agent-auth instructions

32 tagged agent-auth, measured the same way as everything else here.

DeepTrail/deepsecure

Instructions file

Instructions for DeepTrail/deepsecure, covering claude.md, project overview, development commands, environment setup and install development dependencies.

52 6mo ago A 1,603 tokens original Apache-2.0

skills AGENTS.md

02

scalekit-inc/skills

Instructions file CodexOpenCode

AGENTS.md instructions for scalekit-inc/skills, covering agents.md, layout, invocation, writing bar and after a skill edit.

2 6d ago A 584 tokens

add-mcp-oauth

03

scalekit-inc/skills

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).

2 6d ago A 67 tokens

check-agentkit-prod

04

scalekit-inc/skills

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).

2 6d ago A 79 tokens

scalekit-inc/skills

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).

2 6d ago A 84 tokens

audit

06

kanoniv/auth-action

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".

2 5mo ago A 65 tokens

delegate

07

kanoniv/auth-action

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".

2 5mo ago A 61 tokens

scope

08

kanoniv/auth-action

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 ".

2 5mo ago A 54 tokens

captcha-mcp

09

zekebuilds-lab/captcha-mcp

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.

1 19d ago A tokens not measured original MIT

mcp-identity

10

zekebuilds-lab/mcp-identity

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.

0 3mo ago A tokens not measured

mcp-l402-gate

11

zekebuilds-lab/mcp-l402-gate

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.

0 3mo ago A tokens not measured

synauth

12

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.

0 6mo ago A tokens not measured original MIT

At most 3 mods per repository are shown here — the rest are on their repository pages: