By thermiteau
Automates software development workflows using AI agents within Claude Code, from project scaffolding and code quality enforcement to issue resolution, code review, PR creation, security audits, and documentation generation, all coordinated through git and GitHub.
Autonomous code reviewer that performs two-stage review — spec compliance first, then code quality (correctness, test coverage, maintainability). Security is out of scope; do-cybersecurity-review handles that as a mandatory pre-push gate. Dispatched after completing implementation steps or before creating PRs.
Takes a solution design and produces an ordered task list. Dispatched by do-issue-solo and do-issue-guided as a subagent so that planning does not consume the caller's context window.
Reads a GitHub issue, explores the codebase, and produces a solution design. Dispatched by do-issue-solo and do-issue-guided as a subagent so that codebase exploration does not consume the caller's context window.
Handles Maverick plugin and CLI management — installation, project initialisation, and configuration. Dispatched so that CLI internals don't consume the caller's context.
Reviews Claude Code session activity and git diffs to identify missed opportunities, duplicated code, and quality issues.
Scan a project for missing best-practice areas and implement the top recommendation for each gap. Currently covers linting and unit testing. Installs tools, writes configs, and adds CI steps.
Implement a focused code change. Use this skill as the wrapper for any implementation work so the Maverick workflow report captures what was done and so the agent applies the project's coding standards before editing. Intended to be invoked once per task from inside a do-issue-* or do-epic phase, not standalone.
Run a security audit of the project's existing codebase and write a findings report to docs/security-audit.md. Covers secrets exposure, dependency vulnerabilities, authentication and authorisation patterns, input validation, transport security, and common OWASP risks. Run as part of do-init or on demand.
Create, restructure, or update technical documentation. Handles greenfield projects, refactoring non-compliant docs, and incremental updates after code changes.
Work on a multi-story GitHub epic end-to-end. Builds a DAG from the child stories, groups them into waves, runs waves in parallel via per-story worktrees, ejects PRs that fail agent-code-review for human handling, and propagates blocks to downstream stories. Requires git worktrees.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code tooling to build software right
Explore the docs
·
Report Bug
·
Request Feature
Maverick is a Claude Code ( Cursor and Codex ) plugin and local CLI commands that enables autonomous AI-driven software development while enforcing quality, security, and operational best practices.
It provides skills, agents, and hooks that constrain and guide LLM behaviour - making unattended development safe and reliable.
LLMs generate code fast but dont come with any concept of quality, best practice or constraint. Claude Code will happily agree to build the worlds worst idea, with a smile, because without guardrails:
These risks multiply enourmously in unattended development when no human is watching the LLM work. There is no developer catching issues in real-time, no reviewer glancing at the diff, no operator noticing silent failures. Every quality gap becomes a production risk.
Maverick is comprised of three parts:
Maverick comes with Claude Code skills that defines how to write quality code. These are not detailed technical skills, they are the why and how of software development practices. These skills are part of the plugin and get loaded into Claude Code.
There are also a few technical skills that are so common, they have been predefined in the plugin.
Because every codebase is unique, there is no way to ship defined skills that are needed to enable Claude Code. So Maverick builds them when it is initialised in a project.
There are multiple ways to run Claude Code, the most obvious being the software running locally on your machine. This works well for interactive development where you ask Claude Code to complete a task, answer any questions as they come up and monitor the progress.
It falls down when you need to complete multiple features or bug fixes at the same time. Claude Code on local machines, doesnt scale.
Maverick solves this by deploying Claude Code workers to remote Claude platforms such as Amazon Web Services. Those workers are triggered by creating tickets (issues) in GitHub. The worker will autonomously complete the requirements and keep you up to date with notes in the Github Issue.
This is more complicated than cassual users may need and its not required to use Maverick. You can just use the plugin on your local machine and either ask Claude to complete a task solo or with assistance.
I use this repo to build my own software and I aim to improve it every day. That means the change rate is pretty high until I get it to v1 release.
# Install the plugin (registers in ~/.claude/settings.json)
claude plugin marketplace add https://github.com/thermiteau/maverick
claude plugin install maverick@thermite
npx claudepluginhub thermiteau/maverick --plugin maverickFeature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams