AGENTS.md

Rama main · réplica de lectura del repositorio original.

# CLAUDE.md

Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.

Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.

## 1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:
- State your assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.

## 2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
- If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

## 3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:
- Don't "improve" adjacent code, comments, or formatting.
- Don't refactor things that aren't broken.
- Match existing style, even if you'd do it differently.
- If you notice unrelated dead code, mention it - don't delete it.

When your changes create orphans:
- Remove imports/variables/functions that YOUR changes made unused.
- Don't remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user's request.

## 4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:
- "Add validation" → "Write tests for invalid inputs, then make them pass"
- "Fix the bug" → "Write a test that reproduces it, then make it pass"
- "Refactor X" → "Ensure tests pass before and after"

For multi-step tasks, state a brief plan:
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]

Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.

---

These guidelines are working if: fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.

---

## 5. Code Structure

- Maximum of 300 lines per file (ideally 150–250).
- One component per file.
- Move logic into custom hooks (`/hooks`).
- Pure functions and utilities—place them in `/lib` or `/utils`.
- If a file is getting too large, break it down into helpers or hooks yourself until the task is complete.
- Avoid “monoliths”—prefer composition of small modules.


## Documentation and Responses

For user documentation and critical procedures (imports, calculations, migrations), use a style similar to ASD-STE100:
- short sentences (preferably up to 20 words)
- active voice
- unambiguous terms
- avoid using synonyms for the same concepts

For code, comments, and standard agent responses, use clear, everyday language.

## Project Context (Stoic Budget)

Detailed policy lives in `.claude/rules/*.md` (security, database, idempotency, api-standards, clean-architecture, frontend-perf, observability, best-practices, effect, design-tokens). Read those before changes in those domains.

**Styling:** every colour, size and weight follows the light and dark theme tokens; no raw hex, MUI colour defaults or Tailwind palette classes. See `.claude/rules/design-tokens.md`.

**Test fixtures:** invented, never lifted from real statements, receipts, the dev DB or the user's data. Keep the shape that matters to the case and make up the content: `'Alza - AirPods Pro'` → `'ACME Store - Wireless Buds'` (same hyphen, two words, a product inside). Same for people, e-mails, domains and IBANs (`Member One`, `member-1@example.com`, `example.co.il`). Name the value once and derive expectations from it.

<!-- entire-agent:begin -->
Read .entire/agent-guide.md for this repository's workflow, source inspection, and verification guidance.
@.entire/agent-guide.md
<!-- entire-agent:end -->