plan-writing — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited plan-writing (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.
A good plan is a thinking tool, not paperwork. It exists to make the next actions obvious and to tell you when you are finished. Each plan is shaped to its task -- there is no master template to fill in.
Save the plan in the project root as {task-slug}.md, with the slug pulled from the task itself -- "add billing webhooks" becomes billing-webhooks.md. Do not bury it in .aim-agents/, docs/, or a scratch directory.
These are habits, not boilerplate. Every plan is unique to its task.
A handful of meaningful steps beats an exhaustive tree of sub-sub-tasks. List only things you will actually do, one line each. If the plan runs past a single page, it is doing too much -- cut it down or split it.
Vague steps stall; specific ones move.
| Too vague | Concrete |
|---|---|
| "Set up the project" | "Run npm create vite@latest" |
| "Add login" | "Install Lucia, add src/lib/auth.ts and the session middleware" |
| "Polish the UI" | "Apply spacing + dark-mode classes to Sidebar.tsx" |
The test: does the step have an outcome you could point at and verify?
New project: decide the stack first, define the smallest shippable slice, sketch the file layout.
Adding a feature: identify which files change, list new dependencies, decide how you will confirm it works.
Fixing a bug: pin down the root cause, name the exact file and line to change, state the test that proves it is fixed.
Do not staple every helper script onto every plan. Pick the ones that fit the work.
| Working on... | Likely scripts |
|---|---|
| Frontend / React | ux_audit.py, accessibility_checker.py |
| Backend / API | api_validator.py, security_scan.py |
| Mobile | mobile_audit.py |
| Database | schema_validator.py |
| Full-stack | whichever of the above match what you changed |
"Make sure it works" is not verification. Name the concrete check.
| Hand-wavy | Runnable |
|---|---|
| "Verify the component" | "Start npm run dev, click Submit, confirm the toast appears" |
| "Test the endpoint" | "curl localhost:3000/api/orders returns 200 with a JSON array" |
| "Check the theme" | "Open the page, toggle dark mode, confirm contrast holds" |
Use this as a starting shape and bend it to fit -- skip sections you do not need.
# <Task name>
## Goal
One sentence: what gets built or fixed.
## Tasks
- [ ] <specific action> -> Verify: <how you check>
- [ ] <specific action> -> Verify: <how you check>
- [ ] <specific action> -> Verify: <how you check>
## Done when
- [ ] <the headline success condition>
## Notes
<anything worth flagging>Resist adding phases and nested headings unless the work genuinely calls for them. Start minimal; layer in structure only when it earns its place.
[x] as you go and keep the plan current.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.