plan

Plan

Overview

Decompose work into small, verifiable tasks with explicit acceptance criteria. Good task breakdown is the difference between an agent that completes work reliably and one that produces a tangled mess. Every task should be small enough to implement, test, and verify in a single focused session.

When to Use

• You have a spec and need to break it into implementable units
• A task feels too large or vague to start
• Work needs to be parallelized across multiple agents or sessions
• You need to communicate scope to a human
• The implementation order isn't obvious

When NOT to use: Single-file changes with obvious scope, or when the spec already contains well-defined tasks.

The Planning Process

If the caller gives a plan path, write and revise that exact file. Otherwise choose a repo-local path that fits the project, such as docs/plans/YYYY-MM-DD-<feature>.md, plans/<feature>.md, or a caller-established state path.

Step 1: Enter Plan Mode

Before writing any code, operate in read-only mode:

• Read the spec and relevant codebase sections
• Identify existing patterns and conventions
• Map dependencies between components
• Note risks and unknowns

Do NOT write code during planning. The output is a plan document, not implementation.

Step 2: Identify the Dependency Graph

Map what depends on what:

Database schema
    │
    ├── API models/types
    │       │
    │       ├── API endpoints
    │       │       │
    │       │       └── Frontend API client
    │       │               │
    │       │               └── UI components
    │       │
    │       └── Validation logic
    │
    └── Seed data / migrations

Implementation order follows the dependency graph bottom-up: build foundations first.

Step 3: Slice Vertically

Instead of building all the database, then all the API, then all the UI — build one complete feature path at a time:

Bad (horizontal slicing):

Task 1: Build entire database schema
Task 2: Build all API endpoints
Task 3: Build all UI components
Task 4: Connect everything

Good (vertical slicing):

Task 1: User can create an account (schema + API + UI for registration)
Task 2: User can log in (auth schema + API + UI for login)
Task 3: User can create a task (task schema + API + UI for creation)
Task 4: User can view task list (query + API + UI for list view)

Each vertical slice delivers working, testable functionality.

Step 4: Write Tasks

Each task follows this structure:

## Task [N]: [Short descriptive title]

**Description:** One paragraph explaining what this task accomplishes.

**Acceptance criteria:**
- [ ] [Specific, testable condition]
- [ ] [Specific, testable condition]

**Verification:**
- [ ] Tests pass: `npm test -- --grep "feature-name"`
- [ ] Build succeeds: `npm run build`
- [ ] Manual check: [description of what to verify]

**Dependencies:** [Task numbers this depends on, or "None"]

**Files likely touched:**
- `src/path/to/file.ts`
- `tests/path/to/test.ts`

**Estimated scope:** [Small: 1-2 files | Medium: 3-5 files | Large: 5+ files]

Step 5: Order and Checkpoint

Arrange tasks so that:

1. Dependencies are satisfied (build foundation first)
2. Each task leaves the system in a working state
3. Verification checkpoints occur after every 2-3 tasks
4. High-risk tasks are early (fail fast)

Add explicit checkpoints:

## Checkpoint: After Tasks 1-3
- [ ] All tests pass
- [ ] Application builds without errors
- [ ] Core user flow works end-to-end
- [ ] Review with human before proceeding

Step 6: Up-The-Hill Review

A plan is not ready because it exists. Send it uphill through fresh review rounds until an independent plan editor says it is execution-ready.

digraph plan_review {
    "Write current plan" -> "Fresh plan editor";
    "Fresh plan editor" -> "READY" [label="unchanged"];
    "Fresh plan editor" -> "REVISED" [label="fixed"];
    "Fresh plan editor" -> "USER DECISION REQUIRED" [label="blocked"];
    "REVISED" -> "Fresh plan editor" [label="next fresh round, max 5"];
}

1. Dispatch a fresh plan editor with prompts/plan-editor.md.
2. Give it the original request or spec, the plan path, and any caller constraints.
3. If it returns READY, planning is complete.
4. If it returns REVISED, keep the revised plan and repeat with a fresh plan editor.
5. If it returns USER DECISION REQUIRED, stop and present the decision.
6. Stop after 5 editor rounds. If the plan still is not READY, present the latest plan plus the unresolved concern and do not proceed to execution.

Use these verdicts exactly:

• READY: the current plan would let a skilled implementer build the requested result without backtracking; no edits were made.
• REVISED: the current plan had a real execution, architecture, contract, sequencing, or verification problem; the editor fixed it in the plan.
• USER DECISION REQUIRED: requirements conflict or there is no safe autonomous path without a user choice.

The editor must judge the whole plan before acting. Cosmetic rewrites are failures. Missed real plan problems are failures. Score semantic outcome, not prettier prose.

Each review round should leave an artifact trail in the plan report or progress notes:

• Plan verdict
• Plan path
• Current git commit when available, otherwise not committed
• Changed files, or none
• Files inspected

Task Sizing Guidelines

Size	Files	Scope	Example
XS	1	Single function or config change	Add a validation rule
S	1-2	One component or endpoint	Add a new API endpoint
M	3-5	One feature slice	User registration flow
L	5-8	Multi-component feature	Search with filtering and pagination
XL	8+	Too large — break it down further	—

If a task is L or larger, it should be broken into smaller tasks. An agent performs best on S and M tasks.

When to break a task down further:

• It would take more than one focused session (roughly 2+ hours of agent work)
• You cannot describe the acceptance criteria in 3 or fewer bullet points
• It touches two or more independent subsystems (e.g., auth and billing)
• You find yourself writing "and" in the task title (a sign it is two tasks)

Plan Document Template

# Implementation Plan: [Feature/Project Name]

## Overview
[One paragraph summary of what we're building]

## Architecture Decisions
- [Key decision 1 and rationale]
- [Key decision 2 and rationale]

## Task List

### Phase 1: Foundation
- [ ] Task 1: ...
- [ ] Task 2: ...

### Checkpoint: Foundation
- [ ] Tests pass, builds clean

### Phase 2: Core Features
- [ ] Task 3: ...
- [ ] Task 4: ...

### Checkpoint: Core Features
- [ ] End-to-end flow works

### Phase 3: Polish
- [ ] Task 5: ...
- [ ] Task 6: ...

### Checkpoint: Complete
- [ ] All acceptance criteria met
- [ ] Ready for review

## Risks and Mitigations
| Risk | Impact | Mitigation |
|------|--------|------------|
| [Risk] | [High/Med/Low] | [Strategy] |

## Open Questions
- [Question needing human input]

Parallelization Opportunities

When multiple agents or sessions are available:

• Safe to parallelize: Independent feature slices, tests for already-implemented features, documentation
• Must be sequential: Database migrations, shared state changes, dependency chains
• Needs coordination: Features that share an API contract (define the contract first, then parallelize)

Common Rationalizations

Rationalization	Reality
"I'll figure it out as I go"	That's how you end up with a tangled mess and rework. 10 minutes of planning saves hours.
"The tasks are obvious"	Write them down anyway. Explicit tasks surface hidden dependencies and forgotten edge cases.
"Planning is overhead"	Planning is the task. Implementation without a plan is just typing.
"I can hold it all in my head"	Context windows are finite. Written plans survive session boundaries and compaction.

Red Flags

• Starting implementation without a written task list
• Starting implementation before the up-the-hill review returns READY
• Tasks that say "implement the feature" without acceptance criteria
• No verification steps in the plan
• All tasks are XL-sized
• No checkpoints between tasks
• Dependency order isn't considered

Verification

Before starting implementation, confirm:

• Every task has acceptance criteria
• Every task has a verification step
• Task dependencies are identified and ordered correctly
• No task touches more than ~5 files
• Checkpoints exist between major phases
• Plan is saved to a file in the repository
• Up-the-hill plan review returned READY
• The human has reviewed and approved the plan

Prompt Resources

• Use prompts/plan-editor.md for each fresh up-the-hill review round.