Contributing Code with Claude Code
This guide is for people who want to write code for Breeze. It assumes you’ll
work with Claude Code (or a compatible agent) —
the repo ships a CLAUDE.md and a set of skills that hand the agent almost all
the project’s conventions automatically. Your job is to point it at the right
work and to hand back finished, self-reviewed, green PRs.
If you only want to report a bug or pitch an idea, you don’t need any of this —
see the top of CONTRIBUTING.md.
The one idea to internalize
Section titled “The one idea to internalize”Breeze doesn’t have a public roadmap. Work is captured as plan documents in
docs/superpowers/plans/.
A plan spells out the goal, the architecture, the tech stack, and a checklist of
tasks — it’s a ready-to-implement work order, written for an agent to execute.
That means a plan is two things at once:
- The roadmap — it’s what there is to build.
- The approval — if a plan exists and is in the open lane, the what and the how are already agreed. You don’t need a separate sign-off to start.
1. Find something to build
Section titled “1. Find something to build”Open plans live in one folder:
Everything in the plans/ root (400+ files) is completed, shipped work kept
for history — ignore it when looking for something to do. Only open/ is live.
-
Browse
docs/superpowers/plans/open/. Each file is a complete work order: goal, architecture, tech stack, a linked design spec, and- [ ]task checkboxes. -
Pick one that fits your appetite. The plan’s own header tells you the blast radius — some are small UI/CRUD jobs, some touch deeper systems.
-
Give Todd a heads-up that you’re taking it (so two people don’t grab the same plan). Then start.
2. …or propose your own
Section titled “2. …or propose your own”Want to scratch your own itch? Great — but the plan comes first.
-
From the repo root, run Claude Code and use the
brainstormingskill to pin down intent and requirements, thenwriting-plansto produce the plan document. -
Drop the finished plan in
docs/superpowers/plans/open/and share it with Todd. -
Wait for approval on the plan. Once it’s a 👍, it’s an open work order like any other — go build it.
3. Build it
Section titled “3. Build it”-
Run Claude Code from the repo root so it loads
CLAUDE.mdand the project skills automatically. Don’t re-explain the conventions — they’re already in context. -
Follow the plan’s
REQUIRED SUB-SKILLnote (usuallysubagent-driven-developmentorexecuting-plans). Work the- [ ]tasks in order and check them off. -
Write tests as you go — the
breeze-testingandtest-driven-developmentskills cover the repo’s patterns (Drizzle mocks, Go table tests, the coverage checklist). New features are expected to ship with tests.
4. Before you hand it over
Section titled “4. Before you hand it over”Two things are your responsibility, not Todd’s. A PR that skips them isn’t ready.
-
Make CI green yourself. Mirror the gate locally and get it passing before you open anything —
test-api,test-web, andtest-agentare the required jobs. You fix your own reds; a red PR isn’t on anyone’s plate yet. -
Self-review your own diff. Run
/code-review(or thepr-review-toolkitagents) against your changes, address what it finds, and then request a human review.
5. Open the PR
Section titled “5. Open the PR”A PR means done, green, self-reviewed, ready to merge — not a discussion venue and not work-in-progress.
-
Branch, and use Conventional Commits (
feat:,fix:,docs:, …). -
Keep it to one concern. Don’t mix a feature, a refactor, and a docs sweep in one PR — small, single-purpose PRs review fast.
-
Reference the plan you implemented in the PR description.
-
Open it against
main. Once it merges, the plan moves out ofopen/into theplans/archive — the open lane always reflects only what’s still available.