writing-plans — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited writing-plans (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
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: If working in an isolated worktree, it should have been created via the superpowers-uml:using-git-worktrees skill at execution time.
Input: The spec is the UML design model in Astah Pro (docs/superpowers/specs/YYYY-MM-DD-<topic>-design.asta). Read it with the Astah Pro MCP tools before writing the plan — the model elements and diagrams are the requirements you are decomposing into tasks.
Save plans to: docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md
If the design model 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.
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.
This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.
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.
Each step is one action (2-5 minutes):
Every plan MUST start with this header:
# [Feature Name] Implementation Plan
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers-uml:subagent-driven-development (recommended) or superpowers-uml:executing-plans 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.]
**Design model:** `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.asta`
[The model elements and diagrams that bind the whole plan — packages,
shared interfaces, cross-cutting diagrams. Name them exactly as they appear
in Astah Pro.]
---### 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.]
**Realizes:**
- [The model elements and diagrams in Astah Pro this task implements, named
exactly as they appear in the model. The implementer queries these before
coding and updates them if implementation proves them wrong; the reviewer
checks the code against these and queries nothing else.]
- [ ] **Step 1: Write the failing test**
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**
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**
git add tests/path/test.py src/path/file.py git commit -m "feat: add specific feature"
Every step must contain the actual content an engineer needs. These are plan failures — never write them:
**Realizes:** block naming model elements that do not exist in the design modelAfter writing the complete plan, look at the design model with fresh eyes and check the plan against it. This is a checklist you run yourself — not a subagent dispatch.
1. Model coverage: Walk the design model's elements and diagrams with the Astah Pro MCP tools. Can you point to a task whose Realizes: block claims each one? List any gaps — an unrealized model element is either a missing task or a model element that should not exist.
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.
4. Model reference validity: Does every name in every Realizes: block exist in the design model? A task pointing at a model element that isn't there sends its implementer and reviewer looking for nothing.
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.
After saving the plan, offer execution choice:
"Plan complete and saved to `docs/superpowers/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 using executing-plans, batch execution with checkpoints
Which approach?"
If Subagent-Driven chosen:
If Inline Execution chosen:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.