evotown-handoff — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited evotown-handoff (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.
When a task should continue on another engine or team, do not message them in chat directly. Queue a handoff on Evotown.
evotown-agent-setup.py handoff \
--to-team finance \
--title "Expense review" \
--message "Please verify the summary and approve or reject."Or target a specific engine:
evotown-agent-setup.py handoff --to-engine hermes-bob --message "..."Requires EVOTOWN_INGEST_TOKEN and prior register.
POST {EVOTOWN_URL}/api/v1/jobs/from-engine
Authorization: Bearer {EVOTOWN_INGEST_TOKEN}
{
"kind": "handoff",
"source_engine_id": "openclaw-alice",
"target_team_id": "finance",
"title": "Handoff",
"message": "..."
}The receiving machine's Connector will lease the job and trigger local OpenClaw/Hermes Gateway.
Load the evotown-dispatch-complete skill when executing Evotown dispatch jobs.
When this agent finishes the leased job, report completion (do not rely on hook HTTP alone):
evotown-agent-setup.py complete --job-id <job_id from task payload> --status succeeded --summary "..."Or POST run.completed to /api/v1/events with the same run_id as the dispatch job.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.