agent-toolkit

Minimalistic skills and rules for AI coding agents that assist your daily work in any software engineering project

Project-agnostic Works with any agent MIT
# install with one command
git clone https://github.com/eai-org/agent-toolkit.git && cd agent-toolkit && ./install.sh
Other ways to install →

This toolkit is entirely open source and free to use. Give us a star on GitHub to support us.

The problem

Different projects, same repetitive tasks

  • Every project is a different world tech stacks, trackers, conventions, AI adoption
  • Yet the daily tasks repeat everywhere fetch a ticket, refine it, plan, review, reply
  • agent-toolkit lets AI assist exactly those generic skills that can be used in any project

"I kept rebuilding the same AI setup in every project, so I built one that works everywhere."

Principles

Core ideas behind every skill

Keep the context window sharp Atomic skills: do one thing, do it well, load nothing else. Why this matters →
Offload to files, pick up fresh Each phase ends in a self-contained doc a fresh session can pick up. Clean handoffs, easy parallelism. The RPA workflow →
Human in the loop You keep full control: nothing runs behind your back. The agent recommends, you decide.
Never guess The agent checks the existing code first and asks you when in doubt.
Learn from mistakes Every correction you make becomes a durable lesson, so your agents get smarter every day. Learn more →
Versatile by design Skills that work in any project and tech stack, in any type of team or solo.
Philosophy

A minimalistic toolkit, not a framework

There are great skill frameworks out there that auto-activate around everything you do. The agent-toolkit deliberately takes the other road:

auto-activating frameworks
  • a whole methodology
  • skills activate before any task
  • the agent drives
  • pulls you in at its checkpoints
  • fuller context, less to remember
agent-toolkit
  • modular, use only the parts you need
  • primarily user invoked
  • you drive, the agent assists
  • human in the loop by design
  • lean context, predictable behavior
Task workflow

Refine, Plan, Act

A development workflow suitable for any kind of project

Ticketdownload TICKET.md from your tracking board or create it manually
Refinedefines the WHAT and outputs REQUIREMENTS.md
Plandefines the HOW and outputs PLAN.md with the implementation steps
Actexecutes the plan, writing code and running checks

Read more about the task workflow →

Review assistants

Help on both sides of the code review

Code review is still a key part of most teams' workflow. These skills assist in both directions: when others leave feedback on your PRs, and when you review someone else's code.

  • fetch-pr-review downloads all the comments your PR received into a self-contained document that refine-pr-review can consume
  • refine-pr-review assists you in triaging the feedback, comment by comment: address, partial or push back
  • review-code-assistant reviews someone else's PR locally (works for self-review too), suggesting human-voiced comments and explanations. You decide what to post
Fresh eyes review

Let a sub-agent review the code

A fresh perspective works for AI just like it does for humans: a sub-agent with a clean context, seeing only the changeset and a minimal description, catches surprisingly more regressions and issues than the session that wrote the code.

Context & memory hygiene

Your context is often cluttered before you even type

  • context-checkup audits everything that auto-loads at startup (governing docs, skills, MCP servers), measures the token cost and proposes lean, reversible trims
  • memory-doctor drains the agent's auto-memory block by block, relocating each entry to a home you control or archiving it. You confirm every action
Skill & doc authoring

Create and continuously improve the skills and docs your agents rely on

  • compact-docs-writer writes docs with maximum token economy
  • compact-skill-creator creates or edits skills, combining compact-docs-writer with a set of best practices for effective skills
  • self-improve when the agent makes a mistake or doesn't behave the way you want, this skill captures the lesson so it won't repeat the same mistake again

Read more about the authoring skills →

Conversational voice

Texts that sound like a real human typed them

We often ask AI to help draft texts that other people will read:

  • use-conversational-language tells the agent to write in simple, human language instead of sophisticated AI prose full of — em dashes — and fancy terms
  • write-realistic-texts opt-in rule that applies the human voice automatically whenever a text is meant for other humans (code comments, PR replies, chat messages…)
Opinionated rules

Optional and not installed by default: get them all with ./install-opinionated-rules.sh or pick only the ones you want. Examples:

  • git-read-only-by-default prevents the agent from performing git write operations such as commit, push, reset, etc. unless explicitly instructed
  • no-ai-attribution no AI co-author additions on commits and no "Generated with" footers on PRs
  • no-nonsense-comments write only code comments that still make sense to a future reader with zero context, prefer no comment over a low-value one, and voice them via use-conversational-language
  • and more…

Check the full list of available rules →

Share your feedback

Got an issue or an idea? Please report it on GitHub.

Open an issue →