Turns one Claude Code session into a standing relay between a komnet network and the other Claude sessions on this machine. The gateway session watches the komnet inbox, pushes arriving remote messages into whichever local session is waiting for them, and carries their replies back out — so a session that knows…
★not rated 7 7d agoA
tokens not measured
originalMIT
MCP server and agent skills for the Truesight AI quality platform. Score inputs, build evaluations, analyze errors, and review results through natural language.
★not rated 7 5mo agoA
tokens not measured
originalMIT
Skills and an MCP server for building on MapleStory Universe game data. The bundled maple-lookup MCP server searches the MSU Open API for characters, mobs, maps, skills, items, and sprites; the skills cover how that data is structured, how to choose between candidates, and how to turn it into something that renders.…
An adapt-first playbook that helps Opus (or any Claude model) pick up the work habits that made Fable effective — render-level verification, hypothesis-driven debugging, delegation guards, input fidelity, confirm-before-irreversible, and execution rhythm. It does NOT auto-inject rules or fake model capability. Its…
★not rated 7 2mo agoA
tokens not measured
originalMIT
Critical thinking platform for decision analysis, proposal review, debate preparation, and due diligence. Three agents (advocate, adversary, judge) over a grounded argument graph, with a live transcript UI, appeal review, and 10 reasoning traditions.
★not rated 7
changed 5d agoA
tokens not measured
originalMIT
Turn any data file (CSV, Excel, SQLite, JSON/JSONL, Markdown, logs) into a single-file interactive HTML experience or a static infographic PNG. Ships a five-style report design bank, a level-keyed infographic bank (eli5/junior/pro), an infographic-director agent that writes data-story briefs, and a design-adapter…
Take a GitHub issue (bare, or tracked on a Project board) from triage to a merge-ready PR through a gated, worktree-isolated pipeline that scales its depth to the task and asks at most one batched question. The gates hold every run: design hardening, tests green, code review clean. Once you approve the PR in-session…
★not rated 7
changed todayA
tokens not measured
originalMIT
A diagram you talk back to — render a plan, an existing codebase, or a feature as an interactive architecture graph, edit it directly (drag, reconnect, comment), and send the structured edits back to the agent.
★not rated 7 1mo agoA
tokens not measured
originalMIT
Security scanner for AI-agent configuration files — detects prompt injection, dangerous permissions, and credential exposure in settings.json, CLAUDE.md, MCP configs, and more.
★not rated 7 7d agoA
tokens not measured
originalApache-2.0
A full email client for AI agents — Claude, Codex, Cursor or any MCP client: search, read, draft, send, organise and export mail across iCloud, Outlook.com, work/school Exchange, Gmail, QQ and any IMAP mailbox. Credentials stay on your own machine.
★not rated 7 29d agoA
tokens not measured
originalMIT
Library-agnostic design-quality toolkit for Pencil (.pen) files and any companion codebase. Enforces a universal 4px-grid sizing scale, variable-first design tokens, and component extraction at the second repetition - independent of CSS framework. Ships three read-only subagents (pencil-auditor for quality enforcemen.
★not rated 7
changed 3d 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: