software: message and silent-resolution censuses, frozen feature matrices for ports, hash-claimed inherited tests, and downstream consumers pinned by commit SHA.
**How we write** — [`writing-with-ai.md`](.claude/rules/writing-with-ai.md): internal vs external
return _site_not_found_error(site_url)
return f"Error: {str(e)}"
```
## Running tests
```bash
pytest test_gsc_server.py -v
```
No credentials needed — all Google API calls are mocked with `unittest.mock`.
## Docker
plugin locally
make docker-mcp
# Cross-compile for all platforms
make docker-mcp-cross
```
### Testing
```bash
# Run all tests
make test
# Run integration tests specifically
make integration
# Run long-lived
user install/runtime files and public
README/LICENSE/CHANGELOG material. Never stage internal docs, research,
benchmarks, tests or fixtures, logs/results, signing or credential material,
environment files, private paths/memory, or unrelated local work. Verify
TypeScript to JavaScript in `dist/`
- `npm run start` - Run with ts-node (ESM mode)
### Testing
- `npm test` - Run all tests with Vitest
- `npm run test:ui` - Run tests with interactive
entry
point is `mcp-windbg`, which speaks MCP over stdio or streamable-http.
## Build / test / run
Python 3.10+ with the `uv` package manager. CDB must be installed for the live
Sparkle (>= 2.6.0) is the only external dependency (auto-updates via GitHub Releases).
No test suite exists. Validate manually by building and running.
## Development Rules
**Always manually test.** After every change
JSON resource files should list all known models regardless of subscription tier.
## Docker Test Image
- Docker-backed Rust and TypeScript tests build `docker/test-agent/Dockerfile` directly in-process and cache the image
example needs tools, skills, or MCP servers, install them inside the container during setup.
## Testing Examples (ACP v2)
Examples should be validated against v2 endpoints:
1. Start the example: `SANDBOX
JavaScript source files (`.js`, `.mjs`, `.cjs`).
- Prefer `.ts`/`.tsx` for runtime code, scripts, tests, and tooling.
- If touching old JavaScript, migrate it to TypeScript instead of extending it.
## Monorepo + Tooling
document TypeScript APIs unless they are exported and implemented in those files.
## Tests
- TypeScript SDK tests should run against a real running server/runtime over real `/v1` HTTP APIs, typically using
中文说明**:改了什么、为什么、影响面(涉及哪些模块/会话类型)
- 附**实际测试验证**:贴出跑过的命令和关键结果(`bun run build`、`bun run test`、相关 e2e),不要只写「应该没问题」;需要 live 验证的先 `bun run switch:here && bun run daemon:restart
that go beyond what the skills answer — ROAS scaling, ad-account architecture, positioning, copy-testing systems, brand voice at scale, anything that needs human judgment + media-buying experience rather than
stripe-dotnet
## Testing
- Run all tests: `just test` (auto-installs correct .NET version)
- Run a specific test: `just test-one TestClassName` or `just test-one FullyQualifiedName`
## Formatting
- Format: `just format
memos from iPhone/iCloud
## Quick Start
```bash
cd ~/Sites/minutes
cargo build # Build Rust workspace
cargo test -p minutes-core --no-default-features # Fast tests (no whisper model)
cargo run --bin minutes
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.