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
VercelReads credentialsAGENTS.md

eve / openinstinct

vercel/eve/apps/templates/openinstinct/AGENTS.md

This project uses the eve framework: an agent is a directory of files under agent/, and eve compiles and runs it. For a content-only change to the root agent's identity, purpose, tone, or response guidelines, edit its existing authored instructions. Fresh projects use agent/instructions.md; a project may instead use agent/instructions.ts or files under agent/instructions/. You do not need to read the framework docs for a content-only instructions change. A fresh project already has its selected model in agent/agent.ts; preserve that…

5.9k2d agoReviewMountCreate a free account to mount
VercelAGENTS.md

eve / personal-agent-template

vercel/eve/apps/templates/personal-agent-template/AGENTS.md

Durable personal AI assistant built with eve and Nuxt. This project deploys its Nuxt frontend and eve agent as peer Vercel services through vercel.ts. Before writing agent code, read the relevant guide in node_modules/eve/docs/. The eve agent calls Nuxt over HTTP: Authenticated with Authorization: Bearer <INTERNAL_API_SECRET>. See apps/web/server/utils/internal-api.ts. Categories: lib/types/memory.ts. One prose block per category; saves replace the full block. See docs/CUSTOMIZATION.md for details.

Steady4 mentions in 2 weeks

No other project uses it yet

5.9k2d agoReviewMountCreate a free account to mount
VercelReads credentialsAGENTS.md

eve / sanity-copilot-eve-template

vercel/eve/apps/templates/sanity-copilot-eve-template/AGENTS.md

Guidance for AI coding agents working in this repository. A Slack-based Sanity copilot built on the eve agent framework. Users @mention it in Slack; it manages their Sanity project through the Sanity MCP connection (GROQ queries, schemas, drafts, releases), pulls source material from and drafts into Notion (user-scoped OAuth via Vercel Connect), stores files in a private Vercel Blob store, and remembers each user's standing preferences in eve memory. Its workflow lives in agent/instructions.md. The whole agent is defined under…

5.9k2d agoReviewMountCreate a free account to mount
VercelAGENTS.md

eve / slack-company-brain-template

vercel/eve/apps/templates/slack-company-brain-template/AGENTS.md

This project is an eve agent that people reach in Slack. Before writing code, read the relevant guide in node_modules/eve/dist/docs/public/. - agent/instructions.md: the root prompt. Keep it about behavior that applies to every turn: grounding, source routing, and Slack style. - agent/instructions/{github,notion,linear,pagerduty}.ts: until the matching <service>/company-brain connector is attached, tell the agent that source isn't connected and give the vercel connect create command. Delete each once its source works. - agent/connections/{notion,linear,pagerduty}.ts: turn on once their connectors are attached. Detection and…

5.9k2d agoReviewMountCreate a free account to mount
VercelAGENTS.md

eve / eve-agent-desktop

vercel/eve/packages/eve-agent-desktop/AGENTS.md

This published package is the @eve/agent-desktop extension: accessibility-based desktop tools backed by the agent-desktop CLI, plus the @eve/agent-desktop/sandbox helpers that install and start the desktop. Before writing code, read the installed eve package docs for extensions, tools, and sandboxes as applicable. Tests run against the built dist/, so there is no unit tier. Tiers are set by directory: Run typecheck, build, both tiers, lint, and package-scoped formatting before completion.

Steady4 mentions in 2 weeks

No other project uses it yet

5.9k2d agoReviewMountCreate a free account to mount
VercelAGENTS.md

eve / eve-code

vercel/eve/packages/eve-code/AGENTS.md

This private package is the source of the eve/extensions/code extension for CLI-based coding work. It contributes investigation and review skills, instruction fragments, Connect-backed authentication hooks, and consumer sandbox helpers. Before writing code, read the installed eve package docs for extensions, hooks, tools, skills, subagents, and sandboxes as applicable. The eve build copies extension/ into packages/eve/src/extensions/code/extension and compiles it into the eve package; public entry points are declared in packages/eve/package.json and packages/eve/src/extensions/code/. Do not publish this package or add it as…

Steady4 mentions in 2 weeks

No other project uses it yet

5.9k2d agoReviewMountCreate a free account to mount
VercelAGENTS.md

eve / eve-computer-use

vercel/eve/packages/eve-computer-use/AGENTS.md

This private package is the source of the eve/extensions/computer-use extension. It contributes the computer_use tool and the sandbox helpers that install and start the desktop and driver. Before writing code, read the installed eve package docs for extensions, tools, and sandboxes as applicable. The eve build copies extension/ into packages/eve/src/computer-use/extension and compiles it into the eve package; public entry points are declared in packages/eve/package.json and packages/eve/src/computer-use/. Do not publish this package or add it as an eve dependency (it depends…

Steady4 mentions in 2 weeks

No other project uses it yet

5.9k2d agoReviewMountCreate a free account to mount
VercelAGENTS.md

eve / eve-custom-skills

vercel/eve/packages/eve-custom-skills/AGENTS.md

This private package is the source of the eve/experimental/extensions/custom-skills extension. It lets the people talking to an agent save their own versioned skills, personal or shared with everyone in a channel or group chat, and applies them on later turns. Before writing code, read the installed eve package docs for extensions, tools, skills, instructions, and memory as applicable. The eve build copies extension/ into packages/eve/src/extensions/custom-skills/extension and compiles it into the eve package; the public entry point is declared in packages/eve/package.json.…

5.9k2d agoReviewMountCreate a free account to mount
VercelAGENTS.md

eve / eve-git

vercel/eve/packages/eve-git/AGENTS.md

This private package is the source of the eve/extensions/git extension. It owns everything GitHub-facing: the pull request skill, GitHub instructions, and, with github config, the Connect-brokered gh tool and signed-commit workflow. Before writing code, read the installed eve package docs for extensions, tools, skills, instructions, and sandboxes as applicable. The eve build copies extension/ into packages/eve/src/extensions/git/extension and compiles it into the eve package; public entry points are declared in packages/eve/package.json and packages/eve/src/extensions/git/. Do not publish this package or add it…

Steady4 mentions in 2 weeks

No other project uses it yet

5.9k2d agoReviewMountCreate a free account to mount
VercelAGENTS.md

eve / nitro

vercel/eve/packages/eve/src/internal/nitro/AGENTS.md

eve's Nitro host is built from one typed host spec, one ordered plugin list, and one route table. Review and pnpm guard:invariants enforce these rules: 1. Nitro is configured from data. One adapter turns a typed host spec into the NitroConfig passed to createNitro. Nothing writes nitro.options afterward. The only hooks eve uses are declared in that config: the build:before entry wrapper and build:config edits that public options can't express. No rollup:before. 2. Development and production differ by data, not…

5.9k2d agoReviewMountCreate a free account to mount
VercelReads credentialsAGENTS.md

examples / wait-until

vercel/examples/rust/wait-until/AGENTS.md

These defaults are optimized for AI coding agents (and humans) working on apps that deploy to Vercel. - Treat Vercel Functions as stateless + ephemeral (no durable RAM/FS, no background daemons), use Blob or marketplace integrations for preserving state - Edge Functions (standalone) are deprecated; prefer Vercel Functions - Don't start new projects on Vercel KV/Postgres (both discontinued); use Marketplace Redis/Postgres instead - Store secrets in Vercel Env Variables; not in git or NEXT_PUBLIC_* - Provision Marketplace native integrations with…

5.2k10mo agoReviewMountCreate a free account to mount
VercelReads credentialsAGENTS.md

workflow

vercel/workflow/AGENTS.md

CRITICAL RULES: - NEVER push directly to the main or stable branches - Do not remove or break agent-discoverable docs sitemap behavior: keep docs/app/sitemap.md/route.ts and docs/app/[lang]/sitemap.md/route.ts, and keep the sitemap link in docs/app/[lang]/llms.mdx/[[...slug]]/route.ts. Workflow SDK is a durable functions framework for JavaScript/TypeScript that enables writing long-running, stateful application logic on top of stateless compute. The runtime persists progress as an event log and deterministically replays code to reconstruct state after cold starts, failures, or scale events. This repository contains the…

2.5k13mo agoReviewMountCreate a free account to mount
VercelAGENTS.md

workflow / web

vercel/workflow/packages/web/AGENTS.md

Styling rules for this package live in ../web-shared/AGENTS.md. Read them before changing class names, inline styles, or CSS. The short version: never use opacity to set a text colour. Use the same Geist tokens as the dashboard instead.

2.5k13mo agoReviewMountCreate a free account to mount
VercelAGENTS.md

workflow / web-shared

vercel/workflow/packages/web-shared/AGENTS.md

These rules apply to packages/web-shared and packages/web (which consumes it). Text colour always comes from a Geist token or the surface's inherited foreground. Don't make text lighter by fading it: A faded text colour depends on whatever is underneath it, so it becomes unreadable on another surface: the inverted tooltip pill, dark mode, or a coloured row. Geist tokens are defined for both themes. Opacity is fine for anything else, such as disabled controls, overlays, fades and animations, or dimming…

2.5k13mo agoReviewMountCreate a free account to mount
VercelAGENTS.md

chat

vercel/chat/AGENTS.md

Guidance for coding agents working in this repository. For PR workflow, signed commits, and changeset rules, see .github/CONTRIBUTING.md. Install dependencies with pnpm add, not by editing package.json by hand. pnpm + Turborepo monorepo. Packages are ESM ("type": "module"), TypeScript, bundled with tsup. When editing a specific package, read its AGENTS.md if present (most adapters, state packages, create-chat-sdk, and packages/catalog have one). {adapter}:{channel}:{thread} — e.g. slack:C123ABC:1234567890.123456. Some adapters base64-encode IDs that contain delimiters (Teams, Google Chat). mdast is the canonical message…

Steady2 mentions in 2 weeks

No other project uses it yet

2.5k34d agoReviewMountCreate a free account to mount
VercelReads credentialsAGENTS.md

chat / apps

vercel/chat/apps/docs/AGENTS.md

This app (chat-sdk.dev) uses the packaged Geistdocs architecture. The @vercel/geistdocs package owns shared runtime behavior; this app owns local content, configuration, adapters, and site-specific routes. Use these instructions when an AI coding agent edits this app.

2.5k34d agoReviewMountCreate a free account to mount
VercelAGENTS.md

chat / apps

vercel/chat/apps/docs/public/AGENTS.md

Build multi-platform chat bots with Chat SDK (`chat` npm package). Use when developers want to scaffold a bot with create-chat-sdk, build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files, or AI streaming, set up webhook routes or multi-adapter bots, send rich cards or streamed AI responses to chat platforms, or build a custom adapter or state adapter.

2.5k34d agoReviewMountCreate a free account to mount
VercelReads credentialsAGENTS.md

chat / adapter-discord

vercel/chat/packages/adapter-discord/AGENTS.md

Guidance for coding agents working inside the Discord adapter package. The top-level repository AGENTS.md covers monorepo-wide build, lint, and release rules — read it first. This file documents the adapter-specific surface, conventions, and pitfalls. @chat-adapter/discord connects a Chat SDK bot to a Discord guild via HTTP interactions and the Discord Gateway. It covers: - HTTP webhook endpoint at /api/webhooks/discord for slash commands, message components (buttons / selects), and modal submissions. - Gateway transport (websocket) that listens for MESSAGE_CREATE, MESSAGE_UPDATE, MESSAGE_DELETE,…

2.5k34d agoReviewMountCreate a free account to mount
VercelAGENTS.md

chat / adapter-gchat

vercel/chat/packages/adapter-gchat/AGENTS.md

Guidance for coding agents working inside the Google Chat adapter package. The top-level repository AGENTS.md covers monorepo-wide build, lint, and release rules — read it first. This file documents the adapter-specific surface, conventions, and pitfalls. @chat-adapter/gchat connects a Chat SDK bot to Google Chat (the Workspace messaging product, not Hangouts/Meet). It covers: - HTTP webhook endpoint at /api/webhooks/gchat, validated with Google-issued JWTs. - Card v2 rendering for cards, fields, action buttons, image attachments, and dialog modals. - Workspace Events API…

2.5k34d agoReviewMountCreate a free account to mount
VercelAGENTS.md

chat / adapter-github

vercel/chat/packages/adapter-github/AGENTS.md

Guidance for coding agents working inside the GitHub adapter package. The top-level repository AGENTS.md covers monorepo-wide build, lint, and release rules — read it first. This file documents the adapter-specific surface, conventions, and pitfalls. @chat-adapter/github connects a Chat SDK bot to issue and pull-request comment threads on GitHub. It covers: - HTTP webhook endpoint at /api/webhooks/github for issues, issue_comment, pull_request, pull_request_review_comment, and pull_request_review events, validated with HMAC-SHA256 against the App secret. - Comment posting, editing, and deletion via the REST…

2.5k34d 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.