System prompt assembly registry for the DeepSeek Harness

Strix MCP Proxy — the distribution wedge for governed agent tool execution. Point your MCP client at the proxy instead of the underlying server; every callTool is intercepted, evaluated against policy, and emits a signed Ed25519 receipt. Designed so Mode

Node.js native addon build tool

System prompt assembly registry for the DeepSeek Harness

Pure-logic core of Principles Disciple, an AI Agent Governance System - pain signal capture and principle proposal (no I/O)

NestJS enforcement point for Xema entitlement. Resolves the installation license offline via @xemahq/license-verifier, gates biome installation and the running edition against it, and projects it onto the platform Edition + feature-flag axis. Fails closed

Local cost/complexity-aware model router for Oh My Pi, backed by OpenRouter

ESLint plugin for Jupyter core and extensions with early error catching and best practices enforcement

CLI tool to analyze unused and missing CSS variables across adapter packages

Self-judging agent orchestration layer for OpenCode. Reads memory, scores sessions, dispatches decisions.

VisIQ agent-governance plugin for the OpenClaw CLI — action governance on every tool call, retrieval governance on its configured retrieval tools, and audit-trail reporting, wired into OpenClaw's own tool hooks.

Security scanner for PostHog's agentic flows

Model-facing ask_user_question tool over the ctx.userInteraction seam

SynergyERP frontend standards — ESLint, Prettier, commitlint, Husky, Vitest, TypeScript configs, modularization enforcement, and PR templates.

Official WrongStack collection of focused plugins for code quality, security, observability, planning, and agent coordination

Local-first governed tool execution gateway for AI agents. Read/write classification, policy evaluation, signed execution receipts, multi-key rotation with cross-signed chain snapshots, per-capability rate limits, threshold-based escalation, file/webhook

Scaffold a MetaMynd/AgentSafe-governed AI agent in one command — logs in, provisions the agent (identity + mandate + SOP + Standards) in a single call, writes agent.metamynd.json plus a runnable agent + separate tool-gateway process that closes direct-cal

AI coding firewall for Codex and Claude Code

Native ADLC plugin for the GitHub Copilot CLI: skills, hooks, MCP tools, and read-only prosecution agents.

Detect if code is running in an AI agent or automated development environment