work-plan — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited work-plan (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.
Define an action plan BEFORE coding. The plan must be validated before implementation.
Questions to clarify:
# Search for similar code
grep -rn "similar_pattern" --include="*.ts" | head -20
# Identify dependencies
cat package.json | grep -A 20 '"dependencies"'Decisions to make:
Break down into atomic tasks of 1-2h max.
## Plan: [Feature name]
### Objective
[Description in 1-2 sentences]
### Files to create
| File | Description |
|---------|-------------|
| `src/xxx.ts` | [Role] |
### Files to modify
| File | Modifications |
|---------|---------------|
| `src/yyy.ts` | [Changes] |
### Tests to write
- [ ] Nominal case test
- [ ] Edge cases test
- [ ] Error test
### Implementation steps
1. [ ] [Task 1]
2. [ ] [Task 2]
3. [ ] [Task 3]
### Identified risks
| Risk | Mitigation |
|--------|------------|
| [Risk 1] | [Solution] |
### Dependencies
- [ ] [Prerequisite 1]~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.