workweave/router is a model router, a proxy that receives requests from coding tools or applications and forwards each one to a suitable language model through a single endpoint. It is for routing requests across Anthropic, OpenAI, Gemini, and other OpenAI-compatible providers while keeping provider keys on the user's machine. The catalogue entries provide skills, commands, and instructions for using the router.
Borrowing it
Nothing to install: this file belongs to workweave/router. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/workweave/router/main/.claude/skills/test-claude-locally/SKILL.mdgit clone --depth 1 https://github.com/workweave/routerWrote 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/workweave/router/test-claude-locally)<a href="https://agentmods.dev/skills/workweave/router/test-claude-locally"><img src="https://agentmods.dev/badge/skills/workweave/router/test-claude-locally/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/workweave/router/test-claude-locally"><img src="https://agentmods.dev/badge/skills/workweave/router/test-claude-locally.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00111 | $0.02619 |
| Opus 5.5 | $0.00044 | $0.01048 |
| Sonnet 5.5 | $0.00022 | $0.00524 |
| Haiku 4.5 | $0.00011 | $0.00262 |
Grade B, and why
test-claude-locally scanned grade B with 2 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **`~/.claude/settings.json` `env` overrides inherited env vars.** Setting `ANTHROPIC_BASE_URL` in the shell does NOT redirect `claude` — settings.json wins and the request silently goes to prod. Always redirect with `c Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **The router ignores the request's `model` field** and routes via the cluster scorer. The ONLY way to pin a specific model is `/force-model` through a Claude Code session (raw curl cannot). The source is not reproduced here
Licensed Apache-2.0
The repository is licensed Apache-2.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
1 file 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.
- 1mo ago First seen · 146 lines · 111 tokens per session scan B e6b7620a8e9c
test-claude-locally is a skill published in the GitHub repository workweave/router (5,593 stars, last pushed 2d ago), licensed Apache-2.0. It adds 111 tokens to every session and 2,619 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
evidence-publish
Deliver a QA/evidence packet to a tracker or keep it local, behind an always-ask preview gate. Protocol for /orc:qa Phase 6, /orc:evidence, and any evidence-delivery step.
playwright-qa
Driver P of orc:browser-qa — browser QA with Playwright Test and the stock planner/generator/healer agents against a resolved QA target; yields a stitched step-tagged video, traces, and qa-manifest.json.
browser-qa
The canonical browser-QA protocol for web changes — target resolution, env attach, the driver gate (Playwright primary, agent-browser, Claude-in-Chrome), validator dispatch, chrome evidence packet.
qa-targets
Resolve WHERE browser QA runs — named targets in .orc/targets.json (local, staging, preview), the Target gate, credential references (literal | op:// | env:), guard rule.
explainer
Build the narrated what-was-made walkthrough for a QA packet: script from plan + acceptance, demo pass, segments.json, animate graphics, kokoro narration, orc-explain assemble.
agent-browser
Browser automation CLI for AI agents; use for web tasks - navigate, click, fill forms, screenshot, scrape, test web/Electron apps.