writing-a-plan — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited writing-a-plan (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
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.
Plan before you build so you don't drift or thrash. Scale the plan to the task — a one-liner needs no plan; a feature does.
their callers. Understand the existing patterns before proposing changes.
order. Each step should be something you can finish and check.
TaskCreate with the steps. This shows the useryour plan and is fed back to you each turn so you work through it.
in_progress with TaskUpdate whenyou start it and completed the moment it's done — one at a time, not batched.
TaskCreate with the revisedsteps rather than silently abandoning it.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.