agent instructions files

1,263 tagged agent, measured the same way as everything else here.

Browse within: agentic 66agentic-workflow 60chatbot 39agent-orchestration 37framework 35agent-framework 34coding-agent 34copilot 31openclaw 27Multi-Agent 26harness 26ai-coding 25model-context-protocol 25deepseek 23

ai-doc-gen CLAUDE.md

241

divar-ir/ai-doc-gen

Instructions file

Instructions for divar-ir/ai-doc-gen: See AGENTS.md for project instructions (commands, architecture, conventions, gotchas).

not rated 753 +1 1mo ago A 128 tokens original MIT

Wegent AGENTS.md

242

wecode-ai/Wegent

Instructions file CodexOpenCode

Instructions for wecode-ai/Wegent, covering wegent contributor guide, repository map, scoped instructions, domain model and engineering rules.

not rated 747 4d ago C 1,396 tokens original Apache-2.0

Wegent CLAUDE.md

243

wecode-ai/Wegent

Instructions file

Instructions for wecode-ai/Wegent, a project described as: An open-source AI-native operating system to define, organize, and run intelligent agent teams.

not rated 747 4d ago A 3 tokens copy · 100% Apache-2.0

lout33/symbiotic-ai

Instructions file CodexOpenCode

AGENTS.md instructions for lout33/symbiotic-ai, covering agents.md - operations, session start, onboarding protocol, log maintenance and operating mode.

not rated 736 2mo ago A 1,957 tokens

PiDeck AGENTS.md

245

ayuayue/PiDeck

Instructions file CodexOpenCode

Repository instructions for PiDeck, a desktop Electron application for managing AI coding-agent sessions across projects. They define the boundary between the agent process and the desktop interface, which communicate through JSON-RPC, a structured message format.

not rated 709 4d ago A 7,571 tokens original MIT

BigSweetPotatoStudio/HyperChat

Instructions file GitHub Copilot

A set of instructions for the HyperChat project, focused on TypeScript, the project overview, communication between the front end and back end, and memory. It also asks for replies in Chinese.

not rated 708 7d ago A 947 tokens

HyperChat CLAUDE.md

247

BigSweetPotatoStudio/HyperChat

Instructions file

A set of Claude Code instructions for the HyperChat project. It covers replying in Chinese, TypeScript guidance, the project overview, support for multiple platforms, and package structure.

not rated 708 7d ago A 5,670 tokens

HyperChat GEMINI.md

248

BigSweetPotatoStudio/HyperChat

Instructions file Gemini CLI

A set of Gemini CLI instructions for the HyperChat project. It covers replying in Chinese, TypeScript guidance, the project overview, support for multiple platforms, and package structure.

not rated 708 7d ago A 5,161 tokens

TrailSnap AGENTS.md

249

LC044/TrailSnap

Instructions file CodexOpenCode

A set of project instructions for the LC044/TrailSnap codebase. It describes the project's overview, development commands, and its frontend and backend areas.

not rated 697 4d ago A 4,753 tokens AGPL-3.0

TrailSnap CLAUDE.md

250

LC044/TrailSnap

Instructions file

A project instruction file for Claude Code, covering the TrailSnap app’s structure, development commands, frontend, and backend.

not rated 697 4d ago A 4,753 tokens AGPL-3.0

863401402/she-love-me

Instructions file GitHub Copilot

Instructions for 863401402/she-love-me: When the user asks to import or analyze WeChat/QQ chat history, read and follow .agents/skills/she-love-me/SKILL.md from the repository root.

not rated 695 +36 21d ago A 151 tokens original MIT

she-love-me AGENTS.md

252

863401402/she-love-me

Instructions file CodexOpenCode

Instructions for 863401402/she-love-me, covering agents.md, repository focus and codex guidance.

not rated 695 +36 21d ago A 445 tokens original MIT

she-love-me CLAUDE.md

253

863401402/she-love-me

Instructions file

Repository instructions for a chat-relationship analysis workflow involving WeChat and QQ exports. They specify which skill and data-source guide to follow, where private data belongs, and when to ask the user for help.

not rated 695 +36 21d ago A 268 tokens original MIT

frontman AGENTS.md

254

frontman-ai/frontman

Instructions file CodexOpenCode

AGENTS.md instructions for frontman-ai/frontman, covering agent guidelines for frontman, worktree workflow, containerized worktrees, one-time infra setup and per-feature.

not rated 681 4d ago A 2,632 tokens

frontman CLAUDE.md

255

frontman-ai/frontman

Instructions file

Claude Code instructions for frontman-ai/frontman, a project described as: The AI agent that lives in your framework/browser.

not rated 681 4d ago A 3 tokens

denova AGENTS.md

256

alfredxw/denova

Instructions file CodexOpenCode

A project instruction file named AGENTS.md for the alfredxw/denova codebase. It records rules for compatibility, code structure, releases, documentation, and product design.

not rated 673 6d ago A 2,541 tokens original Apache-2.0

denova CLAUDE.md

257

alfredxw/denova

Instructions file

Project-specific instructions for denova, an AI platform for writing novels and creating role-playing games with generated content. They describe how work should be done in that project.

not rated 673 6d ago A 3 tokens copy · 100% Apache-2.0

zoetrope CLAUDE.md

258

furkankly/zoetrope

Instructions file

Instructions for furkankly/zoetrope, covering zoetrope, running and commits.

not rated 667 9d ago A 444 tokens original MIT

MindOS AGENTS.md

259

GeminiLight/MindOS

Instructions file CodexOpenCode

Project instructions for coding agents working on GeminiLight and MindOS. They define collaboration rules, specification sections, coding limits, and testing expectations.

not rated 662 8d ago C 7,640 tokens original MIT

MindOS CLAUDE.md

260

GeminiLight/MindOS

Instructions file

Instructions for GeminiLight/MindOS, a project described as: MindOS is a Human-AI Collaborative Mind System, where human thinks and agents act. Globally sync your mind for all agents: transparent, controllable, and evolving symbiotically.

not rated 662 8d ago A 3 tokens copy · 100% MIT

helixent AGENTS.md

261

MagicCube/helixent

Instructions file CodexOpenCode

AGENTS.md instructions for MagicCube/helixent, covering helixent, architecture (4 layers), 1) foundation, 2) agent and 3) coding.

not rated 657 +3 3mo ago A 1,628 tokens

helixent CLAUDE.md

262

MagicCube/helixent

Instructions file

Claude Code instructions for MagicCube/helixent, a project described as: Helixent is a small library for building ReAct-style AI agent loops based on the Bun stack.

not rated 657 +3 3mo ago A 5 tokens

opskat AGENTS.md

263

opskat/opskat

Instructions file CodexOpenCode

AGENTS.md instructions for opskat/opskat, covering agents.md, project overview, high cohesion, low coupling / solid, fix policy — tdd, root cause, in scope and defensive code / error handling (no meaningless fallbacks).

not rated 658 today A 2,702 tokens GPL-3.0

opskat CLAUDE.md

264

opskat/opskat

Instructions file

Claude Code instructions for opskat/opskat, a project described as: OpsKat — All-in-one server ops workstation.

not rated 658 today A 5 tokens GPL-3.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: