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

Save plans to: docs/superpowers/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.

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 superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.

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

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

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

---

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`

- [ ] **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
• 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.

HTML Companion Offer (Personal Fork)

This section is added by the tobin-superpowers fork and is not present in the upstream superpowers skill. It defines an optional step that produces a shareable HTML companion to the markdown plan before execution handoff.

When to Run

Run this after the Self-Review loop is clean and before the Execution Handoff prompt. The plan is finalized at that point, so the companion will not be stale by the time the user shares it.

The Offer

Ask exactly once, as its own message:

"Would you like an HTML companion for this implementation plan to share with your team? (yes/no)"

• If no: continue to Execution Handoff with no changes.
• If yes: generate the companion per the rules below, save it next to the markdown, then confirm both file paths in a single short message before proceeding to Execution Handoff.

How to Generate

Read skills/shared/html-companion-guide.md for output rules, style guidelines, the color palette, and the HTML skeleton. Treat that guide as authoritative for everything not specified here.

Rendering Priorities for an Implementation Plan

A plan is read by a teammate trying to understand what is being built, in what order, and where the risks sit. Optimize for skimmability.

• Plan summary header. Feature name, total task count, and an estimated scope cue (e.g. "12 tasks across 3 phases"). Sits directly under the document header. Pull the feature name and task count from the plan.
• Phase or subsystem grouping. If the plan organizes tasks under phases or subsystems, render those as collapsible-feeling sections with clear headings. If the plan is flat, render a single task list.
• Tasks as a structured checklist. Each task becomes one row in a checklist. The row should surface, at a glance:
  • Task title and number
  • Files touched (Create / Modify / Test) as inline code chips
  • Verification command (the Run: line) as inline code
  • Status pill if the plan tracks status Do not bury this metadata inside paragraph prose — it should be readable without reading the surrounding text.
• Risk and dependency callouts. Any task with a flagged risk, a cross-task dependency, or a "watch out" note should render as a warning callout in the row, visually distinct from regular tasks.
• Body content (code blocks per step) is preserved per task — render multi-line code in <pre> blocks with the system monospace stack.
• Footer. The relative path to the source markdown plan, per the shared guide.

Output

• Filename: same base name as the markdown, with .html extension.
  • Example: docs/superpowers/plans/2026-05-11-auth-redesign.html
• Do not stage or commit the HTML. Leave it unstaged for the user to decide whether to track it.
• Do not modify the markdown file in any way.

Execution Handoff

After saving the plan, offer execution choice:

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

1. Subagent-Driven (recommended) - I dispatch a fresh subagent per task, review between tasks, fast iteration

2. Inline Execution - Execute tasks in this session using executing-plans, batch execution with checkpoints

Which approach?"

If Subagent-Driven chosen:

• REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development
• Fresh subagent per task + two-stage review

If Inline Execution chosen:

• REQUIRED SUB-SKILL: Use superpowers:executing-plans
• Batch execution with checkpoints for review