================================================================================
AGNOSTIC-AI
================================================================================
Tags: agnostic-ai, developer-tools, ai, open-source
URL: https://chemaclass.com/talks/agnostic-ai/
--------------------------------------------------------------------------------

One spec, every AI CLI. Write your rules, skills, agents, hooks and MCP servers
once, and sync them to the native files that 25 AI coding tools actually read.

Your team uses Claude Code, a colleague prefers Codex, and someone still has
Copilot open. Each tool wants its own files, so the same conventions, skills and
hooks end up copied in several places, and the copies drift apart without a
single error. The tools are not the interesting part here. The workflow is.

We start with what we want from an agent and which part of its setup delivers
each outcome: instructions and rules as hints, hooks and permissions as
guarantees, skills, agents and MCP servers to get work done. Then we follow that
setup through a few tool switches, see where it drifts, and compare two fixes:
symlinks, and agnostic-ai, which keeps one spec and writes the native files 25
AI coding tools read. We close with the trade-offs and with questions for the
room about what belongs in a shared agent setup.

--------------------------------------------------------------------------------

- 2026-09-15 | ACT Berlin #14 [Berlin, Germany] (EN) - One spec, every AI CLI
(https://luma.com/act14)

================================================================================