releases/ClaudeDo
2
0
Fork 0
Code Issues 1 Pull Requests 2 Actions Packages Projects Releases 12 Wiki Activity

docs: add autonomous working-style loop and agent gotchas to CLAUDE.md

Browse Source 
Codifies the brainstorm -> spec/plan -> subagent-driven implementation
-> verify loop, plus project gotchas (release builds, subagent staging,
PathIcon fill, locale parity, test-fake sync).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
mika kuns
2026-06-04 10:36:37 +02:00
parent 39fa83a0a0
commit 9e7f37b5cc
1 changed files with 23 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
CLAUDE.md
View File

@@ -44,16 +44,35 @@ Two-process system communicating over SignalR (`127.0.0.1:47821`):
- Views use compiled bindings (`x:DataType`) - Views use compiled bindings (`x:DataType`)
- ViewModels use `[ObservableProperty]` and `[RelayCommand]` source generators - ViewModels use `[ObservableProperty]` and `[RelayCommand]` source generators
## Working style (autonomous)
For any non-trivial feature, bug, or change, run this loop without hand-holding:
1. **Brainstorm first** (superpowers:brainstorming) — ask clarifying questions one at a time, propose 2–3 options with a recommendation, present a short design, get approval before building.
2. **Write it down** — a spec in `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md` and a step-by-step plan in `docs/superpowers/plans/` (superpowers:writing-plans). Commit the docs.
3. **Implement on main** with superpowers:subagent-driven-development — one subagent per task, TDD, build + test, commit per task with Conventional Commits. Once the plan is approved, do NOT pause for re-approval between tasks; only stop for genuine decisions or blockers.
4. **Trust but verify** — read each subagent's diff and run the build/tests yourself before marking a task done.
5. **Bugs** → superpowers:systematic-debugging (find the root cause before any fix).
6. **Never claim UI works without running it** — explicitly flag visual-verification gaps for the user to check.
Commit freely (per task + the spec/plan docs). Never push without asking.
## Building & Testing ## Building & Testing
`dotnet build ClaudeDo.slnx` requires .NET 9; on .NET 8 build individual projects instead. `dotnet build ClaudeDo.slnx` requires .NET 9; on .NET 8 build individual projects with `-c Release` (a running Worker locks the `Debug` output).
```bash ```bash
dotnet build src/ClaudeDo.App/ClaudeDo.App.csproj # pulls in Ui + Data dotnet build src/ClaudeDo.App/ClaudeDo.App.csproj -c Release # pulls in Ui + Data
dotnet build src/ClaudeDo.Worker/ClaudeDo.Worker.csproj dotnet build src/ClaudeDo.Worker/ClaudeDo.Worker.csproj -c Release
dotnet test tests/ClaudeDo.Worker.Tests # also: Data.Tests, Ui.Tests, Installer.Tests, Releases.Tests dotnet test tests/ClaudeDo.Worker.Tests/ClaudeDo.Worker.Tests.csproj -c Release # also: Data.Tests, Ui.Tests, Localization.Tests, Installer.Tests, Releases.Tests
``` ```
### Gotchas
- **Subagents:** use the `sonnet` model; stage files explicitly by path — never `git add -A` (parallel sessions often leave unrelated WIP in the tree).
- **Icons:** `PathIcon` *fills* its geometry. Line-art/stroke icons must be authored as filled geometry, or rendered with a stroked `Path` — otherwise they render invisible.
- **Localization:** `locales/en.json` and `locales/de.json` keys must stay in parity (Localization.Tests enforces it).
- **Test fakes:** changing `IWorkerClient` / `WorkerHub` / ViewModel constructors breaks hand-rolled fakes in both test projects — update them.
## Docs ## Docs
- `docs/plan.md` — full architecture and design spec - `docs/plan.md` — full architecture and design spec