Voice channel for Claude Code — ambient voice control via a LAN dispatcher with local Whisper STT and Piper TTS. Requires the voice-dispatcher service running on your laptop.
Enterprise architecture astronaut mode. Forces maximum abstraction, design patterns, and production-ready overengineering on every solution. Code still works — it's just impossible to understand without a whiteboard.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Verifies test-count claims against what your suite actually did, before a commit lands. Supports pytest, vitest and jest. If the message makes no claim, it does nothing.
★not rated 2 2d agoA
tokens not measured
originalMIT
Your GitHub Issues as a live roadmap board pinned beside Claude Code chat. Runs a local 127.0.0.1 board server and adds SessionStart/UserPromptSubmit hooks so the pane follows your active project.
★not rated 2 23d agoA
tokens not measured
originalMIT
GitHub issues+milestones tracking convention and project spine: recursive-spine-method, recursive-spine-bootstrap, recursive-spine-migrate, recursive-spine-digest, recursive-spine-pollinate, recursive-spine-scaffold, recursive-spine-handover, recursive-spine-nudge. State lives where it's queryable, not where it merges.
AI image and video generation Creative Director. Claude interprets intent, selects domain expertise, constructs optimized prompts, and orchestrates best-in-class AI models for stunning results.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Keeps MCP-server config in sync between Claude Code and Claude Desktop via a SessionStart hook, and reports the manual steps for anything that can't be auto-synced.
★not rated 2 25d agoA
tokens not measured
originalMIT
Build engineering digital twins as code with AI agents: one source-of-truth design.json mirrored into the build, a cited material-property source of truth (materials.json — never hallucinated allowables), every requirement gets an executable scored audit (PASS/WARN/FAIL), uv PEP723 scripts, rerun visualization (toward.
★not rated 2 3mo agoA
tokens not measured
originalMIT
Idea-to-playable harness for Expo (React Native + TypeScript) apps and games: research, plan, design, contract, and a generator-evaluator build loop with skeptical QA. --kind app|game.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Intent-alignment plugin for coding agents: requirement-analysis playbook, three-level intent funnel with file-in-the-loop persistence, and an optional red-blue adversarial review skill. DingTalk group channel and blocking gates live in the intent-gate-service sister MCP service.
★not rated 2 28d agoA
tokens not measured
originalMIT
Microsoft Teams channel for Claude Code: DMs and mention-gated channel messages over the Microsoft Agents SDK, with tenant/sender allowlists and pairing. Manage access via /msteams:access.
★not rated 2 yesterdayA
tokens not measured
originalMIT
Generate, edit, and batch-create images from inside Claude Code by delegating to OpenAI's Codex CLI (built-in gpt-image, billed against the user's ChatGPT subscription — no API key, no per-image $ charges).
★not rated 2 4mo agoA
tokens not measured
originalMIT
A review layer your agent applies to its own HTML or Markdown output in one command. You pin feedback to the exact word or element, and Markup Mode compiles each note to Markdown precise enough for the agent to act on, then hands it back. No backend, no build step.
★not rated 2 8d agoA
tokens not measured
originalMIT
Multi-account Gmail + Google Calendar + Google Drive + Google Tasks MCP server. Every tool takes an account slug (e.g. work | personal), so one Claude session can act across several Google accounts in parallel — send/draft/delete email, manage calendars, move/upload/share Drive files, and manage tasks. Accounts a.
★not rated 2
changed 3d agoA
tokens not measured
originalMIT
Conduct a parallel multi-session sprint: one conductor, several work managers in git worktrees, a file-based mailbox, watchdog supervision, and a clean teardown.
★not rated 2 1mo agoA
tokens not measured
originalMIT