AgentGuard — security review & secure-by-design for agentic AI (OWASP Agentic 2026 + LLM 2025 + CWE). Use when auditing or designing code that uses LLMs, tool-calling, memory/RAG, MCP or multi-agent.
Use when generating the read-only data-access tools a customer-support agent uses to diagnose an end user's live state — reading a project's backend to propose a tool catalog plus the database access SQL (restricted read-only role, column grants, row-level security), for mandatory human review. Triggers: "discover…
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
Cursor rule "aspectcode" from Aspect-Research/aspectcode, covering aspect code knowledge base, golden rules, recommended workflow, when changing code and how to use the kb files.
Architecture-first, reduction-first workflow for code changes, debugging, refactoring, and cleanup. Use to trace the owning path, prefer no edit and subtraction before additions, replace obsolete behavior instead of layering around it, keep scope closed, refute your own diagnosis and fix before believing them, verify…
Before material coding decisions, apply Higher-Order Decision Architect — first principles, multi-order consequences, inversion, systems, probability, competence, antifragility; strict output format when advising decisions.
Método de trabalho do projeto (loop plan/code, docs vivos).
★not rated 2 12d agoA250 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: