ops — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ops (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.
Before routing, load:
cat ${CLAUDE_PLUGIN_DATA_DIR:-$HOME/.claude/plugins/data/ops-ops-marketplace}/preferences.json — read configured channels to determine available commandscat ${CLAUDE_PLUGIN_DATA_DIR}/daemon-health.json — if action_needed, surface before routingRoute $ARGUMENTS to the correct ops skill:
| Input | Route to |
|---|---|
| (empty), dash, hq | /ops:ops-dash |
| go, morning, briefing | /ops-go |
| setup, configure, init, install | /ops:setup $ARGUMENTS |
| inbox, unread, messages | /ops-inbox |
| comms, send, whatsapp, email, slack, telegram | /ops-comms $ARGUMENTS |
| fires, incidents, down, sentry | /ops-fires |
| projects, dashboard | /ops-projects |
| status, health-status | /ops:ops-status |
| next, priority, what | /ops-next |
| triage, issues | /ops-triage |
| linear, sprint, board | /ops-linear |
| revenue, money, mrr, costs | /ops-revenue |
| deploy, ship | /ops-deploy |
| merge, prs, ship-prs | /ops-merge $ARGUMENTS |
| marketing, email, klaviyo, ads, meta, seo, campaigns | /ops:ops-marketing $ARGUMENTS |
| ecom, shop, shopify, store, orders, inventory | /ops:ops-ecom $ARGUMENTS |
| voice, call, tts, transcribe, phone | /ops:ops-voice $ARGUMENTS |
| yolo | /ops-yolo |
| doctor, health, fix, diagnose | /ops:ops-doctor |
| monitor, apm, alerts, datadog, newrelic, otel | /ops:ops-monitor $ARGUMENTS |
| settings, credentials, creds, config, reconfigure | /ops:ops-settings $ARGUMENTS |
| integrate, connect, add-api, saas, partner | /ops:ops-integrate $ARGUMENTS |
| speedup, clean, optimize, cleanup | /ops:ops-speedup |
| orchestrate, subagents, agents, dispatch, run | /ops:ops-orchestrate $ARGUMENTS |
| feature, feature-dev, fd, architect-feature, explore-feature | /ops:ops-feature-dev $ARGUMENTS |
| secret-sync, secrets, doppler-sync, drift | /ops:ops-secret-sync $ARGUMENTS |
| home, homey, lights, flow, scene, energy, climate, presence, alarm, smart-home, iot, thermostat, dim, door, lock | /ops:ops-home $ARGUMENTS |
| statusline, status-line, cockpit | /ops:statusline $ARGUMENTS |
If $ARGUMENTS is empty, launch the interactive dashboard: invoke /ops:ops-dash directly.
If CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 is set, use Agent Teams when building dashboard sections in parallel. This enables:
Team setup (only when flag is enabled):
TeamCreate("ops-team")
Agent(team_name="ops-team", name="daily-ops", prompt="Gather fires, inbox, and unread comms status")
Agent(team_name="ops-team", name="engineering", prompt="Gather PRs, CI status, and deploy state")
Agent(team_name="ops-team", name="business", prompt="Gather revenue, Linear sprint, and project progress")
Agent(team_name="ops-team", name="automation", prompt="Check cron jobs, daemon health, and scheduled tasks")If the flag is NOT set, use standard fire-and-forget subagents.
This skill is a router only — it does not call CLI tools directly. All tool usage is delegated to the target skill after routing. See the referenced skill's ## CLI/API Reference section for details.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.