openplan-research — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited openplan-research (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.
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.
Use this after $openplan-core and usually after $openplan-align when the next safe action depends on evidence that is not already in the loaded context.
Research reduces uncertainty. It does not decide scope, architecture, acceptance, bypasses, or durable goal/intent.
Use this skill when:
Do not use this skill to pad obvious work. If the needed fact is already in durable local context, cite it and continue.
$openplan-record or $openplan-docs-init;$openplan-review;$openplan-handoff.BLOCKED instead of inventing a conclusion.Only the active human-facing coordinator asks the human follow-up questions. A delegated researcher reports Human decisions required, Open questions, or BLOCKED.
Research question:
Why it matters:
Scope:
Sources reviewed:
Findings:
Inferences:
Options or implications:
Human decisions required:
Confidence:
Residual uncertainty:
Recommended next route:references/report-contract.md: research report shape.assets/claude-code-command.md: Claude Code command/prompt seed.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.