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.
Codebase onboarding tour protocol (repo-tour). Applies when the user asks to onboard onto the codebase, explain how the project works, generate or refresh onboarding docs, or asks where to start reading.
Trace the impact / blast radius of a code change and prove it didn't break other features — run after a fix, before commit/PR/push. Language- and framework-agnostic; works by discovering the project's own conventions. Apply when the user asks "did this break anything", "what else does this affect", "check the impact"…
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…
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.
A text-lint rule for checking writing produced by generative AI. Text linting means automatically checking text for issues against set rules.
★not rated 2 6mo agoA0 tokens
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: