behavioral-contracts-guidelines

name	behavioral-contracts-guidelines
description	Behavioral guidelines to reduce common LLM coding mistakes before writing any code
allowed-tools	["Read","Grep","Glob"]
license	MIT
load_when	["writing_code","reviewing_code","refactoring_code"]
inputs	[{"name":"task_description","type":"string","required":true},{"name":"existing_code","type":"code","required":false}]
outputs	[{"name":"implementation_plan","type":"numbered_steps","format":"[Step] → verify: [observable_check]"}]
constraints	["think_before_coding_required",{"max_lines_before_simplify_check":50},"touch_only_what_task_requires","define_success_criteria_before_starting"]

Behavioral Contracts — Guidelines

Behavioral guidelines to reduce common LLM coding mistakes when writing, reviewing, or refactoring code.

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

Deep-dive note. Las 4 reglas canónicas son siempre-on y viven en .claude/contracts/behavioral-contracts.md (inyectadas vía CLAUDE.md y subagent-context.py). Este archivo es el material de referencia con ejemplos — no necesitás invocarlo como skill, ya estás operando bajo el contrato.

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.