Securely share passwords with your Agents A tool called secret-scratch, published as the TypeScript library @inixiative/secret-scratch, intercepts secrets typed into coding-agent chats before inference, replacing them with opaque references such as †m1.1 and storing the real values in a 0600 scratch-pad file under ~/.secret-scratch/. The tool ships as a drop-in Agent Client Protocol middleware proxy that wraps Claude ACP, Codex ACP and Gemini CLI ACP agents, as a stdio MCP server exposing the secret_scratch and secret_pipe tools, and as a library for custom harnesses, with zero runtime dependencies on Node.js 20+ and Bun 1.4+. It matters because pasting an API key or private key into an agent chat otherwise sends the secret to the model provider and leaves it in session transcripts, tool logs and crash dumps. Securely send secrets to your AI agent with $$value without the LLM, transcript, or logs ever seeing them. You type: Put $$sk live 9876543210 into .env.local as STRIPE KEY, then push it to GitHub Actions. Agent sees: Put †m1.1 into .env.local as STRIPE KEY, then push it to GitHub Actions. Agent calls: secret scratch action: "env", ref: "†m1.1", path: ".env.local", key: "STRIPE KEY" secret pipe envFile: ".env.local", key: "STRIPE KEY", command: "gh secret set STRIPE KEY" Agent gets: { ok: true, exitCode: 0 } Agent tries: cat .env.local - BLOCKED .env.local is held by secret-scratch Zero runtime dependencies. Works with Node.js 20+ and Bun 1.4+. Ships three ways to integrate: 1. Drop-in Agent Client Protocol ACP middleware proxy secret-scratch --