New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Weave Router Model Selector

by weave-os in weave-os/router

Lists which models a Weave Router installation may route to and turns individual models or whole providers on or off, mirroring the router dashboard's settings.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Weave Router Model Selector

skills CLI
$ npx skills add weave-os/router --skill router-models -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install weave-os/router router-models --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/weave-os/router.git skills-src && mkdir -p .claude/skills && cp -r skills-src/install/codex-skills/router-models .claude/skills/router-models && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
router-models
GitHub stars
5.6k
Token cost
~533 tokens
SKILL.md length
285 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
Apache-2.0

At a glance

Lists which models a Weave Router installation may route to and turns individual models or whole providers on or off, mirroring the router dashboard's settings.

  • Checking which models a Weave Router can currently route to
  • Calls npx
  • Turning a specific model or provider on or off for routing
  • Setting or clearing a preference ranking between models

What it does

The skill runs a CLI command that prints every deployed model grouped by provider with a checkbox-style marker showing whether the router may currently pick it, which the agent presents back as a compact checklist keeping the same grouping and exact model IDs the user selects by. When the user names specific models or providers, it works out whether they mean on or off from their phrasing and applies it with an enable or disable command, batching several IDs into one call and then re-listing to confirm the result; when they name nothing, it stops after showing the list and asks what to change rather than guessing.

It also covers ranking models by preference order or clearing that ranking, and listing providers alone. If the installation turns out to be Weave-hosted, model selection belongs to the whole organization rather than this installation, so the skill directs the user to the hosted dashboard instead of trying to change it locally, and presents that case as a plain list with no on/off state. Disabling a model takes effect on the router's very next routing decision, with no restart needed.

When your agent uses it

  • Checking which models a Weave Router can currently route to
  • Turning a specific model or provider on or off for routing
  • Setting or clearing a preference ranking between models

Example prompts

  • “Show me which models this router can pick from right now.”
  • “Turn off the expensive provider and keep the rest enabled.”
  • “Rank these three models by preference, fastest first.”

Requirements

  • A Weave Router installation
  • npx with network access to run the weave-router CLI

What it can do on your machine

Read from SKILL.md and the folder at commit 8e8ebe6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • router.workweave.ai

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Weave Router Model Selector loads about 533 tokens when it runs. Until then it costs about 21 tokens; SKILL.md has 285 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~21
When it runs · the whole SKILL.md, loaded when a task matches
~533

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from weave-os/router at commit 8e8ebe6, republished under its Apache-2.0 licence (© weave-os). 285 words, ~533 tokens.

Download SKILL.mdSave it as .claude/skills/router-models/SKILL.md (or your agent's skills folder).
name
router-models
description
List the models the Weave Router may route to, and turn them on or off.
<!-- weave-router managed router-models skill -->

Weave Router model selection

When the user invokes $router-models, show which models this installation lets the router pick from, and change that selection when asked. This is the same list — and the same stored setting — as the checkboxes on the router dashboard's settings page.

Start by running:

bash
npx --package @weave-os/router -y -- weave-router models --codex{{SCOPE}}

That prints every deployed model grouped by provider, with [x] for models the router may pick and [ ] for models it may not. Present it back as a compact checklist in that same [x] / [ ] form, keeping the provider grouping and the exact model ids — the user selects models by id.

Then:

  • If the user named models or providers, work out whether they want them on or off from how they phrased it, and apply it with weave-router models enable <id>... --codex{{SCOPE}} or weave-router models disable <id>... --codex{{SCOPE}} (add providers before enable/disable to switch a whole provider). Several ids can go in one call. Then re-run the list and show the result.
  • If they named nothing, stop after the list and ask which ones to change. Never change anything they did not ask for.

Other things they might ask for:

  • Rank models by preference: weave-router models prefer <id> <id>... --codex{{SCOPE}} (order matters), or weave-router models prefer clear --codex{{SCOPE}} to drop the ranking.
  • Providers only: weave-router models providers --codex{{SCOPE}}.

If the command reports that this router doesn't expose model selection, that's a Weave-hosted router: model selection belongs to the whole organization there, so tell the user to change it at https://router.workweave.ai/dashboard/settings — don't try to work around it. Its listing carries no on/off state, so present it as a plain list; don't infer which models are enabled.

Disabling a model takes effect on the router's next routing decision; no restart is needed.

© weave-os, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in install/codex-skills/router-models of weave-os/router.

Open the folder on GitHubat commit 8e8ebe6

Compare with similar skills

Weave Router Model Selector next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Weave Router Model Selector compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Weave Router Model Selector this skillweave-os/router5.6k—~533Automated safety check: PassApache-2.0
FreeRide Free Model ManagerShaivpidadi/FreeRide2383 repos~1.1kAutomated safety check: PassNone
OmniRoute Cost and Usage CLIdiegosouzapw/OmniRoute74k1 repos~693Automated safety check: PassMIT
Hyper Jevdisler/ten-levels-of-jev207—~1.7kAutomated safety check: PassMIT
Antigravityyuting0624/antigravity-for-claude-code376—~9.1kAutomated safety check: PassMIT
ClawRouter LLM GatewayBlockRunAI/ClawRouter6.6k—~6.8kAutomated safety check: PassMIT

Similar skills

  • FreeRide Free Model Manager

    Shaivpidadi/FreeRide

    Configures OpenClaw to use free OpenRouter models, setting the best one as primary and adding ranked fallbacks so rate limits do not interrupt work.

    238 GitHub starsUsed in 3 repos~1.1k tokens
    AI & LLM EngineeringAuto-check passed

  • OmniRoute Cost and Usage CLI

    diegosouzapw/OmniRoute

    View cost breakdowns, token usage, and call logs from the CLI. Filter by provider, model, or date range. Export usage reports and inspect per-connection…

    74k GitHub starsUsed in 1 repo~693 tokens
    AI & LLM EngineeringAuto-check passed

  • Hyper Jev

    disler/ten-levels-of-jev

    Integrate and use Jev, TypeSafe AI's System One decision model, in production codebases.

    207 GitHub stars~1.7k tokensUpdated 11 days ago
    AI & LLM EngineeringAuto-check passed

  • Antigravity

    yuting0624/antigravity-for-claude-code

    Run the Antigravity CLI (Gemini) as a collaborating AI inside Claude Code, with intelligent model routing across the software development lifecycle.

    376 GitHub stars~9.1k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed

  • ClawRouter LLM Gateway

    BlockRunAI/ClawRouter

    Describes ClawRouter, a local proxy that forwards each LLM request to the blockrun.ai gateway, which routes to a cheaper capable model, paid by USDC wallet or API key credit.

    6.6k GitHub stars~6.8k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

  • Openrouter Context Optimization

    jeremylongshore/tons-of-skills-marketplace

    Optimize context window usage for OpenRouter models to reduce cost and improve quality.

    2.8k GitHub stars~2.4k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

More from weave-os/router

All 19 skills in this repo

  • Weave Router Local Testing

    weave-os/router

    Stands up the Weave model router in Docker Compose and drives it with claude -p against a real or mocked upstream to reproduce and verify routing and streaming behavior.

    5.6k GitHub stars~3.1k tokensUpdated yesterday
    Auto-check: notes

  • Test Weave Router with Codex

    weave-os/router

    Local test harness for the Weave router: a docker compose stack plus codex exec runs that confirm how Codex requests are routed, translated and marked.

    5.6k GitHub stars~4.7k tokensUpdated yesterday
    Auto-check: notes

  • PR Merge Ready

    weave-os/router

    Works through every review comment on a pull request in one pass, fixes what it can, escalates human decisions and keeps CI churn to a single push.

    5.6k GitHub stars~10k tokensUpdated yesterday
    Auto-check passed

  • Claude Session Router Debugger

    weave-os/router

    Correlates a Claude Code session's local transcript with a model router's production cloud logs to explain why a specific response rendered the way it did.

    5.6k GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

  • Install Language Servers

    weave-os/router

    Installs a language server such as gopls, typescript-language-server, pyright or rust-analyzer and, with explicit confirmation, its underlying toolchain so the lsp tool can use it.

    5.6k GitHub stars~745 tokensUpdated yesterday
    Auto-check: notes

  • Codex Session Debugging

    weave-os/router

    Correlates a Codex CLI session's local transcript with a model router's production logs to explain why a reply rendered the way it did.

    5.6k GitHub stars~4.5k tokensUpdated yesterday
    Auto-check: warnings

Categories

Questions about Weave Router Model Selector

What does Weave Router Model Selector do?

Lists which models a Weave Router installation may route to and turns individual models or whole providers on or off, mirroring the router dashboard's settings. The skill runs a CLI command that prints every deployed model grouped by provider with a checkbox-style marker showing whether the router may currently pick it, which the agent presents back as a compact checklist keeping the same grouping and exact model IDs the user selects by. When the user names specific models or providers, it works out whether they mean on or off from their phrasing and applies it with an enable or disable command, batching several IDs into one call and then re-listing to confirm the result; when they name nothing, it stops after showing the list and asks what to change rather than guessing.

When should I use Weave Router Model Selector?

Weave Router Model Selector fits situations like: checking which models a Weave Router can currently route to; turning a specific model or provider on or off for routing; setting or clearing a preference ranking between models.

How do I install Weave Router Model Selector in Claude Code?

Run `npx skills add weave-os/router --skill router-models -a claude-code`. Or copy the skill folder (install/codex-skills/router-models in weave-os/router) into .claude/skills/router-models in your project. Claude Code loads it when a task matches its description.

How do I install Weave Router Model Selector in Codex?

Run `npx skills add weave-os/router --skill router-models -a codex`. Or copy the skill folder (install/codex-skills/router-models in weave-os/router) into .agents/skills/router-models in your project. Codex loads it when a task matches its description.

Can I use Weave Router Model Selector in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add weave-os/router --skill router-models -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/router-models, .gemini/skills/router-models, .github/skills/router-models and .opencode/skills/router-models in your project.

What does Weave Router Model Selector need to run?

Going by SKILL.md and its folder, Weave Router Model Selector needs the command-line tools its instructions call (npx). Our summary lists: A Weave Router installation; npx with network access to run the weave-router CLI.

Does Weave Router Model Selector access the network?

SKILL.md names 1 domain. As links in the text: router.workweave.ai. This is read from the text; nothing was executed.

Is Weave Router Model Selector safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Weave Router Model Selector use?

Weave Router Model Selector is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Weave Router Model Selector use?

About 533 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Weave Router Model Selector?

Skills that share tags, products or a category with Weave Router Model Selector: FreeRide Free Model Manager (Shaivpidadi/FreeRide, 238 stars), OmniRoute Cost and Usage CLI (diegosouzapw/OmniRoute, 74k stars), Hyper Jev (disler/ten-levels-of-jev, 207 stars) and Antigravity (yuting0624/antigravity-for-claude-code, 376 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Weave Router Model Selector?

weave-os (a GitHub organization) maintains it in weave-os/router, which has 5,576 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 8, 2026.

Source: weave-os/router on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.