AGENTS.md

2026-10-09

RESEARCH · 1 SOURCE · arXiv cs.AI

arXiv:2610.11007v1 models LLM always-loaded context as a capacitated-assortment problem with censored feedback

This paper formulates the problem of curating fixed per-session context files (e.g., AGENTS.md) for LLM agents as a capacitated-assortment model where instructions consume finite attention (token) capacity and retained instructions incur per-session setup cost. The authors prove an upper bound on optimal file size, show appending every positively valued instruction can be arbitrarily suboptimal, analyze learning under censored feedback (missing instructions only produce signal when they cause harm), provide bounds on required evidence and regret with limited human reviewers, and report experiments showing irrelevant rules in real context files reduce model compliance.

6.0

2026-09-30

CODING · 1 SOURCE · InfoQ AI, ML & Data Engineering

Patrick Debois presents 'Context Is the New Code' at QCon London

At QCon London, Patrick Debois argued for treating context as a first-class engineering artifact—applying SDLC practices (testing, CI/CD, package management, security scanning) to context to scale AI coding agents, control non-deterministic outputs, and preserve organizational knowledge. He discussed standards and tools such as AGENTS.md, referenced models like Claude, and cited context tools (Context7, Ref) and organizational practices for generating, evaluating, distributing, and observing context.

4.0

2026-03-31

CODING · 1 SOURCE · Mistral AI

Spaces CLI: designed for humans and coding agents

Spaces is an opinionated CLI that the authors adapted to be usable both by humans and by LLM-based coding agents. Key additions include flag equivalents for interactive prompts (e.g., --components and a -y mode), an introspectable plugin registry, and generated context.json and AGENTS.md so agents can discover project structure and run end-to-end automation (including generating config.yaml, CI, and deploying to Koyeb).

6.0

2026-03-11

CODING · 1 SOURCE · Mistral AI

Proto team built a Vibe agent that autonomously writes RSpec tests for Rails

Applied AI's Proto team built an autonomous agent on top of Mistral's open-source coding assistant Vibe that reads Rails code, generates or improves RSpec tests, validates style and coverage (via RuboCop and SimpleCov), and runs in CI/CD with no human intervention, operating in parallel across files. They used repository-level AGENTS.md for context and separate file-type 'skills' to improve test completeness and quality, raising their internal quality score from 0.68 to 0.74.

6.0