work on raven itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything raven configures →

Part of the raven plugin — 63 skills, 13 commands, 10 agents, 5 hooks, 1 MCP server shipped together

not rated 5repo 6d ago A scan 51 tokens original MIT
View source ↗ giggsoinc/raven
Reuse

Borrowing it

Nothing to install: this file belongs to giggsoinc/raven. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/giggsoinc/raven/main/.claude/skills/router/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/giggsoinc/raven

Made for: Claude Code.

Or install raven, the plugin that ships this one along with the rest of its 63 skills, 13 commands, 10 agents, 5 hooks, 1 MCP server.

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 router

README.md
[![agentmods](https://agentmods.dev/badge/skills/giggsoinc/raven/router.svg)](https://agentmods.dev/skills/giggsoinc/raven/router)
Your own site
<a href="https://agentmods.dev/skills/giggsoinc/raven/router"><img src="https://agentmods.dev/badge/skills/giggsoinc/raven/router.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 311 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 $0.00051 $0.00311
Opus 5 $0.00026 $0.00156
Sonnet 5 $0.00010 $0.00062
Haiku 4.5 $0.00005 $0.00031

Measured 7d ago against content hash ef0478c80e79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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 7d 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.

.claude/skills/router/SKILL.md · 22 lines

What it actually says

Raven Model Router Toggle

Run the matching command and relay its printed output to the user verbatim:

  • /router or /router on → python3 "${CLAUDE_PROJECT_DIR:-.}/scripts/model-router.py" --enable
  • /router off → python3 "${CLAUDE_PROJECT_DIR:-.}/scripts/model-router.py" --disable
  • /router status → python3 "${CLAUDE_PROJECT_DIR:-.}/scripts/model-router.py" --status

What to tell the user (keep it honest)

  • Default ON. SessionStart runs model-router.py --session-start and arms base routing every session.
  • SIMPLE + self-contained → Claude must spawn a Haiku Agent and return that answer. Context-bound SIMPLE stays on the session model (one-line why).
  • The primary session model NEVER changes. Claude Code has no per-turn model swap (/model only). LiteLLM is not wired yet — do not claim it is.
  • /router off opts out until the next SessionStart, which turns it ON again.
  • LOCAL_ONLY (secrets) still blocks cloud subagents either way.
  • State: .raven/.router-state.json.
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. 7d ago First seen · 22 lines · 51 tokens per session scan A ef0478c80e79

Subscribe to this mod's changes

router is a skill published in the GitHub repository giggsoinc/raven (5 stars, last pushed 6d ago), licensed MIT. It adds 51 tokens to every session and 311 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.

Building agents
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens