A deterministic layer between untrusted content and agent actions: it removes the hidden layer, remembers where data came from, and keeps calls inside the boundaries of the intent. | A deterministic layer between untrusted content and AI agent actions: it removes the hidden layer and remembers the provenance
Latest release v0.5.0 — Cordon 0.5.0 · 10 Sept 2026
1 file for Codex and OpenCode: cordon AGENTS.md — 1,405 tokens loaded in every session.
AGENTS.md A 1,405 tok These files are ilyautov/cordon's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.