sniper/split_35b_v2.py` as template)
3. Run `mlx-sniper calibrate` on the processed model
4. Test with `mlx-sniper run`
### Dependencies
mlx, numpy, transformers, safetensors, huggingface_hub
### Hardware
Apple Silicon only
test — "launch your managed agent" skill
## What this project is
A Claude Code **skill** (`launch-your-agent`) that helps a **technical founder** build whatever they want on **Claude Managed Agents
build` then `npm start`
- Full local gate (headers + format + client typecheck + server + client tests): `npm run verify`
- Server tests: `npm run test:server`
- Client tests: `npm run test:client
Format code (Black + isort)
make fmt
# Check formatting without modifying
make check
# Run all tests (requires TENSORLAKE_API_URL env var)
make test
# Run a specific test suite
cd tests
Nothing speculative.
No features beyond what was asked. No abstractions for single-use code.
Test: would a senior engineer say this is overcomplicated? If yes, simplify.
### Rule 3 — Surgical Changes
stripe-java
## Testing
- Run all tests: `just test`
- Run a single test class: `just test-one com.stripe.net.HttpClientTest`
- Pass extra Gradle args: `just test --tests com.stripe.SomeTest`
## Formatting
- Format: `just format` (uses
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.