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 agentmods add skills/dryvist/claude-code-plugins/delegate-to-routernpx skills add dryvist/claude-code-plugins --skill delegate-to-routergit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWrote 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/dryvist/claude-code-plugins/delegate-to-router)<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/delegate-to-router"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/delegate-to-router.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 | $0.00047 | $0.01152 |
| Opus 5 | $0.00023 | $0.00576 |
| Sonnet 5 | $0.00009 | $0.00230 |
| Haiku 4.5 | $0.00005 | $0.00115 |
Grade A, and why
delegate-to-router scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS --max-time 10 -H "Authorization: Bearer $ROUTER_KEY" \ How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
delegate-to-router
Doctrine: prompt://dryvist/auto-ai-agent/model-delegation. This skill is the
mechanics — how to find out what is served right now, and how to call it.
Use it when a subtask is bounded: a summary, classification over a batch, structured extraction, boilerplate drafting, a first-pass read of unfamiliar code. Do not use it to hand off the judgment you were asked for.
1. Read your endpoint from the environment
The router is an OpenAI-compatible endpoint. Its base URL and your credential arrive as environment variables — the names are set by whatever provisioned your session, so read them rather than assuming a value:
env | grep -iE 'router|litellm|openai_(base|api)' | sed 's/=.*/=<set>/'
You never hold a provider credential directly, and the router's own upstream keys are not visible to you. If no endpoint variable is present, the router is not wired into this session: say so and do the work yourself. Do not go looking for a provider key.
2. Fetch the live model menu — never hardcode a name
Model inventories change far faster than this skill does, so the menu is fetched, not remembered:
# Preferred: LiteLLM-native, includes per-model metadata (aliases, limits).
curl -fsS --max-time 10 -H "Authorization: Bearer $ROUTER_KEY" \
"$ROUTER_BASE/model/info"
# Fallback: the plain OpenAI-compatible listing every router serves.
curl -fsS --max-time 10 -H "Authorization: Bearer $ROUTER_KEY" \
"$ROUTER_BASE/models" | jq -r '.data[].id'
Substitute the variable names you actually found in step 1 — $ROUTER_BASE is
expected to already include the API version (e.g. end in /v1), matching the
chat/completions call in step 3. If the variable you found doesn't, add the
version segment yourself before appending these paths.
Select from what came back. Prefer a stable role alias over a concrete model id where the registry publishes one — the alias is the part promised to keep working across model swaps. Sort candidates by cost and take the cheapest that can plausibly do this subtask, not the parent task.
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.
- 4d ago First seen · 111 lines · 47 tokens per session scan A 456c0729db1f
delegate-to-router is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 1,152 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
rspec
This skill should be used when the user asks to "write specs", "create spec", "add RSpec tests", "fix failing spec", or mentions RSpec, describe blocks, it blocks, expect syntax, test doubles, or matchers. Should also be used when editing spec.rb files, working in spec/ directory, planning implementation phases that…
activerecord
This skill should be used when the user asks to "write a migration", "add a column", "add column to table", "create an index", "add a foreign key", "set up associations", "fix N+1 queries", "optimize queries", "add validations", "create callbacks", "use eager loading", or mentions ActiveRecord, belongsto, hasmany…
dragonruby
This skill should be used when the user asks to "create a game", "make a game", "game development", "dragonruby", "drgtk", "game loop", "tick method", "sprite rendering", "game state", or mentions args.outputs, args.state, args.inputs, coordinate system, collision detection, animation frames, or scene management.…
draper-decorators
This skill should be used when the user asks to "create a decorator", "write a decorator", "move logic into decorator", "clean logic out of the view", "isn't it decorator logic", "test a decorator", or mentions Draper, keeping views clean, or representation logic in decorators. Should also be used when editing…
mcp-server
This skill should be used when the user asks to "create an MCP server", "build MCP tools", "define MCP prompts", "register MCP resources", "implement Model Context Protocol", or mentions the mcp gem, MCP::Server, MCP::Tool, JSON-RPC transport, stdio transport, or streamable HTTP transport. Should also be used when…
ratatui-ruby
This skill should be used when the user asks to "create a TUI", "terminal interface", "terminal UI", "ratatui", "ratatui-ruby", "inline viewport", "full-screen terminal app", "terminal widgets", "tui.draw", "tui.pollevent", or mentions RatatuiRuby.run, managed loop, terminal rendering, Tea MVU, or building CLI…