Imyousuf Agentic Test Runner
imyousuf-agentic-test-runner is a Claude Code plugin for the Ship phase that runs tests and debugs failures through an MCP server while keeping the main coding context clean.
by imyousuf · github.com/imyousuf/agentic-test-runner
Run tests and iterate on failures through an MCP-backed runner so your main agent chat stays focused on fixes, not log dumps.
Add it to Claude Code
Install the plugin in Claude Code. One command, paste-ready.
/plugin install imyousuf-agentic-test-runner@imyousuf/agentic-test-runnerBuilt to be called by your agent
Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.
Retrieve this entry with skillselion.get_details("plugin:imyousuf/agentic-test-runner") and the paste-ready config with skillselion.get_install_config("plugin:imyousuf/agentic-test-runner").
What it does
imyousuf-agentic-test-runner is a Claude Code plugin that pairs a test runner with an MCP server so agents can execute tests, inspect failures, and debug without stuffing large logs into the primary coding session. Solo builders shipping web or CLI products can delegate flaky or verbose test cycles to the runner while the main thread stays on patches and design. Keywords in the bundle point at browser control, screenshots, behavior analysis, and structured test tooling—useful when failures need DOM state or reproduction steps, not just stack traces. It fits indie teams who already use Claude Code with MCP and want a repeatable “run → analyze → fix” rhythm during Ship. Complexity is intermediate because you wire the MCP server and align it with your existing test stack. It is a focused integration plugin (one plugin in the repo), not a full marketplace or generic skill library.
Highlights
- Runs tests and debugs failures via a dedicated MCP server
- Keeps coding context clean by offloading test output and analysis
- Browser-oriented ATR tools: navigate, click, screenshots, behavior analysis
- Supports atr, atranalyze, atrbehavior, and atrbrowser-style workflows
- Single-plugin bundle focused on agentic test-and-fix loops
Why builders use it
Failing tests flood the agent with noisy output and burn context, so debugging slows down instead of converging on a fix.
After install, tests run and failures are analyzed in a side channel so you can apply targeted fixes in a cleaner main session.
At a glance
- Type - Plugin in Testing.
- Adoption - 0 installs, 8 stars, 0 votes.
FAQ
Who is imyousuf-agentic-test-runner for?
It is for Claude Code users who run real test suites and want MCP-isolated run-and-debug loops while keeping the primary agent thread lean.
When should I use imyousuf-agentic-test-runner?
Use it during Ship when tests fail repeatedly, especially when browser behavior, screenshots, or structured ATR analysis help reproduce the bug.
How do I add imyousuf-agentic-test-runner to my agent?
Install the plugin from the imyousuf/agentic-test-runner marketplace entry in Claude Code, configure the MCP test-runner server, then invoke its skills or tools from your test workflow.
Comments
Share how you use imyousuf-agentic-test-runner, gotchas, or tips for other indie builders.
No comments yet - be the first to share how you use it.