writing-plans · diff
git:20260327.39c77f1 to git:20260327.8972e9a
17 added, 20 removed. Audit A to A.
---
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:** `docs/plans/YYYY-MM-DD-<feature-name>.md`
+ **Save plans to:** The active conductor track directory: `conductor/tracks/{track_id}/plan.md`
+ If no conductor track exists, create one first using the `/orchestrator-supaconductor:new-track` flow.
## 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 Claude:** REQUIRED SUB-SKILL: Use orchestrator-supaconductor:executing-plans 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: Commit**
```bash
git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"
```
````
## 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, frequent commits
## Conductor Integration
- When invoked with `--output-dir` and `--spec` parameters (from Conductor orchestrator):
- - Save plan.md to the specified `--output-dir` (NOT `docs/plans/`)
- - Read spec from `--spec` path
- - Read project context from `--context-files` paths
- - Include DAG section if `--include-dag=true`
- - After saving, do NOT offer execution choice — return control to orchestrator
- - Update `--metadata` checkpoint to `PLAN: PASSED`
-
- When these parameters are absent, fall back to the standalone workflow below.
-
- ## Execution Handoff (Standalone Mode)
+ This skill is part of the Conductor workflow. All plans are saved to the active track directory.
- After saving the plan, proceed directly to execution — **do NOT ask the user which approach to use.**
+ **When invoked by the Conductor orchestrator** (with `--track-dir` and `--spec` parameters):
+ - Read spec from `--spec` path
+ - Read project context from `conductor/product.md`, `conductor/tech-stack.md`
+ - Save plan to `{--track-dir}/plan.md`
+ - Include DAG section for parallel execution
+ - Update track's `metadata.json` checkpoint to `PLAN: PASSED`
+ - Return control to orchestrator — do NOT start execution
- **Default: Subagent-Driven execution in this session:**
- - **REQUIRED SUB-SKILL:** Use orchestrator-supaconductor:subagent-driven-development
- - Stay in this session
- - Fresh subagent per task + code review
- - Execute ALL tasks autonomously to completion
+ **When invoked standalone** (no parameters):
+ - Look for the active track in `conductor/tracks.md`
+ - Read its `spec.md` for requirements
+ - Save plan to `conductor/tracks/{track_id}/plan.md`
+ - Update track's `metadata.json` checkpoint to `PLAN: PASSED`
+ - After saving, announce the plan summary and HALT — do NOT start execution
+ - The user should run `/orchestrator-supaconductor:implement` or `/orchestrator-supaconductor:go` to execute