Cross-platform desktop notification (Windows/macOS/Linux) when Claude Code finishes a turn. Windows path is ThreatLocker-safe (inline PowerShell). Configurable agent name, session label, icon, and optional sound.
A GTM strategist for Claude Code that researches before it reacts and refuses to flatter. Bottom-up market sizing, named ICP and wedge, motion-vs-math check, load-bearing assumptions, and a ranked verdict with kill criteria.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Skills and agents for Claude Code — visual verification, shareable HTML artifacts, arXiv research intake, model routing, deck and theme systems, and specialist advisor agents.
★not rated 1 9d agoA
tokens not measured
originalMIT
A plugin factory for AI coding agents: describe an idea and your agent builds — and ships — a complete, installable, multi-host plugin (skills, commands, subagents, MCP, hooks, manifest) on a proven golden-path architecture everything it grows inherits. One idempotent command, zero dependencies.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Run and verify code changes by driving the real app — launch it, interact with it, capture evidence. Ships the run, verify, and run-skill-generator skills for Claude Code, Codex, and Antigravity.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Turn scattered information into a durable, provenance-tracked knowledge base. Bundles the Odin skill (judgment) and the neutral Core MCP server (deterministic, invariant-guaranteeing ops). AI is the enabler, not the substrate — the knowledge persists as Markdown + links + git with no vendor lock-in (ADR-0008).
★not rated 1 15d agoA
tokens not measured
originalMIT
Local, no-network analytics for your Codex CLI usage — session stats, tool usage, streaks, burnout, git activity, cost/cache savings, team leaderboards — answerable right from chat via a bundled CLI.
★not rated 1 10d agoA
tokens not measured
originalMIT
Feynman-test partner for LaTeX lecture notes. Pattern-matches against pedagogical reference material (like Todorov's PDFs) and adds stunning visualizations, concrete-to-abstract progressions, and insight boxes. Making a concept teachable is how you discover whether you understand it well enough to write the paper.
★not rated 1 4d agoA
tokens not measured
originalMIT
An image-to-text bridge that lets the text-only DeepSeek model work with pictures. It uses codex exec to send images to gpt-5.4-mini, which returns structured descriptions in Chinese for the conversation.
Say what you want to build in one sentence. Fifteen superforge skills take it from idea to release gate with model tiering and file persistence, plus five Claude Code workflows that enforce the parts prose cannot.
★not rated 1 24d agoA
tokens not measured
originalMIT
The open operating system for building an AI-native company: a Handbook, a Dictionary, and AI skills, flows, loops, and advisor agents spanning the whole arc - frame, architect, build, trust, ship, grow, defend. Theme-agnostic.
★not rated 1 2mo agoA
tokens not measured
originalApache-2.0
An explicitly invoked, token-efficient harness for planning, implementing, and reviewing agent-driven software. It helps technical and non-technical users produce sustainable code through approval-gated specifications, pragmatic repository-aware standards, conditional expert lenses, safe Git workflows, and…
★not rated 1 1mo agoA
tokens not measured
originalMIT
Check MCP servers against the PolicyLayer registry before connecting to them.
★not rated 1 1mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: