Testing Kimi Code's AGENTS.md Behavior
ytjessie_ · x · 2026-07-18
Combined with screenshots, this post discusses the Agent behavior and configuration of Kimi Code.
The images illustrate an investigation into its documentation and operation: Kimi Code reads AGENTS.md instead of CLAUDE.md; the Instruction Files in the official docs support project-level, global-level, and cross-tool AGENTS.md. The screenshots also mention using packet capture/network monitoring to observe its sent requests, understanding the underlying interactions and the model's "harness" behavior.
Overall, it reads more like a practical hands-on guide for Claude Code / Kimi Code / MCP workflows rather than just a simple content creation post.
More from coding & agent
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- Investment Analyst Asks How to Build a Claude-Based Diligence Agent Stack — Careless_Tie2286 · 2026-09-11
- How Do You Catch Behavioral Regressions in LLM Agents Between Releases? — Beautiful_Belt_601 · 2026-09-11
- Treating agents like 50 First Dates: a 3-layer context system so every conversation doesn't start from zero — evielync · 2026-09-11
- Running the Firefox MCP on Android via Termux, ngrok, and mcp-proxy — Nervous-Strain7544 · 2026-09-11
- Run Firefox MCP on Android: Termux + ngrok tunnel tutorial — Nervous-Strain7544 · 2026-09-11