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.

This plan is a disposable derivative of the spec (where one exists): regenerated from it, thrown away after subagent-driven-development runs, never hand-maintained. Don't restate the spec's why/trade-offs — reference them; drift is prevented by regenerating the plan, not by keeping two documents in sync. Where no spec exists (a medium-sized task), keep this plan's own "why" to 2-3 lines and move straight to tasks.

Stay lean. Don't add spec-kit constitutional gates, EARS templates, PR-FAQ sections, or pre-mortem/red-team role-play — the terminal Codex gate (see Execution Handoff) already covers that ground adversarially.

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

Context: If working in an isolated worktree, the owned subagent-driven-development loop handles that isolation 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.

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:** REQUIRED SUB-SKILL: Use `subagent-driven-development:subagent-driven-development` 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]

## 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
• 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.

Open Questions / Unresolved Assumptions

Every plan ends with this required section, appended after the last task, before handoff. It gives the Codex gate (below) concrete targets for its spec-fidelity check.

## Open Questions / Unresolved Assumptions

- [Ambiguity, unverified assumption, or judgment call this plan made without full certainty — one line each, naming which task it affects.]

"None" is a claim, not a default — write it only after you've actually checked for gaps.

Execution Handoff

After saving the plan (including the Open Questions section above), run the terminal Codex gate before handing off to execution:

1. Finalize the plan and confirm it's saved to its canonical path.
2. Invoke codex-review:codex-plan-review on the saved plan file — it checks two things: internal soundness, and fidelity to the spec's intent (did the plan's how drift from the spec's why?).
3. Loop on verdict: fold accepted findings into the plan and re-run per that skill's own round protocol, until it reaches APPROVED/audit-pass or its round cap.
4. If Codex is unavailable or unauthenticated: disclose that the gate was skipped — do not block on it. The review status (reviewed / skipped-disclosed) travels with the plan into subagent-driven-development.

Then hand off execution:

"Plan complete and saved to docs/superpowers/plans/<filename>.md. Codex review: [APPROVED | skipped — disclosed]. Executing via subagent-driven-development: a fresh subagent per task, review between tasks, fast iteration."

• REQUIRED SUB-SKILL: Use codex-review:codex-plan-review to gate the finalized plan, then subagent-driven-development:subagent-driven-development to execute it.
• Fresh subagent per task + two-stage review