Building agents instructions files

anthropics/claude-code-action

Instructions file ✓ vendor

Claude Code instructions for anthropics/claude-code-action, covering claude.md, commands, what this is, how it runs and key concepts.

withastro/flue

Instructions file CodexOpenCode

Instructions for withastro/flue, covering flue, contributing, terminology, project structure and development.

nullclaw/nullclaw

Instructions file CodexOpenCode

Instructions for nullclaw/nullclaw, covering agents.md — nullclaw agent engineering protocol, 1) project snapshot (read first), 3) engineering principles (normative), 3.1 kiss and 3.2 yagni.

Upsonic/Upsonic

Instructions file

Claude Code instructions for Upsonic/Upsonic, covering claude.md, project overview, ai operational guides, default pre-work consultation and keep documents/ai/explanation/ in sync with code.

open-multi-agent/open-multi-agent

Instructions file CodexOpenCode

AGENTS.md instructions for open-multi-agent/open-multi-agent, covering agents.md, repository map, commands, working rules and validation by change type.

anomalyco/models.dev

Instructions file CodexOpenCode

AGENTS.md instructions for anomalyco/models.dev, covering agent guidelines for models.dev, validate, two concepts: lab models vs providers, when to use basemodel (blocker) and exceptions (full inline definition allowed).

WenyuChiou/awesome-agentic-ai-zh

Instructions file

Claude Code instructions for WenyuChiou/awesome-agentic-ai-zh, covering project memory — awesome-agentic-ai-zh, 📍 repo positioning — read before adding anything, canonical anthropic models, framing rules (do not violate) and exercise file conventions.

BlockRunAI/ClawRouter

Instructions file

Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.

crestalnetwork/intentkit

Instructions file GitHub Copilot

Instructions for crestalnetwork/intentkit, a project described as: IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.

Gentleman-Programming/engram

Instructions file CodexOpenCode

AGENTS.md instructions for Gentleman-Programming/engram, covering engram — agent skills index, how to use and skills.

microsoft/agent-governance-toolkit

Instructions file GitHub Copilot ✓ vendor

Copilot instructions for microsoft/agent-governance-toolkit, covering copilot instructions for agent-governance-toolkit, architecture, build, test, and lint, python and install (editable, all extras).

builderz-labs/mission-control

Instructions file

Claude Code instructions for builderz-labs/mission-control, covering mission control, prerequisites, setup, run and docker.

FlorianBruniaux/claude-code-ultimate-guide

Instructions file CodexOpenCode

AGENTS.md instructions for FlorianBruniaux/claude-code-ultimate-guide, covering claude code ultimate guide - project context, purpose, repository structure, published at: https://cc.bruniaux.com/whitepapers/ and key files.

antfu/skills

Instructions file CodexOpenCode

Instructions for antfu/skills, covering skills generator, skill source types, type 1: generated skills (sources/), type 2: synced skills (vendor/) and type 3: hand-written skills.

deusyu/harness-engineering

Instructions file CodexOpenCode

A set of repository instructions for documenting and practising harness engineering, a way of organizing an AI coding agent's work. It covers notes, experiments, progress, references, prompts, and automated consistency checks.

dramaclaw/dramaclaw

Instructions file CodexOpenCode

AGENTS.md instructions for dramaclaw/dramaclaw, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

truefoundry/trueforge

Instructions file CodexOpenCode

AGENTS.md instructions for truefoundry/trueforge, a project described as: The open-source agent harness - the runtime layer that turns an LLM into a working agent.

openclaw/mcporter

Instructions file CodexOpenCode

AGENTS.md instructions for openclaw/mcporter, a project described as: Call MCPs via TypeScript, masquerading as simple TypeScript API. Or package them as cli.

harbor-framework/harbor

Instructions file CodexOpenCode

AGENTS.md instructions for harbor-framework/harbor, covering claude.md - harbor framework, contributing, project overview, quick start commands and install.

eastlondoner/vibe-tools

Instructions file CodexOpenCode

AGENTS.md instructions for eastlondoner/vibe-tools: This is the vibe-tools repo. Here we build a cli tool that AI agents can use to execute commands and work with other AI agents.

makenotion/notion-mcp-server

Instructions file

Claude Code instructions for makenotion/notion-mcp-server, covering claude.md, project overview, architecture, key patterns and adding new endpoints.

JetBrains/koog

Instructions file CodexOpenCode ✓ vendor

AGENTS.md instructions for JetBrains/koog, covering koog ai agent framework, project structure, build & commands, development commands and full build including tests.

AlexAnys/awesome-openclaw-usecases-zh

Instructions file CodexOpenCode

A Chinese-language collection of 50 community-verified ways to use personal AI agents. It uses OpenClaw terms, but explains how agents such as Hermes, Claude Code, and Codex can adapt the examples; the files are instructions, not executable programs.

vijaythecoder/awesome-claude-agents

Instructions file

Instructions for vijaythecoder/awesome-claude-agents, covering claude.md, project overview, working with agents, orchestration pattern for claude code and critical: agent routing protocol.