Instructions file
Instructions for DeepTrail/deepsecure, covering claude.md, project overview, development commands, environment setup and install development dependencies.
32 tagged agent-auth, measured the same way as everything else here.
Instructions file
Instructions for DeepTrail/deepsecure, covering claude.md, project overview, development commands, environment setup and install development dependencies.
Instructions file CodexOpenCode
AGENTS.md instructions for scalekit-inc/skills, covering agents.md, layout, invocation, writing bar and after a skill edit.
Skill Claude CodeCodex
Adds MCP OAuth so an agent can protect the user's MCP server. Use when the user wants MCP OAuth or to protect their MCP server. It does not add API keys or client credentials (that's add-api-auth) or expose AgentKit tools over MCP (that's expose-agentkit-mcp).
Skill Claude CodeCodex
Checks AgentKit go-live so an agent can sign off only when every item is PASS or WAIVE with a reason. Use when the user wants AgentKit production, or to go live AgentKit. It does not write a connected account or token (that's integrate-agentkit) or check SaaSKit go-live (that's check-saaskit-prod).
Skill Claude CodeCodex
Implements SaaSKit login in the Next.js App Router so an agent can add login, callback, session cookies, and logout. Use when the user wants SaaSKit Next.js or App Router auth. It does not write generic Node login (that's implement-saaskit) or write Django, FastAPI, or Flask auth (that's implement-saaskit-python).
Skill Claude CodeCodex
View the kanoniv-auth audit trail. Shows every action the agent took - delegations, scope verifications, tool calls, and results. Filter by agent, action type, or time range. Use when asked to "show audit log", "what happened", "show the trail", or "audit".
Skill Claude CodeCodex
Cryptographic delegation for AI agents. Scope-confines what Claude Code can do in this session using Ed25519 delegation tokens. Every action is verified before execution and signed for the audit trail. Use when asked to "delegate", "restrict scope", "authorize", or "sudo mode".
Skill Claude CodeCodex
Quick scope change for an active delegation. Re-delegates with new scopes, keeping the same agent name and TTL. Use when asked to "change scope", "add code.edit", "switch to read-only", or just "/scope ".
MCP server Claude CodeCodexCursor
Charge AI agents per-call without accounts. PoW solve = free tier, Lightning = paid tier. Runs locally from the @powforge/captcha-mcp npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor
DoI score lookup, vouch event builder, and offline schnorr verify for AI agents. Runs locally from the @powforge/mcp-identity npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor
L402 Lightning paywall + DoI score gate for MCP tools: challenge, verify, score. Runs locally from the @powforge/mcp-l402-gate npm package. Needs 2 environment variables to run.
dennischoubot-glitch/synauth-mcp
MCP server Claude CodeCodexCursor
SynAuth MCP Server — Biometric approval for AI agent actions via Face ID. Runs locally from the synauth-mcp Python package.
At most 3 mods per repository are shown here — the rest are on their repository pages: