Operator Cheatsheet

Aufgaard Operator Cheatsheet

Daily checks (no invocation — happens automatically)

| Surface | When | What you see | |---|---|---| | SessionStart hook | Every Claude Code session open | 🟢 Daily deployment overview — gateway uptime / plugins loaded / errors / yesterday's spend | | PreToolUse(Bash) hook | Every shell command | bash-vet auto-vets; BLOCK-tier rejects before execution | | PreToolUse(Edit on .claude/) hook | Writes to agent-config files | skill-vetter auto-vets; BLOCK-tier prevents commit | | PostToolUse(Task) hook | Subagent task completion | output-vetter verifies the claim against actual state | | Background monitors | Continuous | Push notifications inline: 429-imminent / silent-failure detected / gateway-down / regression-catalogue match / dangerous-skill landed |

Invocable skills (you ask)

Quick checks (single MCP)

• /aufgaard:vet-bash — vet a specific shell command
• /aufgaard:vet-skill — vet a third-party skill before installing
• /aufgaard:vet-config — vet agent-config files (CLAUDE.md, AGENTS.md, .cursor/rules)
• /aufgaard:cost-overview [period] — cost dashboard + 429 prediction
• /aufgaard:health-check [scope] — deployment vitals
• /aufgaard:should-i-upgrade — upgrade safety advisor
• /aufgaard:silent-failures [period] — recent silent-failure detections
• /aufgaard:verify-claim "" — verify agent's stated outcome
• /aufgaard:find-swallowed-exceptions — scan Python for silent error masking

Marquee (all 7 MCPs)

• /aufgaard:production-audit — comprehensive 35-pattern audit; calls all 7 MCPs in parallel; one-page report

When to use which (decision tree)

What's the symptom?
├── Cost / billing concern              → /aufgaard:cost-overview
│   └── 429 imminent specifically       → cost-overview shows 429 status inline
├── Cron / scheduled job concern        → /aufgaard:silent-failures
├── Should I install this skill         → /aufgaard:vet-skill
├── Did my agent's claim match reality  → /aufgaard:verify-claim
├── Should I run this bash command       → /aufgaard:vet-bash
├── Should I upgrade this package        → /aufgaard:should-i-upgrade
├── Is my agent code error-handling solid → /aufgaard:find-swallowed-exceptions
├── Is my deployment healthy            → /aufgaard:health-check
├── Just got a PR with .claude/ changes → /aufgaard:vet-config
└── End-to-end review                    → /aufgaard:production-audit

Backing MCPs (also installable standalone via PyPI)

| Skill family | MCP | PyPI install | |---|---|---| | vet-bash | bash-vet-mcp | pip install bash-vet-mcp | | vet-skill / vet-config | openclaw-skill-vetter-mcp | pip install openclaw-skill-vetter-mcp | | cost-overview | openclaw-cost-tracker-mcp | pip install openclaw-cost-tracker-mcp | | health-check | openclaw-health-mcp | pip install openclaw-health-mcp | | should-i-upgrade | openclaw-upgrade-orchestrator-mcp | pip install openclaw-upgrade-orchestrator-mcp | | silent-failures | silentwatch-mcp | pip install silentwatch-mcp | | verify-claim / find-swallowed-exceptions | openclaw-output-vetter-mcp | pip install openclaw-output-vetter-mcp |

What this is NOT

• ❌ Not a SaaS — runs entirely locally, no hosted backend, no telemetry
• ❌ Not a runtime sandbox — observes + advises; doesn't kill agents or block deploys (except via the bash-vet / skill-vetter hooks, which return verdicts the agent can override with explicit user intent)
• ❌ Not a generic FinOps / SAST / monitoring rebrand — purpose-built for the AI-deployment shape
• ❌ Not a substitute for production discipline — it's a tool kit; the discipline is yours

What's covered vs not

23 of 35 documented production-AI failure patterns are covered (see production-patterns skill for the full catalogue). 12 are uncovered — flagged honestly in audit reports. The uncovered patterns cluster in observability-completeness, deploy-config security, runtime-monitoring extensions, and cross-model deception. These are the next-build frontier.

When to escalate

• 0 critical, few high findings → maintenance mode; the existing checks are sufficient
• 3+ critical findings → run a deeper review; the catalogue lists named patterns and remediations
• Pattern not in the catalogue → the catalogue is biweekly-refreshed via the venture's research instance; if you have a recurring pattern that's missing, that's a signal worth recording

Lead-gen footer (always available)

The [Production-AI MCP Suite Bundle](https://temurah.gumroad.com/l/production-ai-mcp-suite) ($29) includes the 8-page Field Reference PDF — full 35-pattern catalogue with verbatim operator-incident sources, MCP coverage map, audit rubric, and 7-MCP cheat sheet.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: temurkhan13
• Source: temurkhan13/aufgaard
• License: MIT

Install and usage instructions live in the source repository linked above.