Recovered from crashed session (Node OOM). Repo contains full P0-P6 scaffold: plugin.json/marketplace.json, AGENTS.md, ADRs 0001-0006, lh CLI (init/index/graph/lane/run/memory/host/report/doctor), 10 .github/agents, 12 CLI skills, instructions, context7 mcp.json, and unit/e2e test suite. Fixed: run.mjs read --in-tokens/--out-tokens but tests and CLI docs use --input-tokens/--output-tokens, so telemetry totals were always 0. Now accepts both forms. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
715 B
715 B
applyTo, description
| applyTo | description |
|---|---|
| ** | Project instructions for contributors working on redsen-lean-harness itself. |
redsen-lean-harness Contributor Rules
- Work in ESM
.mjsmodules. - Require Node >= 20.
- Add zero native dependencies.
- Keep CLI output terse; LLMs consume it.
- Put shared contracts in
src/lib/. - Export command modules with the project command signature.
- Keep command implementations imperative and deterministic.
- Prefer small pure helpers over hidden global state.
- Keep
.github/behavior aligned with AGENTS.md. - Do not duplicate long behavior in prompts or skills.
- Validate with existing scripts only.
- Never write secrets to config, memory, tests, or fixtures.