Files
jparkerweb b78b3cd6a3 Document Pathfinder and community feedback across the contributor docs
Moves the README's deep material into .readme/ (walkthrough, autonomous
loop, status line, metrics, test bot) and brings AGENTS.md, the .agents-docs
set and QUICK-REFERENCE.md in line with Step 0 and the metrics ingestion
flow.

AI Assisted
2026-08-08 12:39:29 -07:00

2.9 KiB

Walkthrough: one feature, start to finish

A REST API for task management, from a sentence to archived specs. Every block below is a separate conversation — that's the whole trick.

Back to README


Session 1 — Plan

You:  /plan2code-1-plan
      I want to build a REST API for a task management application.

AI:   🤔 [REQUIREMENTS ANALYSIS]
      Six questions. Four of them I need answered before I can size this.
      ...

AI:   🤔 [TECH STACK]
      Proposing Fastify + Postgres + Zod. I don't pick this alone — sign off?

You:  approved

AI:   🤔 [ARCHITECTURE DESIGN]
      ...

AI:   🤔 [TRANSITION DECISION]
      Confidence: 92% (gate is 90%). Assumptions written to the draft: 3.
      → specs/task-api/PLAN-DRAFT-20260804.md

Two files land: the draft, and a PLAN-CONVERSATION-*.md log of how you got there.

Started foggy instead? Run /plan2code-0-pathfinder first. When its map clears it writes a PLAN-DRAFT that Step 1 picks up at Phase 4, with requirements and scope already answered.


Session 2 — Document

You:  /plan2code-2-document
      specs/task-api/PLAN-DRAFT-20260804.md

AI:   📝 [DOCUMENTATION]
      Creating specs/task-api/overview.md
      Creating specs/task-api/Phase 1.md   Project setup           (6 tasks)
      Creating specs/task-api/Phase 2.md   Data model              (8 tasks)
      Creating specs/task-api/Phase 3.md   API endpoints          (11 tasks)
      Creating specs/task-api/Phase 4.md   Authentication          (7 tasks)

      Parallel execution groups: Phase 3 and Phase 4 don't share files.

Sessions 3…N — Implement, one phase each

You:  /plan2code-3-implement
      specs/task-api/overview.md

AI:   ⚡ [PHASE 1: Project setup]
      (Phase 1 is the next unchecked phase.)
      ...
      ✓ 6/6 tasks. Checkboxes updated in Phase 1.md and overview.md.
      Next: Phase 2 — Data model (8 tasks). New conversation.

Repeat. New conversation each time. It always finds the next open phase itself.

When you reach a parallel group, it offers you the choice — open a second agent, take the other phase, and the [/] marks keep them from colliding.

Optional, any time: /plan2code-review for an independent second opinion on what just landed.


Final session — Finalize

You:  /plan2code-4-finalize
      specs/task-api/overview.md

AI:   🧹 [VALIDATION]
      All 32 tasks verified against the phase specs. 2 gaps found and fixed.

AI:   🧹 [DOCUMENTATION REVIEW]
      README needs the new /tasks endpoints. AGENTS.md is current.

AI:   🧹 [SPEC CLEANUP]
      Moved specs/task-api/ → specs--completed/task-api/

      Implementation complete.

If requirements move mid-build

Don't patch the code and hope the specs catch up. Run /plan2code-1b-revise-plan — it edits the specs (and only the specs), so the drawing and the build stay in agreement.