agentleFS

AGENTS.md examples from real projects

How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.

Worked for most · soon
2233adminAGENTS.md

obsidian-llm-wiki

2233admin/obsidian-llm-wiki/AGENTS.md

Codex works in this repository as an obsidian-llm-wiki agent host. Follow the same host-neutral workflow contract as Claude Code. Before changing ingest, memory, source registration, project/work-OS behavior, or external workflow…

374mo agoReviewMountCreate a free account to mount
2233adminAGENTS.md

opencli-Razormind

2233admin/opencli-Razormind/AGENTS.md

These rules apply only to this repository. They extend the workspace rules in D:\projects\AGENTS.md. - Start each task by identifying the requested outcome, acceptance criteria, affected scope, and the smallest…

1858d agoReviewMountCreate a free account to mount
2233adminAGENTS.md

opencli-Razormind / frontend

2233admin/opencli-Razormind/frontend/AGENTS.md

This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in node_modules/next/dist/docs/ (resolved from this file's directory; in…

198 projects use a version of this

1858d agoReviewMountCreate a free account to mount
2233adminReads credentialsAGENTS.md

design-pipeline

2233admin/design-pipeline/AGENTS.md

Design and film workflow (UI, motion web, product films, PV/MAD edits) shipped as a packaged agent skill. Runtime scripts use Node.js CommonJS; the root package.json is a private maintenance workspace for evals/cases and tools/browser-automation, separate from the packaged skill. Package entry is skill/SKILL.md; stage contracts live in skill/references/stages.md, with route guidance in pipeline-reference.md; behavior specs and changes live in openspec/.

112mo agoReviewMountCreate a free account to mount
2233adminAGENTS.md

obsidian-vault-bridge

2233admin/obsidian-vault-bridge/AGENTS.md

Obsidian plugin that turns a vault into compiled LLM knowledge infrastructure. MCP server exposes vault CRUD, search, graph, lint, and init. A separate Python compiler engine handles deterministic operations (diffing, hashing, link validation, topology analysis). Transport: stdio (via connector) or WebSocket (localhost:48765). Filesystem fallback when Obsidian is closed. 15 tools: vault.read, vault.create, vault.modify, vault.append, vault.delete, vault.rename, vault.mkdir, vault.search, vault.searchByTag, vault.searchByFrontmatter, vault.graph, vault.backlinks, vault.batch, vault.lint, vault.init All write operations are dry-run gated by default. Pass dryRun: false to execute. Add to…

07mo agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

About AGENTS.md

What is AGENTS.md?

An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.

Where does it go?

At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.

What should it contain?

Setup and test commands, code style, and the rules a new contributor would need to know.

Does Claude Code read it?

Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.