Standard
AGENTS.md is a plain-text file convention giving AI coding agents project-specific context and instructions, akin to CLAUDE.md and .cursorrules files.
OpenCode, Copilot CLI and Claude Code read instruction files meant for other agents, a dev.to guide reports. A rule can load from a file you never edited, or not load at all, so the loaded-file list comes before any prompt rewrite.
Reality
Claude Code 2.1.277 through 2.1.280 read AGENTS.md only when a remote feature flag resolved true, and 2.1.281 fixed it. Repos relying on the file got no project instructions with telemetry off or on Bedrock, Vertex, Foundry and gateways, according to a dev.to write-up.
Reality
Anthropic's Claude Code mods, on by default from 2.1.287, let JavaScript or TypeScript code rewrite prompts, block tool calls and approve permission requests. For teams, the governance question moves from what the agent is told to which code it runs.
Perspective Coverage
5 publishersReality
Cloudflare's cloudflared 2026.9.3 adds an --allowed-mail flag that limits a Quick Tunnel to approved email addresses via a one-time PIN. Public stays the default, so the safeguard works only if whoever starts the tunnel, increasingly a coding agent, adds the flag.
Reality
Relipa's AI development workflow wraps a coding agent in six stages and fixes the tests before any code is written. Most of its published detail covers the workspace plumbing that runs before a model is ever called.
Reality
AI code reviewers lose hosted rule ingestion first on self-managed GitLab, Azure DevOps Server and Bitbucket Data Center, a dev.to comparison says. Of the three mechanisms it compares, only a pass/fail rule can block a merge, and vendors tend to put that one on paid tiers.
Reality
Eval harness agents-md-evals found 25 of 26 assertions passed identically with or without a 755-line AGENTS.md file. The finding rests on that one file, and it assumes the agent loaded the file in the first place.
Reality
The model documentation concedes Astra asks for clarification more often than GPT-5.6 Sol and sometimes stops early. Every remedy on the page is more instruction text, loaded into the same context the docs blame for stalls.
Reality
A dev.to post credits Anthropic with running the same model and the same prompt under two harnesses, 20 minutes and $9 for a broken result against six hours and $200 for a working one. The hourly spend barely moved.
Reality
Claude Code started reading AGENTS.md on September 18, but only where no CLAUDE.md sits in the working directory or any parent above it. Monorepos need a stub file per package or a change to the instructionFiles setting.
Reality
Version 2.1.277 reads a shared AGENTS.md when no CLAUDE.md is in scope. The documented exceptions cover first sessions, telemetry-disabled runs, Bedrock, Vertex and Foundry, and the hooks governance tooling watches.
Reality
A dev.to template for CLAUDE.md and AGENTS.md swaps style adjectives for Avoid/Preferred code pairs that name the exact helper an agent should call, on the argument that a code shape is the only part a model can imitate.
Reality
Anthropic shipped the AGENTS.md fallback in Claude Code 2.1.277 as a flag-gated built-in mod. Two machines on the same pinned version can load different project instructions. The same week's digest also logs a reverted deny-rule fix.
Perspective Coverage
4 publishersReality
Anthropic's memory documentation sets a 200-line target per instruction file and reserves real blocking for a hook. Everything written in markdown arrives as context the model weighs against your last message.
Reality
shinpr has taken claude-code-workflows through 133 releases, and the recent ones delete structure the models no longer need. His session reader then found three mandatory steps in his own repository that never ran.
Reality
Claude can now read AGENTS.md, the file other agent tools already look for. XDA-Developers reports developers called the change small and long overdue, and the Claude-specific syntax that forced a second file has not moved.
Reality
Derek Wang's essay argues agent reliability is set by a file the model reads before any task prompt. Its ten behavior rules split into the ones a harness can verify and one the model grades itself on.
Reality
Claude Code now supports AGENTS.md through a built-in plugin with four loading modes. The default treats the two filenames as alternatives, and the mode itself is set in user or managed settings outside the repo.
Reality
The opencode-agent-memory plugin gives an OpenCode agent scoped Markdown blocks it rewrites through three tools, plus an opt-in journal it can search locally but never revise. The maintainer documents the failure modes himself.
Reality
A month and a half of prototyping an experimental functional language with Codex ended with eight artifacts around the repository and a documentation flow in which ChatGPT writes the prompts and Codex writes the spec.
Reality
Build · August 14, 2026 · One report1 publisher