Instructions file CodexOpenCode
Instructions for Trusty-Squire/trusty-squire, covering agents.md — rules for ai coding agents in this repository, tl;dr — the three rules that matter most, never claim a publish succeeded without proof, the canonical verification tool and what does not count as proof.
Instructions file
Instructions for Trusty-Squire/trusty-squire, covering claude.md, project overview, objective function (what this project optimizes for), current state and production, deployed, verified end-to-end.
Skill Claude CodeCodex
Use when a coding agent needs to sign up for a website or SaaS, provision an OAuth client or API key, pay a checkout, or otherwise act on a real website on the user's behalf — and the secret or card must NOT land in chat, source code, or a .env file. Trusty Squire is an MCP server that drives a real browser through…
MCP server Claude CodeCodexCursor +2
Trusty Squire signs up / in to websites for you so you don’t have to. Runs locally from the @trusty-squire/mcp npm package.
MCP server Claude CodeCodexCursor +2
Credential broker that signs your AI agent up to SaaS dev tools, within a signed spending mandate. Runs locally from the @trusty-squire/mcp npm package.