Writing Plans

---
name: writing-plans
description: Use when you have a spec or requirements for a multi-step task, before touching code
---

# 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 (created by brainstorming skill).

**Save plans to:** `.internal/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:**

```markdown
# [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. Each Task becomes a bead (`bd create -t task --parent <epic-id>`). Steps within tasks use checkbox (`- [ ]`) syntax for human readability.

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

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

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

---
```

## 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`

- [ ] **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"
```
````

**Beads integration:** When executing this plan, the executing skill creates an epic bead for the plan and a child task bead for each Task N. The `- [ ]` checkboxes remain in the markdown for human readability, but task-level tracking uses beads (`bd create`, `bd update --claim`, `bd close --reason`). Dependencies between tasks should be declared with `bd dep add`.

## 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.

## User Review Gate

After self-review passes, **open the plan file in the user's editor** so they can review it, then gate progression with `AskUserQuestion`:

**⚠️ Run `open` as a standalone Bash call** — never chain it after `bd` commands in the same invocation (e.g., `bd close <id> && open file.md`). The combination hangs.

```bash
# Auto-open plan in user's editor (platform-detected)
# macOS:
open "<plan-file-path>"
# Linux (fallback):
xdg-open "<plan-file-path>" 2>/dev/null
# If neither available: just report the path
```

Then immediately use the `AskUserQuestion` tool:

```json
{
  "questions": [{
    "question": "Plan opened in your editor at `<path>`. Review it and let me know when ready.",
    "header": "Plan review",
    "options": [
      {"label": "Approved", "description": "Plan looks good — proceed to choose execution method"},
      {"label": "Needs changes", "description": "I want to revise the plan before proceeding"}
    ],
    "multiSelect": false
  }]
}
```

If the user selects "Needs changes", make the requested changes and re-run the self-review. Only proceed to execution handoff once approved.

If you discovered something reusable, capture it before closing:

```bash
# Only if worth preserving for future sessions:
bd remember "pattern: <planning insight for future tasks>"
```

## Execution Handoff

After the plan is approved, **use the `AskUserQuestion` tool** to offer the execution choice:

```json
{
  "questions": [{
    "question": "Plan complete and saved. How would you like to execute it?",
    "header": "Execution",
    "options": [
      {
        "label": "Subagent-Driven (Recommended)",
        "description": "Fresh subagent per task with two-stage review between tasks — fast iteration, high quality"
      },
      {
        "label": "Inline Execution",
        "description": "Execute tasks in this session using executing-plans — batch execution with checkpoints"
      }
    ],
    "multiSelect": false
  }]
}
```

**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

## Integration

**Called by:** **brainstorming** — this is brainstorming's terminal state. After design approval, brainstorming invokes writing-plans.

**Invokes:**
- **subagent-driven-development** — execution handoff (user choice).
- **executing-plans** — execution handoff (user choice).

**Pairs with:** **stress-test** — optional adversarial review of the plan before execution.