auditor

Claude skills that make my life easier.

An agentic skills framework & bundle-plugin engineering toolkit that works.

Agent Almanac — a curated reference of executable skills, specialist agents, and teams for AI-assisted development, with interactive visualization

The autonomous SDLC for Claude Code that won't pass a gate on an unproven verdict.

Know what your agents are doing

Autonomous agent factory — loop runner, worktree engine, and a local dashboard over the event log.

Custom skills for Claude Code CLI - Intent Layer setup and maintenance

Workflow management CLI for Anthropic Claude Code, Cursor, and Gemini CLI. 30 AI agents — incl. a virtual eng team — 84 commands, 62 skill categories. Built for Claude Opus & Sonnet.

A company that runs in a folder. AI roles for prospecting and sales, a live office in your browser, and the AI you already pay for (Claude Code, Codex, OpenCode, Antigravity).

Skills and tools that make your AI coding agent do better work: it finds the right skill, runs its own code, remembers your project's rules and keeps notes in Obsidian. 240+ skills and optional tools for Claude Code, Cursor, Codex, OpenCode

Versioned AI agent team managed project orchestration system for Claude Code, Codex, and Gemini. Focused on software development projects with extensive support for Apple platforms, Python, and others, the system can be extended to support

Spec-driven development workflow for Claude Code — built around an approved design doc, where each stage waits for your approval.

In this repo, we explore Google's ScientistOne research pipeline, recreated entirely from Claude Code primitives — subagents as researchers, skills as stages, hooks as integrity guards. Includes a bundled offline demo task and Chain-of-Evid

One private investor's research, kept in public and put to the test: theses on seven US-listed companies, each with 20-30 tests that could prove it wrong; earnings forecasts timestamped before results and scored after; a public mistakes log

Portable, LLM-agnostic framework for multi-model AI workflows: model routing, structured agent handoff (AAHP), and a phased agent pipeline. MIT.

A self-improving Claude Code setup

This is a simulated Digital FTE project — a real Claude Code project built using the Agent Factory methodology. Every file is genuine: settings.json with hooks, SKILL.md with YAML frontmatter, agents, plugins, and MCP configs. Click any fil

A Claude Code project template that makes an AI agent build software under enforcement — deterministic machine gates, automatic test→requirement traceability, and an evidence-gated completion contract — instead of on model goodwill. Ships w

Independent audit agent for Claude Code: audits an app built by another agent (OWASP ASVS/Top 10 security, every feature, UI via Playwright, single source of truth, repo hygiene, git practice, token efficiency), never writes code, hands fin

A Claude Code kit: a push guard that holds a push until a leak scan and one audit have cleared HEAD.

A harness that ships a development process to coding agents and enforces it. One YAML catalog projects instructions, skills, subagents and permissions to Claude, Codex and Copilot. Git hooks refuse bad work at commit time. A loop drives eac

Claude Code mods that show your work items, tasks and sessions, for any tracker. Mods show and ask; they never enforce.