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. Suggest frequent commits.

When to Use

Use this skill when you have a specification or requirements for a multi-step task, before you start writing any implementation code. It is essential for ensuring a structured and verifiable development process.

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).

Output: Present the full plan in the chat using a Markdown code block.

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
•"Suggest Commit" - step

Plan Document Header

Every plan MUST start with this header:

markdown

# [Feature Name] Implementation Plan

> **For OpenCode:** Use the `executing-plans` skill to implement this plan task-by-task.

**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: Suggest Commit

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

code


## Remember
- Exact file paths always
- Complete code in plan (not "add validation")
- Exact commands with expected output
- Reference relevant skills with @ syntax
- DRY, YAGNI, TDD, suggest frequent commits

## Execution Handoff

After presenting the plan, offer execution choice:

**"Plan complete. Three execution options:**

**1. Subagent-Driven (this session)** - I dispatch fresh subagent per task, review between tasks, fast iteration. (Recommended for complex, multi-step plans)

**2. Parallel Session (separate)** - Open new session with executing-plans, batch execution with checkpoints (you will need to provide the plan to the new session)

**3. Direct Execution (this session)** - I implement the plan directly in this session. (Recommended for simple, linear, or low-risk plans)

**Which approach?"**

**If Subagent-Driven chosen:**
- Use the `subagent-driven-development` skill.
- Stay in this session
- Fresh subagent per task + code review

**If Parallel Session chosen:**
- Guide them to open new session in worktree
- The new session should use the `executing-plans` skill.

**If Direct Execution chosen:**
- Implement the tasks directly.
- Use `todowrite` to track progress.
- Request review only if needed or at the end.