Writing Plans

---
name: writing-plans
description: Use when you have a spec or requirements for a multi-step implementation task, before touching code. Produces a task-by-task plan an engineer with zero codebase context can execute. For a fresh or large project, scaffold project-cartography first so the plan lands in a mapped codebase; execute via executing-plans.
---

# Writing Plans

## Overview

Write comprehensive implementation plans assuming the executing engineer has zero context for the codebase and questionable taste. Document everything they need: which files to touch for each task, the code itself, how to test it, docs to check. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.

Assume a skilled developer who knows almost nothing about this toolset or problem domain, and doesn't know good test design well.

**Save plans to:** a dated file, e.g. `docs/plans/YYYY-MM-DD-<feature-name>.md` (user preferences for plan location override this default).

## Scope Check

If the spec covers multiple independent subsystems, it should have been decomposed during design. If it wasn't, suggest breaking this into separate plans — one per subsystem. Each plan should produce working, testable software on its own.

If the spec has two or more independent components, plan them as lanes (parallel-plans) instead of separate plans when they share contracts.

## Choosing Between Defensible Directions

When two or more approaches both look viable (your own alternatives, or competing plans from different sessions), do not blend them into mush. Pick one using this tie-break order:

1. Correctness and fit to the user's request.
2. Grounding in real files, APIs, tests, and data - not invented structure.
3. Simpler first implementation that does not block the intended future.
4. Better validation and rollback story.
5. Lower token/time cost of execution, once quality is acceptable.

Record the rejected direction and the deciding criterion in one line - the executor should never re-litigate the choice.

## File Structure

Before defining tasks, map out which files will be created or modified and what each one is responsible for. This is where decomposition decisions get locked in.

- Design units with clear boundaries and well-defined interfaces. Each file has one clear responsibility.
- Prefer smaller, focused files over large ones that do too much — edits are more reliable when a file can be held in context at once.
- Files that change together should live together. Split by responsibility, not by technical layer.
- In existing codebases, follow established patterns. Don't unilaterally restructure — but if a file you're modifying has grown unwieldy, including a split in the plan is reasonable.

This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.

## Task Right-Sizing

A task is the smallest unit that carries its own test cycle and is worth a fresh reviewer's gate. When drawing task boundaries: fold setup, configuration, scaffolding, and documentation steps into the task whose deliverable needs them; split only where a reviewer could meaningfully reject one task while approving its neighbor. Each task ends with an independently testable deliverable.

## Bite-Sized Step Granularity

**Each step is one action (2-5 minutes):**
- "Write the failing test" - step
- "Run it to make sure it fails" - step
- "Implement the minimal code to make the test pass" - step
- "Run the tests and make sure they pass" - step
- "Commit" - step

## Plan Document Header

**Every plan MUST start with this header:**

```markdown
# [Feature Name] Implementation Plan

> **For agentic workers:** Execute this plan task-by-task (fresh subagent per task with review between tasks, or inline with checkpoints). Steps use checkbox (`- [ ]`) syntax for tracking.

**Goal:** [One sentence describing what this builds]

**Architecture:** [2-3 sentences about approach]

**Tech Stack:** [Key technologies/libraries]

**Parallel:** [Optional, only when execution will use parallel-plans] <N> lanes, foundation first

## Global Constraints

[The spec's project-wide requirements — version floors, dependency limits,
naming and copy rules, platform requirements — one line each, with exact
values copied verbatim from the spec. Every task's requirements implicitly
include this section.]

---
```

## Task Structure

````markdown
### Task N: [Component Name]

**Files:**
- Create: `exact/path/to/file.py`
- Modify: `exact/path/to/existing.py:123-145`
- Test: `tests/exact/path/to/test.py`

**Interfaces:**
- Consumes: [what this task uses from earlier tasks — exact signatures]
- Produces: [what later tasks rely on — exact function names, parameter
  and return types. A task's implementer sees only their own task; this
  block is how they learn the names and types neighboring tasks use.]

- [ ] **Step 1: Write the failing test**

```python
def test_specific_behavior():
    result = function(input)
    assert result == expected
```

- [ ] **Step 2: Run test to verify it fails**

Run: `pytest tests/path/test.py::test_name -v`
Expected: FAIL with "function not defined"

- [ ] **Step 3: Write minimal implementation**

```python
def function(input):
    return expected
```

- [ ] **Step 4: Run test to verify it passes**

Run: `pytest tests/path/test.py::test_name -v`
Expected: PASS

- [ ] **Step 5: Commit**

```bash
git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"
```
````

## No Placeholders

Every step must contain the actual content an engineer needs. These are **plan failures** — never write them:
- "TBD", "TODO", "implement later", "fill in details"
- "Add appropriate error handling" / "add validation" / "handle edge cases"
- "Write tests for the above" (without actual test code)
- "Similar to Task N" (repeat the code — the engineer may be reading tasks out of order)
- Steps that describe what to do without showing how (code blocks required for code steps)
- References to types, functions, or methods not defined in any task

Placeholders for *client facts* (prices, contacts, codes) are the one exception and are mandatory, not forbidden — see the fact-guard skill.

## Remember
- Exact file paths always
- Complete code in every step — if a step changes code, show the code
- Exact commands with expected output
- DRY, YAGNI, TDD, frequent commits

## Self-Review

After writing the complete plan, look at the spec with fresh eyes and check the plan against it. This is a checklist you run yourself.

**1. Spec coverage:** Skim each section/requirement in the spec. Can you point to a task that implements it? List any gaps.

**2. Placeholder scan:** Search your plan for red flags — any of the patterns from the "No Placeholders" section above. Fix them.

**3. Type consistency:** Do the types, method signatures, and property names used in later tasks match what earlier tasks defined? A function called `clearLayers()` in Task 3 but `clearFullLayers()` in Task 7 is a bug.

If you find issues, fix them inline. If a spec requirement has no task, add the task.

## Execution Handoff

After saving the plan, offer the execution choice:

**"Plan complete and saved to `<path>`. Three execution options:**

**1. Subagent-Driven (recommended)** — dispatch a fresh subagent per task, review between tasks, fast iteration (see the subagent-driven-development skill)

**2. Inline Execution** — execute tasks in this session with review checkpoints (see the executing-plans skill)

**3. Parallel lanes** — several sessions or worktree subagents, one per lane (see the parallel-plans skill)

**Which approach?"**