Claude resources tagged “permissions”
10 curated Claude Code resources tagged permissions in the HeyClaude directory — mostly guides, agents, and mcp servers.
Highlights from this set
Standout entries tagged permissions, picked by their own metadata — trust tier, provenance, documentation, and recency.
All permissions resources
Auto Mode Hard-Deny Policies For Safe Automation
Set autoMode.hard_deny rules to block risky actions in auto mode.
BrowserStack MCP Server for Claude
Official BrowserStack MCP server for running browser and device testing, fetching automation artifacts, and managing test workflows.
Claude Code Auto Mode Policy Auditor Agent
Reviews autoMode.environment trust, the hard_deny/soft_deny/allow precedence, and $defaults splicing so the classifier blocks exfiltration without breaking routine internal work.
Claude Code Auto Mode Policy Review Capability Pack Skill
Review autoMode environment, allow, and deny rules with claude auto-mode CLI checklists.
Claude Code Security Guidance Remediator Agent
Audit a Claude Code setup against official security guidance and produce a ranked remediation plan: permissions, MCP trust, credentials, and hooks.
Claude Code Subagent MCP Scope Guide
Scope MCP servers and permissions cleanly for Claude Code subagents.
MCP Remote Server Security Auditor Agent
Review MCP server adoption in Claude Code using official security documentation.
Permission Design for Claude Agent SDK Agents
Least-privilege Agent SDK permissions: the hooks→deny→mode→allow→canUseTool order, allow/deny rules, modes, and a dontAsk lockdown.
Signal coverage
How these 10 resources score on the trust and safety signals HeyClaude reviews — counted from this set, not the directory as a whole.
A short, calm digest of reviewed Claude resources. Unsubscribe any time.