ALWAYS invoke when the user mentions Saltzer (e.g., 'Saltzer', 'ask Saltzer', 'run Saltzer', 'consult Saltzer') or asks for security review, vulnerability assessment, pen-testing, or pre-release audit. Principal Application
Explains how claudeloop integrates with claude-agent-sdk (ClaudeAgentOptions, ClaudeSDKClient vs query(), RateLimitEvent, ResultMessage, AssistantMessage, session discovery via list_sessions()) and the never-block-on-a-human design (permission_mode, can_use_tool, AskUserQuestion handling, hooks). Use this whenever building or modifying src/claudeloop/infrastructure/agent/ (the M2+ agent gateway, options builder, message translation, session catalog, capacity probe), whenever the user asks about the Claude Agent SDK, ClaudeAgentOptions fields, session resumption, rate-limit events, or why a run might block on a human. Make sure to consult this before writing any code that calls claude_agent_sdk directly — infrastructure/agent/ is the ONLY place that import is allowed, per the onion architecture (see the claudeloop-architecture skill), and getting the never-block guarantees wrong here defeats the entire purpose of this project.
Use when adding dependencies, reviewing a project's dependency tree, or checking for known vulnerabilities and ownership risk — covers pip-audit, npm audit, govulncheck, lock file hygiene, update policy, and trust assessment.
when debugging TanStack Query/React Query issues, inspecting cache state, troubleshooting API calls, investigating stale data, mutations not updating UI, or infinite refetch loops
112mo agoReviewMountCreate a free account to mount
instructions below are written for any agent. The phone is driven
> through an MCPserver, so any client that speaks MCP can use it: the
> tools appear here under