Writing Plans

Overview

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

Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.

Announce at start: "I'm using the pitroom-writing-plans skill to create the implementation plan."

Context: If working in an isolated worktree, it should have been created via the pitroom-worktrees skill at execution time.

Save plans to: docs/pitroom/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 broken into sub-project specs during brainstorming. If it wasn't, suggest breaking this into separate plans — one per subsystem. Each plan should produce working, testable software on its own.

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 should have one clear responsibility.
• You reason best about code you can hold in context at once, and your edits are more reliable when files are focused. Prefer smaller, focused files over large ones that do too much.
• Files that change together should live together. Split by responsibility, not by technical layer.
• In existing codebases, follow established patterns. If the codebase uses large files, 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.

Worker Tier

Every task names the worker tier that implements it, on its own line right under the heading: **Worker:** cheap, **Worker:** standard or **Worker:** capable. pitroom run --plan uses it when the executor names no worker; the user's config maps tiers to workers (tiers).

• cheap: the task text contains the complete code (implementation is transcription plus testing), or a single-file mechanical fix.
• standard: several files with integration concerns, or an implementer working from prose.
• capable: design judgment or broad understanding of the codebase.

Turn count beats token price: the cheapest models take 2-3× the turns on multi-step work. The user prefers the free tier, so start with cheap for everything a cheap worker can plausibly do and raise only the tasks that need more; a failed cheap task costs one retry on a higher tier. When you are truly unsure between two tiers for a task that is costly to redo, take the higher.

Bite-Sized Task 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:

# [Feature Name] Implementation Plan

> **For agentic workers:** REQUIRED SUB-SKILL: Use pitroom-driven-development to implement this plan task-by-task (each task runs as `pitroom run -i --plan <this file> --step N`). Steps use checkbox (`- [ ]`) syntax for tracking.

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

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

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

**Spec:** [path to the spec/design doc this plan implements — the plan
argues from the spec, so the spec travels with it; executors read both]

## 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

Task headings are exactly ### Task N: <name>: pitroom run --plan finds tasks by them, and a task runs until the next heading of the same or a higher level.

### Task N: [Component Name]

**Worker:** cheap | standard | capable

**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"
```

Workers never commit: an implementer skips commit steps, and the primary commits after the task's review, when it applies the patch. Write the commit step anyway; it tells the primary what to commit and how to word it.

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

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 — not a subagent dispatch.

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 you used in later tasks match what you defined in earlier tasks? A function called clearLayers() in Task 3 but clearFullLayers() in Task 7 is a bug.

4. Headings and tiers: every task has a ### Task N: heading with a unique N and a **Worker:** line.

If you find issues, fix them inline. No need to re-review — just fix and move on. If you find a spec requirement with no task, add the task.

Execution Handoff

After saving the plan, optionally have a read-only worker check it with plan-document-reviewer-prompt.md (fill {{PLAN_FILE}} and {{SPEC_FILE}} with sed as in pitroom-brainstorming, run it with pitroom run --task-file). Then offer:

"Plan complete and saved to docs/pitroom/plans/<filename>.md. Two execution options:

1. Pitroom-driven (recommended) - a worker implements each task in an isolated copy, another model reviews it, I apply and commit between tasks

2. Inline - I execute the tasks myself in this session, with the same checkpoints

Which approach?"

Either way: REQUIRED SUB-SKILL: pitroom-driven-development (its "Inline execution" section covers option 2).