openplan-html-brief — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited openplan-html-brief (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 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.
Use this as a better temporary frontend for human understanding. It turns agent output into a concise, readable HTML page.
.html file./tmp/openplan-brief-<timestamp>.html.Keep it simple:
Use calm status colors:
Do not let color be the only signal; include text labels.
<!doctype html>
<html lang="en">
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>OpenPlan Brief</title>
<style>
:root { color-scheme: light; font-family: Inter, ui-sans-serif, system-ui, sans-serif; }
body { margin: 0; background: #f6f7f9; color: #1f2937; }
main { max-width: 1080px; margin: 0 auto; padding: 28px; }
header { margin-bottom: 18px; }
h1 { margin: 0 0 6px; font-size: 28px; letter-spacing: 0; }
h2 { margin: 22px 0 10px; font-size: 18px; }
.meta { color: #667085; font-size: 14px; }
.strip { display: grid; grid-template-columns: repeat(auto-fit, minmax(180px, 1fr)); gap: 10px; }
.tile, .card { background: white; border: 1px solid #e5e7eb; border-radius: 8px; padding: 14px; }
.label { color: #667085; font-size: 12px; text-transform: uppercase; letter-spacing: .04em; }
.value { margin-top: 4px; font-weight: 650; }
.ok { border-left: 4px solid #16a34a; }
.warn { border-left: 4px solid #d97706; }
.bad { border-left: 4px solid #dc2626; }
ul { padding-left: 20px; }
code { background: #f2f4f7; padding: 2px 5px; border-radius: 4px; }
table { width: 100%; border-collapse: collapse; background: white; border: 1px solid #e5e7eb; }
th, td { text-align: left; padding: 10px; border-bottom: 1px solid #e5e7eb; vertical-align: top; }
th { background: #f9fafb; font-size: 13px; color: #475467; }
</style>
<main>
<header>
<h1>OpenPlan Brief</h1>
<div class="meta">Scope: ... · Generated: ...</div>
</header>
<section class="strip">
<div class="tile"><div class="label">Mode</div><div class="value">Review</div></div>
<div class="tile"><div class="label">Result</div><div class="value">No blocking findings</div></div>
<div class="tile warn"><div class="label">Human Decision</div><div class="value">Needed</div></div>
</section>
<section>
<h2>Summary</h2>
<div class="card"><ul><li>...</li></ul></div>
</section>
</main>
</html>If the HTML summarizes work for another agent, pair it with $openplan-handoff. The HTML is for people; the handoff snapshot is for agents.
For Claude Code, use assets/claude-code-command.md as a slash command or prompt seed.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.