Files
plan2code/QUICK-REFERENCE.md
T
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

5.3 KiB

Plan2Code Quick Reference

Commands

Step Command Input Output
Init /plan2code-init None AGENTS.md file
Update /plan2code-init-update AGENTS.md Updated AGENTS.md
0 /plan2code-0-pathfinder A foggy idea pathfinder/map.md + PLAN-DRAFT-.md
quick /plan2code-quick-task Requirements Conversational plan (standalone — not a pipeline step)
review /plan2code-review Scope guidance Review findings + fixes
1 /plan2code-1-plan Requirements PLAN-CONVERSATION-.md + PLAN-DRAFT-.md
1b /plan2code-1b-revise-plan Specs + changes Updated specs
2 /plan2code-2-document PLAN-DRAFT.md overview.md + Phase files
3 /plan2code-3-implement overview.md Implemented code
4 /plan2code-4-finalize overview.md Archived specs
handoff /plan2code-handoff Conversation Self-contained handoff doc in handoffs/

File Structure

specs/
└── <feature-name>/
    ├── pathfinder/                   # From Step 0 (optional, if charted)
    │   ├── map.md                    #   the map: destination, decisions, fog
    │   └── questions/NN-<slug>.md    #   one decision question per file
    ├── PLAN-DRAFT-<date>.md          # From Step 1 (verified plan)
    ├── PLAN-CONVERSATION-<date>.md   # From Step 1 (conversation log)
    ├── overview.md                   # From Step 2
    └── phase-X.md                    # From Step 2

specs--completed/                     # After Step 4
└── <feature-name>/                   # Archived specs

Note: <date> uses YYYYMMDD format (e.g., 20250204)

Key Rules

  • Start NEW conversation for each step (and each implementation phase)
  • ONE phase per conversation (but parallel phases can run in separate instances)
  • Reply "approved" to complete phases
  • 90% confidence required before planning completes
  • Never look in specs--completed/ (it's archived specs)

Phase Status

Checkbox Status Meaning
[ ] Pending Not started
[/] In Progress Agent working (or paused)
[x] Complete Approved

Parallel Execution

When phases have no file conflicts or dependencies, they can run simultaneously:

  1. Documentation Mode auto-detects parallel-eligible phases
  2. Implementation Mode shows selection UI with status for each phase
  3. Run multiple /plan2code-3-implement instances on different phases
  4. [/] status shows which phases are actively being worked on

Quick Troubleshooting

Issue Solution
Lost context mid-phase Attach spec files, say "resume from Task X.Y"
Wrong phase started Say "abort", start correct phase
Need to change plan Use /plan2code-1b-revise-plan
Multiple spec folders Specify which: "Continue with specs/user-auth/"
Need AGENTS.md file Use /plan2code-init to generate one
Update AGENTS.md Use /plan2code-init-update after sessions
Run phases in parallel Check Parallel Execution Groups in overview.md

Workflow Decision

New to a project?
└── /plan2code-init → Generate AGENTS.md for project-specific guidance

Learned something during a session?
└── /plan2code-init-update → Add learnings to AGENTS.md

Too unclaer to plan? (big idea, don't yet know what the questions are)
└── /plan2code-0-pathfinder → chart it, clear one decision per session
    └── then → /plan2code-1-plan (resumes at Phase 4)

Is it a quick, small task?
├── Yes → /plan2code-quick-task (standalone)
└── No → /plan2code-1-plan (full workflow)
         ├── /plan2code-2-document
         ├── /plan2code-3-implement (repeat per phase)
         │   └── OR: plan2code-loop (autonomous alternative)
         └── /plan2code-4-finalize

Need to revise mid-implementation?
└── /plan2code-1b-revise-plan

Autonomous Loop (Alternative)

The plan2code-loop CLI is an alternative to Step 3, not a replacement.

Approach Use When
/plan2code-3-implement You want interactive control per phase
plan2code-loop You want hands-off autonomous execution
plan2code-loop   # Fully interactive - auto-detects specs, prompts for options

Loop Modes

Mode Description
One task per loop (default) One task per agent invocation. Node handles git commits.
One phase per loop All tasks in a phase per invocation. LLM handles git commits. Best for smart models with larger context.

Session state stored per-spec in specs/<feature>/.plan2code-loop/