Bug Hunt Loop
by NeuroSquad teamVersion 1updated Oct 2, 2026
The app shows everything it will install and asks once before anything runs.
The canvas
About this template
One agent that reproduces a bug before it touches the code, finds the root cause, proves the fix with a test and writes down what happened.
What's inside
- Fixer (Claude Code) with everything it needs connected by arrows.
- Repro terminal: a shell the agent runs commands in (
terminal_run), and you watch it happen. - Repro browser: a real Chrome the agent can navigate, click, type into and screenshot, for bugs you can only see in a page.
- systematic-debugging skill (from skills.sh): a step-by-step root-cause method the agent loads on demand. It ships helper scripts, so the import dialog flags it.
- Bug report note with a template: what happens, what you expected, steps, logs. The agent appends its findings under it.
How to use
- Fill in the Bug report note.
- Press Enter on the Fixer's pasted prompt (edit it first if you like).
- The agent reproduces, writes a failing test, fixes, re-runs, and reports root cause and fix in the note.
The browser card runs Chrome for Testing, which the app downloads by itself.
More templates
See all- OfficialFeaturedCoding
Long-Running Project with Memory
by NeuroSquad team2 agents · 5 cards
For a project that lasts weeks: decisions, conventions and gotchas go into a shared memory, and come back automatically in later sessions and to the other agent. What's inside…
- #memory
- #mem0
- #long-running
- #multi-agent
1 like1 download - OfficialFeaturedCoding
Worktree Crew: Lead + Parallel Workers
by NeuroSquad team3 agents · 6 cards
A lead agent splits a big change into independent tasks and runs two workers in parallel, each in its own git worktree, so they never overwrite each other's files. What's inside…
- #multi-agent
- #git-worktree
- #refactoring
- #kanban
- OfficialFeaturedCoding
Test-First Pair
by NeuroSquad team2 agents · 4 cards
Test-driven development split between two agents: one only writes tests, the other only writes the code that makes them pass. Neither can quietly weaken the other's work. What's…
- #tdd
- #testing
- #pair-programming
- #multi-agent
Put your squad to work
Free for Windows and macOS. Bring the agents you already use.
Linux is coming later.
The first-run wizard can install an agent CLI, Git and the dictation model for you — or skip each step.