Skip to content

KunanonJ/superstacks / plugins/superstacks/skills/writing-plans

writing-plans

Verified

Use when you have a spec or requirements for a multi-step task, before touching code

Writing Plans

Overview

Write implementation plans for an engineer who has not seen this codebase or this spec. Assume they write idiomatic code in the project's language once they know the exact interface and the exact test, and that they will make a reasonable choice wherever the plan leaves one open. What they cannot know is what you decided: which files, which names and signatures, which values from the spec, which tests prove each task. Document those. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.

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

Context: If working in an isolated worktree, the user already created it.

Save plans to: the pull request body (a ## Plan section). Do not write plan files under docs/. 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.

Step Granularity

Each step is one action with a checkable result:

  • "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

> Steps use checkbox (`- [ ]`) syntax for tracking.

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

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

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

**Spec:** [path to the spec/design doc this plan implements — the plan
argues from the spec, so the spec travels with it; executors read both]

## 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.]

## Review Focus

[The five input classes or failure modes the spec implies but no task's
tests exercise that are most likely to bite a person using this software
— one line each, naming the input or condition and the behavior a
reasonable person would expect, most likely first. The spec is a vision
document: it says what the software must do, not everything it will
meet, and its silence on an input is not permission for that input to
break the program. Write the list here, once, with the spec in front of
you. Then, for each line, add the test that pins it to the task that
owns the code, in that task's own step style.]

---

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: Implement `function(input: InputType) -> ResultType` in `exact/path/to/file.py`**

One line on the approach when the signature and the test leave a choice
(which library call, which data structure); a code block only for an
algorithm they do not determine.

- [ ] **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"
```

What a Step Contains

A step is done when the implementer can write exactly one reasonable thing from it. That is the whole requirement: unambiguous, not complete. Each kind of step carries what makes it unambiguous and nothing more:

  • A test step: the test's name and its assertions, as code, with the spec's exact values in them.
  • A code step: the exact signature (name, parameters, return type), the file it lives in, and the specific values the spec pins. The implementer writes the body. A body appears only for an algorithm the signature and tests do not determine, or for exact copy the spec fixes.
  • A verification step: the command to run and the output that means it passed.
  • A reference to another task: that task's Interfaces block says what to use; the plan does not repeat that task's code.

A plan is the set of decisions the implementer cannot make alone. A plan longer than the code it describes has written the code instead. Lines that decide nothing ("TBD", "handle edge cases", "add appropriate validation", "write tests for the above", a type or function no task defines) are the opposite failure, and the self-review catches both.

A call that changes another system

When a step calls another system and the call changes something there (it deletes, charges, sends or books), plan for the case where the change happened and you never read the answer: the request timed out, the reply could not be parsed, the process died, or the claim on the row was lost before the result was stored.

Three rules keep the record honest.

  1. Write what you are about to do before you do it. Store every identifier you will need to check the result, and the time of the request, before sending. A retry that looks the other system up again finds it already changed and concludes there was nothing to do.
  2. Decide only from what is written. Count the requests sent (before each send) and the answers read (after each valid answer). A closing state that means "nothing was there" is allowed only when the two counts are equal.
  3. Name a closing state by what was proven. Keep the "verified" time for the outcome the other system confirmed. Give every other closing state its own label and no verified time, so that no report can count it as proof.

Plan the test with the design: a fake of the other system that applies the change and then fails the call.

Generated Lists That Every Open Change Rewrites

A generated file that every change rewrites and that holds whole-tree numbers makes each merge a conflict for every other open change, and each conflict costs a merge of the main branch and a full pipeline run. Split it in two.

  • Rows. One row for the smallest unit a change touches (a module, a source file), one row per line, sorted by key, with an empty line between rows. Each row holds only facts of its own key. Every change regenerates the rows, and a test compares them with a fresh scan.
  • Totals. Anything computed across rows. They are regenerated on request, by whoever ends a batch of merges, and no test compares them.

Prove the split with real merges in a temporary repository: two changes far apart, two neighbouring rows, a row added between two changed rows, and two changes to one row. The last case is the one to write a rule for: it can merge without a conflict into a row that is wrong, so regenerate the rows after every merge of the main branch, not only when a conflict is reported.

Compare a generated list only on what its source alone decides: no dates, no machine paths, no counts that another change can move. Run its guard from every path that can change the source.

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. Step scan: Every step must let the implementer write exactly one reasonable thing, and no step may carry more than that: a line that decides nothing is a gap, a function body the signature and tests already determine is a transcript. Fix both.

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.

4. Review Focus: For each input class or failure mode the spec implies, is there a task whose tests exercise it? The five uncovered ones most likely to bite a person go in the Review Focus section, and each line there gets its test added to the owning task. An empty section means you checked and found none, not that you skipped the check.

5. Proportion: Compare the plan's length to the spec's. A plan several times longer than the spec it implements is a transcript of the program, not a plan. If code blocks are most of the document, replace bodies with signatures, test names and assertions, and check that each step is still unambiguous.

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 and self-reviewing the plan, link it for your human partner to read. If they have already explicitly supplied an execution method, ask them to review the plan and confirm it captures what they want; wait for that review before implementation, then use the preserved method. Otherwise, ask them to review the plan and choose an execution method before implementation.

When no execution method has already been supplied:

"Plan complete in the pull request body. Please review the plan. Which execution approach would you prefer?

  • Subagent-driven - A fresh subagent implements each task and a fresh reviewer checks it before the next one starts, then a whole-branch review at the end. Most thorough; costs a fresh context per task and per review.
  • Native - I implement every task myself in this session, the way this harness runs work, then one fresh reviewer on the most capable model checks the whole branch. Cheapest and fastest; no independent review until the end. Runs well with a mid-tier session model, since the plan carries the design.

For this plan I recommend , because <one sentence from the plan: how much the tasks depend on each other's interfaces, how many there are, what a shipped mistake would cost>. Does the plan capture what you want, and which approach should we use?"

When an execution method has already been supplied:

"Plan complete in the pull request body. Please review the plan. Does it capture what you want?"

If Subagent-driven chosen: implement each task with a fresh subagent and a fresh reviewer before the next task.

If Native chosen: implement every task in this session, then one fresh reviewer on the whole branch.

receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 321kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 321kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 321kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 321kUpdated Claude CodeCodexVerifiedInstall