Orchestrate autonomous project leads and multi-platform workflows from within Claude Code. Spawn persistent background agents, dispatch parallel tasks, generate images via Grok/Codex CLI, create videos with HyperFrames, post to social media (X, LinkedIn, Bluesky), and control browsers with Playwright. Integrates Telegram/Discord for voice intake and reminders.
Drafts social, blog, or technical content in the user's voice. Use when the user asks "draft a tweet about X", "write a blog post on Y", "compose a LinkedIn post about Z", or similar content-creation tasks.
The lead of an independent project workstream. Has its own cwd, its own agent team (created via TeamCreate), and its own Remote Control URL. Reports back to the Telegram orchestrator via SendMessage.
Publishes a Bluesky draft (produced by social-bluesky-writer) via the AT Protocol API. Reads credentials from ~/.claude-pw/bluesky.json, calls com.atproto.server.createSession for a session token, then posts each entry in the draft via app.bsky.feed.post. No Playwright — direct API only.
Produces a Bluesky post draft (or linked-reply thread) from a social campaign brief and supporting assets. Use when the social-publish skill needs a Bluesky draft. Outputs a structured JSON draft ready for social-bluesky-poster.
Scaffolds a new MCP server skeleton when the user says "I need a new MCP for X", "build an MCP that does Y", or "wrap Z in an MCP".
Generate or edit an image by delegating to the user's Codex CLI subscription. Use when the user requests "draw / render / generate / create / sketch / design an image of X" or similar. Returns a local PNG path which the Telegram channel will upload as a photo.
Generate an image via the grok CLI (/imagine command). Returns a local PNG/JPG path. Used as one of the two providers in parallel dual-image dispatch (the other is codex-image-gen). Do NOT call this inline — always dispatch via Agent so the channel stays responsive.
GSAP animation reference for HyperFrames. Covers gsap.to(), from(), fromTo(), easing, stagger, defaults, timelines (gsap.timeline(), position parameter, labels, nesting, playback), and performance (transforms, will-change, quickTo). Use when writing GSAP animations in HyperFrames compositions.
HyperFrames CLI tool — hyperframes init, lint, preview, render, transcribe, tts, doctor, browser, info, upgrade, compositions, docs, benchmark. Use when scaffolding a project, linting or validating compositions, previewing in the studio, rendering to video, transcribing audio, generating TTS, or troubleshooting the HyperFrames environment.
Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation (beat sync, glow, pulse driven by music), add animated text highlighting (marker sweeps, hand-drawn circles, burst lines, scribble, sketchout), or add transitions between scenes (crossfades, wipes, reveals, shader transitions). Covers composition authoring, timing, media, and the full video production workflow. For CLI commands (init, lint, preview, render, transcribe, tts) see the hyperframes-cli skill.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
soma.mayankgupta.in · by Mayank Gupta
Claude Soma (Greek soma, "body") gives Claude Code a body: a Telegram channel, voice in and out, a project orchestrator that spawns persistent, independent agent teams per workstream, social posting, and a showcase dashboard. It is authed entirely through a Claude Max subscription — no Anthropic API keys — and runs on a single Oracle Cloud Ubuntu ARM free-tier VPS.
Hermes-Agent by Nous Research is a ~27,000-line platform for self-improving messaging agents: channels, cron, skills, memory curation, sandbox backends, trajectory tooling. After studying it, the question this project answers is:
What if your engine is Claude Code? How much do you actually need to build?
The answer is a few thousand lines. Channels (Telegram, Discord, custom), agent teams, server-hosted scheduled routines, Remote Control, mobile push, MCP, hooks, plugins, and auto-memory are all native to Claude Code if you know where to look. The platform layer collapses; Claude Soma is the missing slice — a voice pipeline, a project orchestrator, social posting, a dashboard, and curated workflows — riding Claude Code's native rails.
voice-stt (whisper.cpp) transcribes voice memos;
voice-tts (piper -> opus) speaks replies.systemd unit
and tmux server, so a channel restart can't take it down.systemd timers and crontab, all surfaced together.The Telegram session is an orchestrator, not a team-lead. It spawns multiple independent project-leads, each in its own cgroup, each able to run its own agent team — sidestepping Claude Code's "one team per lead" constraint while giving you per-project specialization.

A request flows in on Telegram (text or voice); fast work is answered inline, slow work is dispatched to a background subagent so the channel stays responsive. Messaging a project-lead is delivered by typing into its tmux pane and reading the reply back from it — leads are independent processes, not chat teammates.

Each project-lead is spawned via sudo systemd-run into its own transient unit
and dedicated tmux socket, inherits all MCP servers except Telegram, and can
be attached to directly from the Claude mobile app or claude.ai/code via its
Remote Control URL. Three control surfaces, one Max account.

npx claudepluginhub techfreakworm/claude-somaUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Memory compression system for Claude Code - persist context across sessions
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.