Afield guide
/

A real repository case study

Rules that
survive the prompt.

Prompts ask for behavior. Repositories preserve it. The interview project combines written context, reusable skills, executable checks, commit hooks, and independent review so the rule is still present when the conversation is gone.

THE SHORT VERSION A prompt is advice for one run. A repository rule is reusable context plus an executable boundary.

From intent to evidence

Five places
a rule can hold.

Not every rule belongs in a hook. Put guidance where an agent can discover it, deterministic policy in a command, cheap checks at commit time, and independent judgment at review.

Small instruction packages

Teach the trap.
Name the trigger.

These skills are not downloaded magic. They are repository-specific procedures under .agents/skills/, distilled from mistakes, commands, and architectural decisions that kept recurring.

CLI RATCHET

Debt may go down.
Never silently up.

pnpm check:ui
# raw buttons
# swallowed catches
# pages without h1
# hardcoded colours
Read the checker →
HUSKY / PRE-COMMIT

Fast checks before history.

pnpm exec lint-staged
node scripts/check-ui-contract.mjs
Read the hook →
COMMIT MESSAGE

Intent has a grammar.

pnpm exec commitlint --edit $1

feat: add interview timer
fix(api): scope session query
Read commitlint config →
INDEPENDENT REVIEW

A second reader checks intent.

.pr-review.json
├── focus
├── exclude_paths
├── languages
└── instructions
Read review policy →
COPY / ADAPT

Ask your agent to map the enforcement stack.

Use this in the interview repository or adapt the path names to another project.

GO DEEPERRead the implementation, not just this summary.