AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assisted software engineering.

Open-source customer money path for usage-based SaaS — authorize customer spend before paid work runs.

OpenGhost is an Agent Skill for authorized web app penetration testing: Enter lab url paste credential your agent and wait everything does with help of openghost

Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.

The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Plugin, agent skills, and a GitHub Action.

Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-calibrated judges, gated self-update loop, pressure testing, 10 authoring principles grounded in empirical research.

Security testing toolkit for AI Agent: curated SecLists wordlists, injection payloads, and expert agents for authorized pentesting, CTFs, and bug bounties

AI agent skills for the personal operator's craft — decisions, research, second-brain, content rotation, scenario modeling, and meta-skills to author more. Works with Claude Code, Codex, Cursor.

AI Native Product Methodology — 80 executable skills across P0-P14 stages, covering needs discovery to aesthetic authority. From 8 books.

Agent-assisted maintainership and development framework for Apache projects — Triage, Mentoring, Drafting (agent-authored fixes with human review), and Pairing (developer-side dev-cycle) skills shipping; Agentic Autonomous (auto-merge) on the roadmap.

Scan any agent skill — authored or compiled — for prompt injection, secrets, and malicious execution before it touches your agent. Or compile the long tail on the fly.

AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 19 tools. Works with Claude, GPT-4, or local models. For authorized security research only.

Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.

Find and repair substance defects in AI-assisted prose, code, docs, and agent output. Reports defects, never authorship. Structural tests over model judgement, because LLM judges agree with human slop labels at chance.

OKF (Open Knowledge Format): Durable, structured memory for AI agents. Author, validate, consume, and maintain portable knowledge bundles through an ecosystem of Skills, MCP, an interactive graph, TUI, CLI, Docker, and a Claude Code plugin. 100% local.

Deepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, claims-ledger triangulation with dissent protection, relevance × authority evidence filter, multi-angle red team, four-layer citation verification. 105 blocks, 29 channels, 460+ stat sources, 47 APIs, 1072 verified endpoints.

Search global patents across WIPO, EPO, USPTO, CNIPA, JPO, KIPO and other authorities, together with scientific literature from PubMed, arXiv, Nature, Science and other major sources using natural-language, semantic, keyword and structured search.

Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a CV→DBLP-fact-checked academic homepage generator and hand-authored long-form blogs 🌱

Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.

A Claude Code plugin marketplace

Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!

Open agent skills and tool schemas for Superior Trade — build, backtest, and deploy trading strategies on Hyperliquid

A local MCP runtime that attacks what you own and only reports what it proved. 17 CVEs across 9 projects came out of this repo. Install: npx -y hacker-bob@latest install /path/to/project, then run /bob-evaluate target.com