Credential Brokers

Supervised coding, brief to merged PR. The agent writes a spec, works it, runs your gates, and hands the diff to reviewers that argue with it before you ever look.

21 skills

The messy part, before there is anything to build. Name the outcome, find the assumption that would sink it, and test that one first. What survives gets cut into specs a delivery loop can pick up.

12 skills · 3 agents · hooks

Run Jira and Confluence from a conversation, including reviewed Jira or Jira Align refresh with capability-scoped write-back.

14 skills · hooks

Ask a question, get an answer with citations you can check. It runs from a two-minute lookup to a multi-week investigation with its own folder, and argues against its own findings before handing them over.

12 skills · 2 agents · hooks

Start from what the customer is trying to do and end at a screen someone could build. Journey, copy, flows, visual craft — and a reviewer that asks about the empty state and the focus ring you forgot.

13 skills · 1 agent · hooks

Build the web surface, then prove it holds up. HTML, CSS, and JS with a real token system, a WCAG 2.2 AA target, and Core Web Vitals measured rather than asserted. A reviewer reads the diff for the regressions those three tend to hide.

9 skills · 1 agent · 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

Official Convex plugin for Claude Code with bundled Convex skills, the convex-expert subagent for code-writing, a runtime-error monitor, and MCP access for backend development, schema design, real-time features, auth, file storage, scheduled jobs, and AI agents.

16 skills · 1 command · 2 agents · 1 MCP server · hooks

SOC2, HIPAA, and GDPR compliance validation, secrets scanning, compliance checklists, and regulatory documentation

1 command · 1 agent

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

45 advanced engineering skills: agent designer, agent workflow designer, RAG architect, database designer + schema designer + SQL assistant, migration architect, observability designer, dependency auditor, changelog generator, API design reviewer, API test suite builder, CI/CD pipeline builder, MCP server builder, skill security auditor, skill tester, performance profiler, focused-fix, browser-automation, full-page-screenshot, git-worktree-manager, monorepo-navigator, codebase-onboarding, interview-system-designer, runbook-generator, spec-driven-workflow, secrets-vault-manager, env-secrets-manager, pr-review-expert, self-eval, tc-tracker, feature-flags-architect, kubernetes-operator, chaos-engineering, ship-gate, slo-architect (error-budget + multi-window burn-rate alerts per Google SRE Workbook), tech-debt-tracker, agent-regression-evals, coding-agent-rollout, commit-craft, agent-run-forensics and i18n-localization. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.

48 skills · hooks