Coding Pipeline

A disciplined 4-phase workflow for any non-trivial coding task. Each phase has a clear purpose, explicit exit criteria, and a loop-back rule when things go wrong. The phases exist because AI agents' default failure mode is blind iteration: edit → build → edit → build → give up. This skill forces hypothesis-driven work, one-fix-at-a-time discipline, root-cause verification, and bounded debugging.

This is a rigid skill — follow the phases exactly. Do not skip, merge, or reorder.

Core Rule

Every non-trivial task — bug fix, feature, refactor — goes through all 4 phases in order:

┌─────────────┐    ┌──────────┐    ┌───────────────┐    ┌─────────────┐
│  1 PLANNER  │───▶│ 2 CODER  │───▶│  3 VALIDATOR  │───▶│  4 DEBUGGER │
│ hypothesis  │    │ one fix  │    │ build + root  │    │ max 3 tries │
└─────────────┘    └────┬─────┘    └───────┬───────┘    └──────┬──────┘
       ▲                │                  │                   │
       │                │ unclear cause    │ fails             │ new hypothesis
       └────────────────┴──────────────────┴───────────────────┘
                        loop back to PLANNER

Skipping a phase or jumping straight to Phase 2 is the failure mode this skill prevents.

Quick Reference

Phase 1 — Planner

Goal: Understand the task and formulate an explicit hypothesis before any code change.

Required outputs:

1. Task breakdown — what is actually being asked? Break into the smallest independent units.
2. Hypothesis — one sentence in the form: "I believe [symptom] is caused by [cause], because [evidence]."
3. Scope — which files/modules are in-bounds, which are explicitly out-of-bounds
4. Success criteria — how Phase 3 will verify this is fixed (not just the symptom gone)

Forbidden in Phase 1:

• Editing any code
• Running build or test commands to "see what happens"
• Multiple parallel hypotheses — pick one, commit to it
• Vague hypotheses ("something with the auth flow") — sharpen until specific

Exit criteria: Hypothesis is concrete, testable, and you can point to why this is the cause — not just what looks broken.

Loop-back trigger: If during Phase 2 or 3 the hypothesis turns out wrong, return here. Do not patch on top of a broken hypothesis.