mtarcure/claude-vibe-squad
Markdown-first multi-model AI orchestration in one tmux session. A single coordinator (Chrono) routes scoped markdown task packets across 4 frontier model lanes (GPT-5.6 Sol / Claude Opus 5 + Fable 5 / Gemini 3.5 / Kimi K3) and 73 role-base
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit mtarcure/claude-vibe-squad/chrono/.claude ./rig-claude-vibe-squad # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit mtarcure/claude-vibe-squad/.agents/skills/accessible-media-authoring .claude/skills/accessible-media-authoring $ npx degit mtarcure/claude-vibe-squad/.agents/skills/agent-prompt-engineering .claude/skills/agent-prompt-engineering $ npx degit mtarcure/claude-vibe-squad/.agents/skills/agentic-safety-audit .claude/skills/agentic-safety-audit $ npx degit mtarcure/claude-vibe-squad/.agents/skills/audio-event-map-authoring .claude/skills/audio-event-map-authoring $ npx degit mtarcure/claude-vibe-squad/.agents/skills/auto-scaffold .claude/skills/auto-scaffold $ npx degit mtarcure/claude-vibe-squad/.agents/skills/chain-construct-smart-contract .claude/skills/chain-construct-smart-contract $ npx degit mtarcure/claude-vibe-squad/.agents/skills/chain-construct .claude/skills/chain-construct $ npx degit mtarcure/claude-vibe-squad/.agents/skills/claim-verification .claude/skills/claim-verification $ npx degit mtarcure/claude-vibe-squad/.agents/skills/code-reachability-audit .claude/skills/code-reachability-audit $ npx degit mtarcure/claude-vibe-squad/.agents/skills/code-review-loop .claude/skills/code-review-loop $ npx degit mtarcure/claude-vibe-squad/.agents/skills/color-theory .claude/skills/color-theory $ npx degit mtarcure/claude-vibe-squad/.agents/skills/conversation-design .claude/skills/conversation-design $ npx degit mtarcure/claude-vibe-squad/.agents/skills/copy-refinement .claude/skills/copy-refinement $ npx degit mtarcure/claude-vibe-squad/.agents/skills/cosmos-sdk-audit-checklist .claude/skills/cosmos-sdk-audit-checklist $ npx degit mtarcure/claude-vibe-squad/.agents/skills/cross-chain-bridge-audit .claude/skills/cross-chain-bridge-audit $ npx degit mtarcure/claude-vibe-squad/.agents/skills/cross-file-relationship-synthesis .claude/skills/cross-file-relationship-synthesis $ npx degit mtarcure/claude-vibe-squad/.agents/skills/data-flow-trace .claude/skills/data-flow-trace $ npx degit mtarcure/claude-vibe-squad/.agents/skills/dedup-prior-art-check .claude/skills/dedup-prior-art-check $ npx degit mtarcure/claude-vibe-squad/.agents/skills/defi-invariant-check .claude/skills/defi-invariant-check $ npx degit mtarcure/claude-vibe-squad/.agents/skills/dependency-cycle-audit .claude/skills/dependency-cycle-audit $ npx degit mtarcure/claude-vibe-squad/.agents/skills/dependency-health-triage .claude/skills/dependency-health-triage $ npx degit mtarcure/claude-vibe-squad/.agents/skills/detection-as-code .claude/skills/detection-as-code $ npx degit mtarcure/claude-vibe-squad/.agents/skills/diff-aware-semgrep-scan .claude/skills/diff-aware-semgrep-scan $ npx degit mtarcure/claude-vibe-squad/.agents/skills/differential-review .claude/skills/differential-review $ npx degit mtarcure/claude-vibe-squad/.agents/skills/dimensional-analysis-check .claude/skills/dimensional-analysis-check $ npx degit mtarcure/claude-vibe-squad/.agents/skills/dual-level-retrieval .claude/skills/dual-level-retrieval $ npx degit mtarcure/claude-vibe-squad/.agents/skills/durable-nonce-exploitation .claude/skills/durable-nonce-exploitation $ npx degit mtarcure/claude-vibe-squad/.agents/skills/erc1271-revert-data-check .claude/skills/erc1271-revert-data-check $ npx degit mtarcure/claude-vibe-squad/.agents/skills/error-based-ssti .claude/skills/error-based-ssti $ npx degit mtarcure/claude-vibe-squad/.agents/skills/evm-audit-flow .claude/skills/evm-audit-flow $ npx degit mtarcure/claude-vibe-squad/.agents/skills/figma-implement-design .claude/skills/figma-implement-design $ npx degit mtarcure/claude-vibe-squad/.agents/skills/findings-filter .claude/skills/findings-filter $ npx degit mtarcure/claude-vibe-squad/.agents/skills/forensic-timeline-authoring .claude/skills/forensic-timeline-authoring $ npx degit mtarcure/claude-vibe-squad/.agents/skills/game-design-fundamentals .claude/skills/game-design-fundamentals $ npx degit mtarcure/claude-vibe-squad/.agents/skills/game-mechanics-balancing .claude/skills/game-mechanics-balancing $ npx degit mtarcure/claude-vibe-squad/.agents/skills/head-tail .claude/skills/head-tail $ npx degit mtarcure/claude-vibe-squad/.agents/skills/incident-response-runbook .claude/skills/incident-response-runbook $ npx degit mtarcure/claude-vibe-squad/.agents/skills/interactive-audio-design .claude/skills/interactive-audio-design $ npx degit mtarcure/claude-vibe-squad/.agents/skills/interface-ambiguity-check .claude/skills/interface-ambiguity-check $ npx degit mtarcure/claude-vibe-squad/.agents/skills/keyword-clustering .claude/skills/keyword-clustering
$ curl -fsSL --create-dirs -o .claude/agents/accessibility-engineer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/accessibility-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/agentops.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/agentops.md $ curl -fsSL --create-dirs -o .claude/agents/ai-engineer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/ai-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/asset-provenance-and-rights-auditor.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/asset-provenance-and-rights-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/backend-engineer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/backend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/bounty-researcher.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/bounty-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/brand-voice.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/brand-voice.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/content-verifier.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/content-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/data-extraction-engineer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/data-extraction-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/database-engineer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/database-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/detection-engineer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/detection-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/devops-engineer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/devops-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/editor.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/editor.md $ curl -fsSL --create-dirs -o .claude/agents/exodia.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/exodia.md $ curl -fsSL --create-dirs -o .claude/agents/experimental-attacker.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/experimental-attacker.md $ curl -fsSL --create-dirs -o .claude/agents/exploit-developer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/exploit-developer.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-engineer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/frontend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/game-designer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/game-designer.md $ curl -fsSL --create-dirs -o .claude/agents/game-engineer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/game-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/growth-and-search-analyst.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/growth-and-search-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/harness-optimizer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/harness-optimizer.md $ curl -fsSL --create-dirs -o .claude/agents/ichigo.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/ichigo.md $ curl -fsSL --create-dirs -o .claude/agents/image-designer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/image-designer.md $ curl -fsSL --create-dirs -o .claude/agents/impact-validator.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/impact-validator.md $ curl -fsSL --create-dirs -o .claude/agents/incident-responder.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/incident-responder.md $ curl -fsSL --create-dirs -o .claude/agents/interactive-audio-designer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/interactive-audio-designer.md $ curl -fsSL --create-dirs -o .claude/agents/kestrel.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/kestrel.md $ curl -fsSL --create-dirs -o .claude/agents/knowledge-librarian.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/knowledge-librarian.md $ curl -fsSL --create-dirs -o .claude/agents/large-context-analyst.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/large-context-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/level-narrative-designer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/level-narrative-designer.md $ curl -fsSL --create-dirs -o .claude/agents/localization-specialist.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/localization-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/loop-operator.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/loop-operator.md $ curl -fsSL --create-dirs -o .claude/agents/mac-ops.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/mac-ops.md $ curl -fsSL --create-dirs -o .claude/agents/memory-curator.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/memory-curator.md $ curl -fsSL --create-dirs -o .claude/agents/music-composer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/music-composer.md $ curl -fsSL --create-dirs -o .claude/agents/performance-optimizer.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/performance-optimizer.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/privacy-steward.md https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/model-lanes/claude/.claude/agents/privacy-steward.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (88)
accessible-media-authoringagent-prompt-engineeringagentic-safety-auditaudio-event-map-authoringauto-scaffoldchain-construct-smart-contractchain-constructclaim-verificationcode-reachability-auditcode-review-loopcolor-theoryconversation-designcopy-refinementcosmos-sdk-audit-checklistcross-chain-bridge-auditcross-file-relationship-synthesisdata-flow-tracededup-prior-art-checkdefi-invariant-checkdependency-cycle-auditdependency-health-triagedetection-as-codediff-aware-semgrep-scandifferential-reviewdimensional-analysis-checkdual-level-retrievaldurable-nonce-exploitationerc1271-revert-data-checkerror-based-sstievm-audit-flowfigma-implement-designfindings-filterforensic-timeline-authoringgame-design-fundamentalsgame-mechanics-balancinghead-tailincident-response-runbookinteractive-audio-designinterface-ambiguity-checkkeyword-clusteringknowledge-base-integrationknown-advisory-backport-checklayered-analysis-looplevel-design-patternslocale-adaptationmulti-stance-audit-fanoutnarrative-structureosint-platform-auditparser-differential-route-confusionpersuasive-technical-writingplatform-complianceplayer-engagement-psychologypre-audit-threat-modelprogram-rubric-lookupread-only-reentrancy-checkrequirements-elicitationreview-severity-ladderrule6-rights-gaterule8-truth-gatesandbox-provision-disciplinescope-decompositionscope-estimationsecurity-ownership-mapsecurity-threat-modelsemgrep-rule-authorsignature-validation-auditskill-description-trigger-authoringsolana-audit-flowsound-design-principlesstructured-data-authoringsupply-chain-auditsystematic-attackingsystematic-bug-huntingtake-over-resumetechnical-seo-audituniswap-v4-hook-access-controlvariant-analysisvibecheckvideo-post-productionvirality-analysisvisual-regression-baselinevisual-verifyvoice-performance-directionvulnhunter-solanawcag-conformance-auditde-ai-before-deliverylane-budget-estimationmode-selection
Subagents (70)
| accessibility-engineer model: inherit | Thin Claude adapter for accessibility-engineer; canonical brief is authoritative. |
| agentops model: inherit | Runtime, doctor, status drift, and agent operations. |
| ai-engineer model: inherit | Thin Claude adapter for ai-engineer; canonical brief is authoritative. |
| architect model: inherit | System design and tradeoff judgment; Codex reviews implementation feasibility. |
| asset-provenance-and-rights-auditor model: inherit | Thin Claude adapter for asset-provenance-and-rights-auditor; canonical brief is authoritative. |
| backend-engineer model: inherit | Thin Claude adapter for backend-engineer; canonical brief is authoritative. |
| bounty-researcher model: inherit | Thin Claude adapter for bounty-researcher; canonical brief is authoritative. |
| brand-voice model: inherit | Thin Claude adapter for brand-voice; canonical brief is authoritative. |
| code-reviewer model: inherit | Thin Claude adapter for code-reviewer; canonical brief is authoritative. |
| content-verifier model: inherit | Thin Claude adapter for content-verifier; canonical brief is authoritative. |
| data-extraction-engineer model: inherit | Thin Claude adapter for data-extraction-engineer; canonical brief is authoritative. |
| database-engineer model: inherit | Thin Claude adapter for database-engineer; canonical brief is authoritative. |
| detection-engineer model: inherit | Thin Claude adapter for detection-engineer; canonical brief is authoritative. |
| devops-engineer model: inherit | Thin Claude adapter for devops-engineer; canonical brief is authoritative. |
| editor model: inherit | Thin Claude adapter for editor; canonical brief is authoritative. |
| exodia model: inherit | Thin Claude adapter for exodia; canonical brief is authoritative. |
| experimental-attacker model: inherit | Thin Claude adapter for experimental-attacker; canonical brief is authoritative. |
| exploit-developer model: inherit | Thin Claude adapter for exploit-developer; canonical brief is authoritative. |
| frontend-engineer model: inherit | Thin Claude adapter for frontend-engineer; canonical brief is authoritative. |
| game-designer model: inherit | Thin Claude adapter for game-designer; canonical brief is authoritative. |
| game-engineer model: inherit | Thin Claude adapter for game-engineer; canonical brief is authoritative. |
| growth-and-search-analyst model: inherit | Hybrid research_synthesis + content_text. Backup is codex — Kimi must NEVER be the quality backup. Kimi throughput is allowed ONLY for deterministic, supplied-data metadata templating under the conjun |
| harness-optimizer model: inherit | Audit-oriented prompt, tool, and script drift role; implementation charter remains a future split. |
| ichigo model: inherit | Thin Claude adapter for ichigo; canonical brief is authoritative. |
| image-designer model: inherit | Thin Claude adapter for image-designer; canonical brief is authoritative. |
| impact-validator model: inherit | Thin Claude adapter for impact-validator; canonical brief is authoritative. |
| incident-responder model: inherit | Thin Claude adapter for incident-responder; canonical brief is authoritative. |
| interactive-audio-designer model: inherit | Thin Claude adapter for interactive-audio-designer; canonical brief is authoritative. |
| kestrel model: inherit | Thin Claude adapter for kestrel; canonical brief is authoritative. |
| knowledge-librarian model: inherit | Vault organization, links, and durable knowledge hygiene; Google Drive is a controller-smoked read path requiring typed handoff until squad-lane access is verified. |
| large-context-analyst model: inherit | Long-context analysis moves from Kimi to Fable because Fable and Sol provide the required context and judgment. Direct metered tools require bounded opt-in; Perplexity remains partial with the truth g |
| level-narrative-designer model: inherit | Thin Claude adapter for level-narrative-designer; canonical brief is authoritative. |
| localization-specialist model: inherit | Thin Claude adapter for localization-specialist; canonical brief is authoritative. |
| loop-operator model: inherit | Bounded autonomous loops, checkpoints, and stall detection. |
| mac-ops model: inherit | Local Mac and process hygiene, launchd, tmux, and shell environment. |
| memory-curator model: inherit | Memory, vault, brain-map hygiene, and public-private boundary checks. |
| music-composer model: inherit | Thin Claude adapter for music-composer; canonical brief is authoritative. |
| performance-optimizer model: inherit | Thin Claude adapter for performance-optimizer; canonical brief is authoritative. |
| planner model: inherit | Plans dispatch shape, write ownership, and parallel safety. Conductor is a partial spec-driven planning framework, not a swarm/subagent dispatcher; Drive access requires controller handoff.; degrades[ |
| privacy-steward model: inherit | Thin Claude adapter for privacy-steward; canonical brief is authoritative. |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| UserPromptSubmit | * | bash "${CLAUDE_PROJECT_DIR:-.}/../bin/context-tripwire.sh" |
Slash commands (2)
/status/stop
Plugins (1)
chrono-media-studio@claude-vibe-squad
Similar rigs
VersoXBT/claude-initial-setup
75 skills, 14 agents, 15 commands for Claude Code. Plug-and-play starter kit covering TypeScript, Python, Go, Rust, React, Next.js, FastAPI, Django, Docker, CI/CD, security, testing, and more. Cross-AI support for Cursor, Copilot, and Codex
Orchestrator 5.1k tok ·
stretchcloud/claude-code-unified-agents
—
Orchestrator 1.8k tok ·
maltehedderich/master-class-agents
A curated collection of AI agent templates, built on the architectural principles and design patterns taught by the most influential voices in the field.
Orchestrator 2.6k tok ·
YousefNabil-SOC/claude-apex
Public mirror + teaching install of my Claude Code environment: 1,276 skills, 185 agents, 235 commands, 8 wired MCP servers, three-layer auto-routing (10 CARL domains). Curated original core + the open plugin/marketplace ecosystem, all cred
Orchestrator 5.4k tok ·