Turn a bug report into a reproduction plan
A clear diagnostic checklist that helps a developer reproduce the issue.
Workflows for developers using Muse: reproduction plans from bug reports, changelog summaries, dependency audits. Plus a community Muse invite code pool.
Developers already delegate to agents inside the editor. Muse sits outside it: a personal agent with its own browser that can read a bug report, chase a changelog, or summarise what changed in a dependency since you last looked.
The workflows below are written for the glue work around code rather than the code itself, and they produce something you can paste into an issue or a pull request.
A clear diagnostic checklist that helps a developer reproduce the issue.
Sundog's developer workflows focus on research, documentation and triage. For code changes, use the tooling your team already trusts, and never give an agent credentials it does not need.
Sign in to Sundog, take one code from the community pool, redeem it under Redeem invite code in your Muse settings within 48 hours of joining, then add your own code for the next person. You and the person who shared the code each get 1 billion Muse tokens. One code per person, and codes never bypass Meta's availability or eligibility rules.
Starter workflows are original instructions written as starting points and are labelled untested. Community members report what worked, and those results appear on each workflow page as they come in.
A review queue of stale links, inconsistent examples, and missing prerequisites.
A timestamped account of an incident with evidence and unanswered questions.
A focused test plan covering the important behaviors and failure cases.
A readable walkthrough of a specific feature's control flow and data flow.
A release plan that covers migrations, configuration, verification, and rollback.
An upgrade checklist grounded in release notes and your current usage.
A clearer PR description connecting the problem, final behavior, and validation.
A source-backed plan for integrating an API safely and predictably.