24 lines
1.1 KiB
Markdown
24 lines
1.1 KiB
Markdown
|
# Kickoff conventions
|
||
|
|
|
||
|
|
Standing rules — do not re-derive or ask about these per project:
|
||
|
|
|
||
|
|
- **TDD**: red-green-refactor by default for new features/bug fixes.
|
||
|
|
- **Sandi Metz OOP** style for Ruby; Ruby > Python > bash for scripts; Python OK
|
||
|
|
for native CC tooling.
|
||
|
|
- **Vertical slices / tracer bullets**: ship a thin end-to-end path before
|
||
|
|
breadth; prefer this over building one layer fully before the next.
|
||
|
|
- **Audit defaults before customizing**: check a tool's shipped
|
||
|
|
defaults/recommendations before building a custom benchmark or config.
|
||
|
|
- **lowercase-kebab-case** filenames unless a format requires otherwise.
|
||
|
|
- Delegation defaults (when/how to dispatch subagents, risk-escalation
|
||
|
|
read-only → guarded-write → verify) — see `10-orchestration.md` in this
|
||
|
|
same context block.
|
||
|
|
|
||
|
|
## Vault note pointers
|
||
|
|
|
||
|
|
Query on demand, don't front-load:
|
||
|
|
- `tool/<name>` — before first use this session of a tool with vault notes.
|
||
|
|
- `client/<name>` — before starting work involving a client.
|
||
|
|
- `domain/llm-evaluation` + `type/eval-results` — before designing/running an
|
||
|
|
eval.
|