acaprino/writing-plans

Source: Ported from obra/superpowers -- skills/writing-plans

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 writing-plans skill to create the implementation plan."

Context: This should be run in a dedicated worktree. If working in an isolated worktree, it should have been created via the git-worktrees:wt skill at execution time.

Save plans to: 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 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.

UI/Frontend Visual Checkpoint

If the plan involves UI or frontend work (new views, layouts, components, visual redesigns), generate a standalone HTML mockup before writing the detailed task list:

1. Create a single .html file with React and a UI library (shadcn/ui, Radix UI, daisyUI, or other appropriate library) loaded from CDN (esm.sh, unpkg, cdn.tailwindcss.com), showing the full layout with:
   • All views/screens as navigable tabs or scrollable sections
   • Realistic placeholder content (domain-appropriate, not lorem ipsum)
   • Colors, typography, and spacing matching the design spec
   • Responsive behavior with at least one mobile breakpoint
   • Key states visible (empty, loaded, error, loading)
   • Interactive navigation and state transitions (React useState for tab switching, modals, etc.)
   • The file must open directly in a browser without npm install
2. Save it next to the plan: docs/plans/YYYY-MM-DD-<feature-name>-mockup.html
3. Tell the user to open it in a browser and ask for approval before proceeding
4. Only write the detailed implementation plan after the user confirms the visual direction

This avoids investing in a detailed plan for a layout the user hasn't validated visually.

Skip this step if: the task is backend-only, CLI-only, or the user explicitly says they don't need a mockup.

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.

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:** Use subagent-driven execution (if subagents available) or ai-tooling:executing-plans to implement this plan. Steps use checkbox (`- [ ]`) syntax for tracking.

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

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

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

## 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 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

Remember

• Exact file paths always
• Complete code in every step. If a step changes code, show the code.
• Exact commands with expected output
• Reference relevant skills with @ syntax so engineers can jump to them directly
• 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 -- 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.

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:

"Plan complete and saved to docs/plans/<filename>.md. Ready to execute?"

Execution path depends on harness capabilities:

If harness has subagents (Claude Code, etc.):

• Prefer subagent-driven execution: fresh subagent per task + review between tasks
• Do NOT offer a choice - subagent-driven is the standard approach

If harness does NOT have subagents:

• Execute plan in current session using ai-tooling:executing-plans
• Task-by-task execution with verification at each step