plan-review

The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't s

Agent skills for infrastructure, security, software engineering, and agent workflows, with portable installs, quality checks, and evidence-based review.

Workflow infrastructure plugin for Claude Code projects — TDD-driven sprint management, review gates, hook parameterization, and multi-stack config

Autonomous CI/CD for AI-written code: plans, builds, and adversarially audits changes to any repo — a different model reviews the builder — shipping only what passes deterministic gates. Failures become durable lessons; runs are checkpoint-

Portable Claude Code global configuration: custom skills, PreToolUse hooks, and a custom statusline. Runs on Linux, macOS, WSL.

A personal AI agent you fork and make your own. Single process, few files, no abstractions. Extend through skills that transform code, not config.

A cloneable set of Claude Code settings, usable across different machines

A Claude Code plugin that carries one feature through six gated SDLC stages (intake, discover, design, build, verify, ship) with zero-token preflight checks, cost-tiered subagents, a four-lens diff review, an append-only attempt ledger, a s

Dotfiles for Cyrus sandboxes: installs Matt Pocock's agent skills into ~/.claude/skills

My Darwin Nix system configs!