🔌
Plugins
Loading...
Showing 30 of 23002 results
Free AI-powered SEO toolkit — audit websites, plan content strategy, optimize pages, generate schema markup, cluster keywords, and track AI visibility. Works with any website or codebase.
Fast, token-efficient MCP for SearXNG metasearch. Privacy-respecting search across 70+ engines with stdio + streamable-http transports, Docker, and optional rendered (Playwright) fetch for JS-heavy pages. Self-hostable. The underlying server is also usable independently of Claude Code via `uvx --from git+https://github.com/88plug/searxng-mcp searxng-mcp`.
Build, diagnose, and verify SeatLayer integrations inside an existing application.
Anthropic 공식 security-guidance 통합 — Write/Edit/MultiEdit pre-hook 25 위험 패턴 무료 검출
Wiki autoorganizado (patrón LLM Wiki de Karpathy) + capa propia de ingesta diaria de noticias: un cron recoge RSS y Claude escribe el radar del día filtrado por tus temas de interés. Todo en español y en Markdown plano. Basado en claude-obsidian v1.9.2 de AgriciDaniel (MIT, crédito en ATTRIBUTION.md).
Self-evolving AI second brain. Auto-learns from sessions, discovers tools, maintains a local knowledge base, and self-critiques code quality.
Agentic workflow with memory and tribal knowledge. Transforms Claude from goldfish to elephant with persistent knowledge across sessions.
AI-powered personal memory layer for Claude Code — persistent memory, live integrations (Gmail, GitHub, Asana, Slack), proactive monitoring, and MCP server for Claude Desktop
PDCA-native Knowledge Work OS with Cross-Plugin Orchestrator — 18 skills, 17 Pokemon agents, 31 MCP tools, Artifact Viewer, Cycle Memory with Self-Evolution, Code Engineering Lane, and zero-key adaptive fetch
Multi-model code review, Q&A, and adversarial debates using Codex + Gemini CLI tools
Cross-vendor second-opinion code review client commands (/second-opinion:start, /second-opinion:models). Does not auto-register an MCP server on install; the external mcp-second-opinion server is opt-in - register it with `claude mcp add second-opinion --transport http --url http://127.0.0.1:8080/mcp` once it is running.
Get 1-3 independent second opinions from fresh Claude reviewers to strengthen your reasoning before presenting to the user.
Runs code reviews using external LLM CLIs (OpenAI Codex, Google Gemini) on uncommitted changes, branch diffs, or specific commits. Bundles codex-mcp-server for direct MCP tool access to Codex.
Pre-commit secret gate: a PreToolUse hook scans staged changes and blocks commits carrying secrets, plus a semantic review subagent. Zero config.
Secrets lifecycle with masking: set, get, list, rotate, delete, validate, run-with-secrets, and a web UI (/secrets:*). Bundles the PostToolUse output-masking hook so plugin installs mask credentials with no host script setup.
Inject and audit 1Password secrets via the op CLI: op:// references with op run/op inject, an always-ask permission gate, and an opt-in deny-capable PreToolUse audit hook. Use for API keys, tokens, credentials, .env secrets, OP_SERVICE_ACCOUNT_TOKEN, or 1Password.
Secure Boot certificate-rotation suite — triage and remediate the Microsoft Secure Boot 2011→2023 UEFI CA rotation (CAs expiring 2026) across Dell PowerEdge / iDRAC9 bare metal, Ubuntu/Linux servers, and Harvester HCI / KubeVirt guest VMs: the PK→KEK→db trust chain, per-platform fixes (iDRAC BIOS-staged keys applied on reboot, self-authenticating manual `db` append via the existing 2011 KEK, the Harvester OVMF v1.6.0 floor with ephemeral-vs-persistent NVRAM triage), and audit via mokutil / efi-readvar / racadm bioscert / Redfish.
Security scanning: quick/full/deep scans (gitleaks, git history, pip-audit), finding explanations, and risk-graded permission audits (/security:*).
The pre-release security gate for any repository. Catches PII, secrets/credentials, and supply-chain risk before they ship. Runs parallel, multi-agent audits across data files, git history, source, and frontend, and consolidates them into a single severity-ranked report with a PASS / REVIEW / BLOCK verdict. Stands alone, or serves as foundry's SECURITY gate when both are installed.
Two complementary JavaScript/TypeScript web security skills: web-security-review traces data flow and reports only proven vulnerabilities; web-security-hardening performs an applicability-aware OWASP ASVS 5.0.0 gap assessment across browser controls, input/files, identity/sessions/secrets, frameworks, storage, and deployment.
Two complementary JavaScript/TypeScript web security skills: web-security-review traces data flow and reports only proven vulnerabilities; web-security-hardening performs an applicability-aware OWASP ASVS 5.0.0 gap assessment across browser controls, input/files, identity/sessions/secrets, frameworks, storage, and deployment.
Security hardening skills for GitHub Actions pipeline hardening and CI security.
Security reviewer for AI-generated and vibe-coded apps — hunts the hardcoded secrets, broken row-level security, and prompt-injection sinks that coding assistants ship by default, then drives a scan, fix, and rescan loop with honest, CWE-mapped findings.
面向 AI 生成与 vibe coding 应用的安全审查专家——专抓编码助手默认会带上的硬编码密钥、失效的行级安全（RLS）和提示注入注入点，然后驱动"扫描—修复—复扫"闭环，输出诚实、映射到 CWE 的发现。