mtarcure/claude-vibe-squad

Multi-model AI orchestration where behaviour is Markdown, not code. One coordinator routes scoped task packets to 71 role-based specialists across 5 model families (Codex / Claude / Gemini / Grok / Kimi) — each working in an isolated git worktree, each reviewed by a rival family before it lands. One tmux session, no server.

49Stars on the repository
146Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

README

01

mtarcure/claude-vibe-squad

Agent Claude Code

Generated from shared/specialist-runtime-map.tsv. Each adapter points back to canonical markdown.

not rated 49 yesterday A 0 tokens

architect

05

mtarcure/claude-vibe-squad

Agent Claude Code

System design and tradeoff judgment; Codex reviews implementation feasibility.

not rated 49 yesterday A 15 tokens

editor

16

mtarcure/claude-vibe-squad

Agent Claude Code

Thin Claude adapter for editor; canonical brief is authoritative.

not rated 49 yesterday A 13 tokens

fable

19

mtarcure/claude-vibe-squad

Agent Claude Code

Thin Claude adapter for fable; canonical brief is authoritative.

not rated 49 yesterday A 15 tokens

mtarcure/claude-vibe-squad

Agent Claude Code

Hybrid researchsynthesis + contenttext. Backup is codex — Kimi must NEVER be the quality backup. Kimi throughput is allowed ONLY for deterministic, supplied-data metadata templating under the conjunction gate; it EXCLUDES keyword research, SERP interpretation, analytics, recommendation, and schema selection, and any…

not rated 49 yesterday A 178 tokens

harness-optimizer

24

mtarcure/claude-vibe-squad

Agent Claude Code

Audit-oriented prompt, tool, and script drift role; implementation charter remains a future split.

not rated 49 yesterday A 23 tokens

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: