notify-on-completion — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited notify-on-completion (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.
http://127.0.0.1:60766/agent/notifyContent-Type: application/jsontitle (string, required): Concise heading for the notification title (e.g., "Build succeeded", "Tests failed").content (string, required): One to two sentences summarizing the outcome. Include key facts such as what finished, duration, artifact paths, or a brief error summary. Keep under ~950 characters because the server truncates the displayed body to 1000 characters after prefixing the agent.agent (string, required): Short identifier for the calling agent or workflow (e.g., "codex", "ci-run"). Avoid blanks and trailing spaces.The server renders the notification body as <agent>: <content>.
title and content.content (duration, counts, artifact hints, or top error line).jq -n or printf); escape quotes to avoid invalid payloads.agent_name="codex"
title="Feature implemented"
content="The feature was implemented in ${elapsed}s; bundle at dist/."
curl --fail --silent --show-error \
-X POST http://127.0.0.1:60766/agent/notify \
-H "Content-Type: application/json" \
-d "$(jq -n --arg title "$title" --arg content "$content" --arg agent "$agent_name" '{title:$title, content:$content, agent:$agent}')"title and summarize the error in content.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.