Skip to content

hashgraph-online/awesome-codex-plugins / plugins/AgentDrives/agentdrives-mcp/skills/check-agent-access

check-agent-access

Unverified

Use when you or the user must choose a tool, API or provider for a task, or someone asks "can my agent use X?": whether an AI agent can sign up for and use each product on its own, from AgentDrives' test drives.

Check agent access

AgentDrives' agent signs up for each product like a new customer, does real work, tries to pay and leaves. Each product gets a level from L0 to L5 for how far an agent gets on its own.

Find tools for a task

GET https://agentdrives.com/api/find-tools?task=send+an+invoice

The products we drove that do the task, best first. Each has its level, gets_in_alone (our agent got in with no person), where it stopped and the drive date (tested_at).

Check one product

  1. Find its slug: GET https://agentdrives.com/api/tools?query=
  2. Read its drive: GET https://agentdrives.com/tools/.md (Markdown) or GET https://agentdrives.com/api/tools/.json (JSON with every attempt).

Over MCP

Connect to https://agentdrives.com/api/mcp (no key). choose_provider_for_task {"task": "send an invoice"} finds tools; get_provider {"slug": "stripe", "brief": true} reads one.

Read the answer

  • L0 Read-only: Agents can read about it, but there is nothing to use.
  • L1 Needs a person: Agents can't get in on their own.
  • L2 Gets in: An agent gets in on its own but does less than half the core work.
  • L3 Does the work: An agent gets in on its own and does half the core work or more.
  • L4 Runs on its own: An agent does the core work and can leave on its own.
  • L5 Autonomous: All of that, and it can pay on its own for the work.
  • stop: the checkpoint where our agent stopped, with the evidence.
  • tested_at: the drive date. A product can change after it.

Not listed yet

POST https://agentdrives.com/api/suggest {"url": "example.com"} asks us to drive it. Anyone can send one.

finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 318kUpdated Claude CodeCodexUnverifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 318kUpdated Claude CodeCodexUnverifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 318kUpdated Claude CodeCodexUnverifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 196kUpdated Claude CodeCodexVerifiedInstall