What we make

An agentic skills framework & software development methodology that works.

Curated Claude Code plugin marketplace

Prime Radiant's Claude Code plugin marketplace.

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenAI, Anthropic, and Google models.

Lightweight agentic coding environment

Self-hosted Slack knowledge bot that watches invited conversations, keeps durable notes in a Git-backed wiki, and answers when mentioned; built on the Claude Agent SDK, Bolt Socket Mode, and MCP servers.

A Claude Code plugin that reverse-engineers clean behavioral specs, test vectors, and acceptance criteria from any codebase, producing a provenance trail so a fresh team can reimplement without inheriting the original's internal structure.

Iterative development methodology plugin for Claude Code — extracts requirements, defines walking skeleton, loops through audited sprints autonomously

Two Claude Code skills for adversarial code review (single-model PAR and multi-model MMAR with cross-critique to catch hallucinations), plus a fixture-based eval suite.

A portable coding-agent plugin for shepherding GitHub pull requests through CI and review.

Claude Code plugin for triaging GitHub issues and pull requests, with a security-gated PR review workflow.

Keep AI-driven work tracked in Linear: a Claude Code / Codex skill + hook that find or create a ticket and move it through your workflow. A public example of how Prime Radiant works.

A documentation department in a box: studies a project and its readers, decides the doc portfolio with you, writes contributor, user, and adopter docs with verified claims, and keeps them true as the code moves.

Claude Code plugin that automatically evaluates whether Claude should continue working instead of stopping prematurely

Make a movie that proves your software actually works — three recording routes plus a checker that catches frozen pictures, desynced narration, and dropped words before you ship

Claude Code plugin for direct Chrome browser control via DevTools Protocol - zero dependencies

A lightweight MCP server that provides Claude with a private journaling capability to process feelings and thoughts

Semantic search for Claude Code and Codex conversations. Remember past discussions, decisions, and context instead of re-deriving them.

A lightweight Linear MCP server for Claude Code that exposes one tool with action dispatch (search, get, update, comment, create, graphql, help) using ~500 tokens instead of the standard MCP's ~17,000.

A single-binary Go CLI that gives AI agents a Slack identity to send messages, read channels, and stream real-time events, with admin tooling to provision new bots.

Launch, control, and monitor other Claude Code sessions as workers via tmux

Generate a coding-agent plugin for every harness from one config file

Skills and resources for developing Claude Code plugins, skills, MCP servers, and extensions.

Rust CLI that converts EPUBs into a single YAML-headed Markdown file with per-chapter byte and line offsets, giving LLM agents a navigation API for token-efficient reading.

A Claude Code plugin for durable agent learning: analytical reading, a cross-linked Zettelkasten slip-box with a bundled CLI, first-person beliefs with falsifiers, experience capture, and deliberation forks.

William Strunk Jr.'s Elements of Style (1918) in markdown format for AI agents

Session Explorer: a local web app for browsing Claude Code and OpenAI Codex CLI session histories, built with React Router, Express, and SQLite.

A Bun CLI that ingests Claude Code and Codex session transcripts, generates LLM-powered daily summaries, and serves a browsable web UI for your engineering journal.

Claude Code plugin that records every session as structured turns in cxdb via lifecycle hooks, enabling trajectory browsing, tool-call inspection, and token-usage observability.

Coding-agent VM orchestrator: runs coding agents in isolated VMs — Firecracker micro-VMs on Linux (with ZFS-based audit-trail snapshots) and Apple's container tool on macOS.

File-defined workflow orchestrator in Go — YAML workflows and runners, disk-persisted state, resume, approvals, and live graph views

Reusable TypeScript core for building unattended Claude-powered chat agents: session storage, per-room workspaces, responder/adapter base classes, and shared bot infrastructure.

Transparent logging proxy for LLM API traffic that auto-configures clients and records every request and response to Claude, OpenAI, and other providers for debugging, auditing, and analysis.

Read an AI-agent transcript and estimate what it cost — a Rust core with C-ABI bindings for Python, Go, and TypeScript (Bun + Node).

A framework for running evals against small (and large) models

Behavioral eval lab (Quorum) for the superpowers project that drives real coding-agent CLIs (Claude, Codex, Gemini, Kimi, and more) through a QA agent and grades them on workflow compliance against scenario criteria and deterministic...

AI-powered QA testing framework that uses LLMs (Claude or GPT) to test web apps, CLI tools, and TUI programs from markdown story cards, returning structured pass/fail verdicts with evidence.

A portable, model-agnostic test suite of declarative YAML scenarios for evaluating AI assistant security against prompt-injection and data-exfiltration attacks, with Python tools and pluggable harnesses.

Clearance product workspace: a monorepo for the Markdown viewer, currently shipping a native Swift/macOS app with structure for future shared Tauri implementations on Windows, Linux, and Android.

Clipboard sync daemon for Mac + remote tmux fleet. Mirrors macOS pasteboard to remote OS clipboards and tmux paste buffers. Enables image paste into Claude Code/Codex over SSH without OSC 52 or Xvfb.

Automatically mount remote filesystems over SSH on macOS via FUSE-T and ControlMaster

macOS menu-bar meter for coding-agent subscription quotas

macOS photo culling app — catalog-first, non-destructive, AI-assisted. Early development; not ready for use.

Hearthstone gives babysitters and family instant answers to household questions, grounded in your Google Docs with cited sources; Bun backend plus iOS app with PIN-based guest access.

A browser bookmarklet that exports your Kindle Notebook highlights and notes to local markdown files, one book per file, bundled into a ZIP, with no backend.

A macOS command-line tool that syncs your Beeper chat history to local JSONL files, downloading attachments and organizing messages by network, chat, and date for backup, search, or LLM use.

Durable, git-backed working-state for coding agents: append-only ledgers with identity, evidence, cursors, and agent-curated roll-ups

Ledger-backed persistent memory plugin for Claude Code

Experimental self-improving multi-agent coding system: a root agent recursively decomposes goals and delegates to specialist subagents, learning from failures by mutating a git-backed agent genome. Supports Claude, GPT, and Gemini.

Bun-workspaces monorepo of TypeScript bindings around Ghostty's VT state machine: libghostty-vt (Terminal/RenderState/Formatter model layer) and blinkyterm (agent-facing terminal Runner).

Experimental skills for Claude Code Superpowers - new techniques and tools