1Password (Touch ID-gated)

Work with Cloudflare through wrangler, the cf CLI, cloudflared and the REST API inside the project's account, zones and name prefixes: writes to another project's Workers, buckets, tunnels or zones are refused, and credentials stay out of command lines and the transcript.

1 skill · hooks

Work with Linode inside the project's tag boundary: resources are created with the project tag, and writes to another project's resources are refused.

1 skill · hooks

Adversarial review with two independent Claude reviewers, Opus 5.5 and Sonnet 5.5 at effort high: run the reviewers, confirm each ran on its model and effort, reproduce every finding before trusting it, and turn attack inputs into tests. Includes a script that tells a quiet sub-agent from a hung one.

1 skill · 1 agent

Run Google's Antigravity CLI (agy) headless as a second-opinion code reviewer, refuse to trust its exit code, and report every finding to the user verbatim before touching any code.

1 skill

Run OpenAI's Codex CLI non-interactively as a second opinion, and report every finding it returns to the user verbatim before touching any code.

1 skill

Run DeepSeek V4.1-Flash at effort max through a pinned, sandboxed DeepSeek Harness (dsh) as a second-opinion code reviewer, refuse a run that did not produce a real review, and report every finding to the user verbatim before touching any code.

1 skill

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.

hooks

AgentDB (external: maintained in ruvnet/agentdb, pinned to commit 27678c3, plugin 3.6.0): agentdb's own standalone MCP server pinned to [email protected] (vector memory with get/list/update/delete for records, patterns and skills, hybrid keyword + vector episode search and an opt-in local cross-encoder, an opt-in aidefence injection guard on memory writes, reflexion, skills, outcome feedback, capabilities report), a memory-specialist agent, 3 skills, /agentdb-status, and the agentdb mod guard that keeps secrets out of memory and refuses delete/reset unless allowed. Complements ruflo-agentdb, which reaches AgentDB through ruflo's server

3 skills · 1 command · 1 agent · 1 MCP server

Install the "AAS Security Engineer" workflow plugin from Agentic Awesome Skills.

12 skills

Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture

24 skills · 2 agents

SAST analysis, dependency vulnerability scanning, OWASP Top 10 compliance, container security scanning, and automated security hardening

5 skills · 3 commands · 2 agents