agent-instructions

Portable agent setup through one INSTALL.md: minimal project instructions, verified workflows, native memory reuse, and reversible configuration.

Codex harness for consistent AI-assisted development workflows, including agent instructions, standard setup/check/test/eval scripts, CI, hooks, and documentation. | AI 기반 개발 작업을 일관되게 진행하기 위한 Codex 하네스입니다. 에이전트 지침, 표준 setup/check/test/eval 스크립트, CI, 훅, 문서를 포함합니다.

🤯 Stop AI agents from leaving zombie terminals in GitHub Codespaces & VS Code. Copy-paste terminal management rules for Copilot, Claude, Gemini, Cursor, Windsurf, Cline, Aider. Fix "terminal unresponsive" errors, agent refusing to run commands, isBackground true, kill_terminal. Install script + dev container + templates.

This is a mirror, active development happens on codeberg: https://codeberg.org/botfile/botfile

Make Claude Code behave consistently across repos, sessions and humans: rules-as-files governance with precedence, declined-decisions journal, objection sparring. Sanitized from a live production system. Free, MIT.

ALIGNS.md helps you and your AI agents share project goals, priorities, and judgment through a maintained alignment skill.

Portable agent skills for AI coding agents — works with Claude Code, OpenAI Codex CLI, Gemini CLI, Cursor & GitHub Copilot: code review, vertical-slice architecture, Go testing strategy, low cognitive-complexity & AGENTS.md generation. Markdown-only — install with npx skills.

Anchor — the production-grade AGENTS.md template for AI coding agents. 51 sections of battle-tested rules. Keep your agents grounded.

Local AGENTS.local.md overlays for Codex via hooks, without replacing the official codex command.

AI Project Starter: documentation-first starter kit for AI-coded projects, project context, guardrails, and agent instruction files.

Test whether AGENTS.md, GEMINI.md, and coding-agent instructions actually work.

A model-agnostic guide for creating concise, project-specific AGENTS.md and CLAUDE.md instructions.

Adaptive virtual CTO for Claude Code and Codex. You own product decisions; the agent owns the technical lifecycle through verified completion.

Sanitized working notes and reusable audit artifacts for (coding) agent instructions, verification, and cross-surface maintenance.

Reusable AI agent defaults, prompts, skills, wrappers, and MCP video-editing workflows for coding, DevOps, token efficiency, and Palmier Pro automation.

Code-like DSL and compiler for agent workflows that compile to portable AGENTS.md instructions.

Production-grade Laravel 13 + PHP 8.4 coding standards as instructions for AI coding agents (Claude Code, Copilot, Cursor). Always-loaded core + 27 on-demand topic sub-docs.

Project standards, context templates and opt-in hooks for AI coding agents. Clear context. Local checks. Evidence before done.

Prompt Architect: reusable prompt patterns, approval-gated workflows, and verification checklists for AI-assisted development.

One set of rules above every model. A router, lean core and thirteen specialist skills coordinating engineering, design, security, research and project memory in compatible AI agents.