Security review skill for risky tool calls and prompt injection attempts — pre-execution gate for autonomous agents.
community ops
Ironclaw Agent Guard
Security review skill for risky tool calls and prompt injection attempts — pre-execution gate for autonomous agents.
54/100 140 GitHub stars
Updated Mar 15, 2026
#security#guard#prompt-injection
What it does
Same corner
Related skills in ops
Sentry MCP
partnerSentry's official MCP server. Search issues, fetch stack traces, query events, and triage incidents from the agent.
#sentry#errors#observability
ops 84
Data Plugin (Cowork)
anthropicQuery, visualize, and interpret datasets — write SQL, run analysis, and build dashboards via Anthropic Cowork.
#data#sql#cowork
ops 80
Grafana MCP
partnerSearch dashboards, query Prometheus/Loki/Tempo data sources, and triage incidents in Grafana.
#grafana#observability#monitoring
ops 78
Coming soon
Built something better? Submit your skill.
The submission portal opens next sprint. For now, ship to GitHub and tag claude-skill.
Free PDF
Get all skills as a PDF
The full Skills Bank, organized by category, with install commands and 1-line verdicts.
- ✓ 47 tools, ranked by use case
- ✓ 5 mini case studies of $500K founders
- ✓ Starter stack vs Scale stack
- ✓ No fluff. Built by Maxime, used daily.