Analysis updated 2026-06-20
Install a frontend developer persona into Claude Code so it reviews your UI with expert-level standards, not generic advice.
Activate a security engineer agent to audit your codebase for vulnerabilities during a code review session.
Use a technical writer agent to generate project documentation without writing prompts from scratch.
Assemble a virtual team of focused AI agents for different parts of a solo project.
| msitarzewski/agency-agents | nvm-sh/nvm | papers-we-love/papers-we-love | |
|---|---|---|---|
| Stars | 94,309 | 93,236 | 105,928 |
| Language | Shell | Shell | Shell |
| Setup difficulty | easy | easy | easy |
| Complexity | 1/5 | 2/5 | 1/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Run the shell install script, it copies Markdown agent files into your AI tool's config directory.
Agency-agents is a collection of pre-written persona files for AI coding assistants. The author calls it a complete AI agency at your fingertips: each agent is a markdown file describing a specialised role, a frontend developer, backend architect, mobile builder, security engineer, technical writer, code reviewer, database optimiser, and many others organised into divisions like Engineering. According to the README each agent has its own identity and personality, a core mission, example workflows, expected technical deliverables, and success metrics, so it can be used as a ready-made expert rather than a blank prompt template. In practice, you do not run this repository as software. Instead, you copy or install the agent definitions into one of the supported AI coding tools so the assistant takes on that role when activated. The README ships shell scripts that install the agents to Claude Code by default and can also generate integration files for other tools the project lists as supported, including GitHub Copilot, Antigravity, Gemini CLI, OpenCode, OpenClaw, Cursor, Aider, Windsurf, and Kimi Code. After installation you activate an agent inside a session, for example by saying "activate Frontend Developer mode", and the assistant follows that persona's instructions. Someone might use it to skip writing prompts from scratch when starting a new task, to assemble a small team of focused assistants for different parts of a project, or to study how detailed role prompts are structured. The repository is shell-script-driven and is released under the MIT licence.
A ready-made set of AI persona files you install into your AI coding tool so it acts as a specialised expert, frontend developer, security engineer, code reviewer, and more, instead of a blank assistant.
Mainly Shell. The stack also includes Shell, Markdown.
MIT licence, use freely for any purpose, including commercial, as long as you keep the copyright notice.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.