mu-plan

name	mu-plan
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 mu-plan skill to create the implementation plan."

Context: This should be run in a dedicated worktree (created by mu-arch skill).

Save plans to: docs/plans/YYYY-MM-DD-<feature-name>.md

• (User preferences for plan location override this default)

Process Flow

digraph mu_plan {
    "Read design spec" [shape=box];
    "Scope check:\nsingle subsystem?" [shape=diamond];
    "Suggest decomposition" [shape=box];
    "Map file structure" [shape=box];
    "Define tasks\n(bite-sized, TDD)" [shape=box];
    "Write plan document" [shape=box];
    "Plan review loop\n(dispatch reviewer)" [shape=box];
    "Approved?" [shape=diamond];
    "Fix issues" [shape=box];
    "Execution handoff\n(invoke mu-code)" [shape=doublecircle];

    "Read design spec" -> "Scope check:\nsingle subsystem?";
    "Scope check:\nsingle subsystem?" -> "Map file structure" [label="yes"];
    "Scope check:\nsingle subsystem?" -> "Suggest decomposition" [label="no"];
    "Suggest decomposition" -> "Map file structure" [label="after split"];
    "Map file structure" -> "Define tasks\n(bite-sized, TDD)";
    "Define tasks\n(bite-sized, TDD)" -> "Write plan document";
    "Write plan document" -> "Plan review loop\n(dispatch reviewer)";
    "Plan review loop\n(dispatch reviewer)" -> "Approved?";
    "Approved?" -> "Execution handoff\n(invoke mu-code)" [label="yes"];
    "Approved?" -> "Fix issues" [label="no"];
    "Fix issues" -> "Plan review loop\n(dispatch reviewer)";
}

Scope Check

If the spec covers multiple independent subsystems, it should have been broken into sub-project specs during mu-arch. 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:

# [Feature Name] Implementation Plan

> **For agentic workers:** REQUIRED SUB-SKILL: Use devmuse:mu-code (recommended) or devmuse:mu-code 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]

---

Task Structure

### Task N: [Component Name]

**Covers:** UC-1, UC-3

**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
• Include Covers: UC-xxx per task when a scope artifact exists — this tells the coder which use cases to trace in tests

Plan Review Loop

After writing the complete plan:

1. Dispatch the mu-reviewer subagent in review-plan mode with precisely crafted review context — never your session history. This keeps the reviewer focused on the plan, not your thought process.
   • Provide: PLAN_FILE_PATH (path to the plan document), SPEC_FILE_PATH (path to spec document)
   • The reviewer will validate inputs, build an anchor list (UC-IDs, task numbers, file paths) from the documents, and only emit findings tied to those anchors — preventing hallucinated UCs / class names / file paths.
2. If ❌ Issues Found: fix the issues, re-dispatch reviewer for the whole plan
3. If ✅ Approved: proceed to execution handoff

Review loop guidance:

• Same agent that wrote the plan fixes it (preserves context)
• If loop exceeds 3 iterations, surface to human for guidance
• Reviewers are advisory — explain disagreements if you believe feedback is incorrect

Execution Handoff

After saving the plan, offer execution choice:

"Plan complete and saved to docs/plans/<filename>.md. Two execution options:

1. Subagent-Driven (recommended) - I dispatch a fresh subagent per task, review between tasks, fast iteration

2. Inline Execution - Execute tasks in this session, batch execution with checkpoints

Which approach?"

Invoke devmuse:mu-code to execute the plan. mu-code supports both modes.

Integration

• Invoked by: mu-arch (terminal state)
• Produces: Implementation plan at docs/plans/<name>.md
• Consumed by: mu-code (reads plan, executes tasks)
• Terminal state: invoke mu-code