🧪
AutomationGo

Test Claude Locally

by workweave

Test Claude Locally is an Automation skill for Claude Code, published by workweave in router.

967 stars52 forkson workweave/routerAdded 2026/08/21Repository updated 2026/08/21
agentic-codingai-gatewayanthropicclaude-codecodexmodel-routeropenai-compatible
Install in seconds
Install Test Claude Locally
Copy Test Claude Locally into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/workweave/router/tree/main/.claude/skills/test-claude-locally ~/.claude/skills/test-claude-locally

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/workweave/router.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
.claude/skills/test-claude-locally/SKILL.md in workweave/router
Installs to
~/.claude/skills/test-claude-locally
Collection
One of 4 skills cataloged from this repository
Category
Automation1523 skills

What Test Claude Locally does

Test Claude Locally runs the router in local Docker Compose and drives it with `claude -p` to reproduce routing and translation behavior for a chosen upstream model. Use it to verify fixes, model streaming quirks, or `/force-model` routing without changing global Claude Code settings.

Test Claude Locally is cataloged under Automation on DirSkills. Test Claude Locally comes from a repository tagged agentic-coding, ai-gateway, anthropic, claude-code and codex.

Documentation

README

Testing the router locally

For an automated pre-merge regression net (fixture-driven, asserts caching/streaming/decision-headers against real Anthropic), run make smoke — see docs/SMOKE.md. This skill is the interactive counterpart: stand the stack up by hand and drive it with claude -p to reproduce or verify a one-off bug.

Stand up the router in docker compose, point a one-off claude -p session at it via --settings, and read the local server logs to confirm behavior. Two upstream modes: the real provider API (needs a working key + credits) or a mock upstream that emits an exact SSE shape (deterministic, no credits).

Critical gotchas (read first)

This is the opening of the README. Read the full README on GitHub.

Commands Test Claude Locally provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /force-model

Frequently asked about Test Claude Locally

  • What else does workweave publish alongside Test Claude Locally?

    Test Claude Locally is one of 4 skills that DirSkills catalogs from workweave/router, the repository it ships in. Its siblings there include Debug Claude Session, Disable Routing and PR Feedback Loop. Each one is a separate skill with its own page in this directory, installs the same way Test Claude Locally does, and is maintained by workweave in that same repository. The rest of the collection is listed on the workweave/router page.

  • How does Test Claude Locally compare to other Automation skills?

    Test Claude Locally ranks #858 by stars among the 1523 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Test Claude Locally against them. Open each page to compare what they document and how they install.