thomascasali/claude-kb-workflow
Knowledge that crosses your projects: Claude Code native memory is per-project and per-machine, this adds the layer above. Sessions become a wiki; a page reaches the stable cross-project KB only after a numeric bar: 2+ projects, 2+ sessions
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 thomascasali/claude-kb-workflow/agents ./rig-claude-kb-workflow/agents $ npx degit thomascasali/claude-kb-workflow/commands ./rig-claude-kb-workflow/commands $ npx degit thomascasali/claude-kb-workflow/skills ./rig-claude-kb-workflow/skills
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 thomascasali/claude-kb-workflow/skills/brainstorming-design .claude/skills/brainstorming-design $ npx degit thomascasali/claude-kb-workflow/skills/debugging-sistematico .claude/skills/debugging-sistematico $ npx degit thomascasali/claude-kb-workflow/skills/deploy-production-skill .claude/skills/deploy-production-skill $ npx degit thomascasali/claude-kb-workflow/skills/educational-presentation-skill .claude/skills/educational-presentation-skill $ npx degit thomascasali/claude-kb-workflow/skills/flutter-production-skill .claude/skills/flutter-production-skill $ npx degit thomascasali/claude-kb-workflow/skills/verifica-prima-di-completare .claude/skills/verifica-prima-di-completare
$ curl -fsSL --create-dirs -o .claude/agents/README-AGENTI.md https://raw.githubusercontent.com/thomascasali/claude-kb-workflow/main/agents/README-AGENTI.md $ curl -fsSL --create-dirs -o .claude/agents/backend-dev.md https://raw.githubusercontent.com/thomascasali/claude-kb-workflow/main/agents/backend-dev.md $ curl -fsSL --create-dirs -o .claude/agents/ci-cd.md https://raw.githubusercontent.com/thomascasali/claude-kb-workflow/main/agents/ci-cd.md $ curl -fsSL --create-dirs -o .claude/agents/database.md https://raw.githubusercontent.com/thomascasali/claude-kb-workflow/main/agents/database.md $ curl -fsSL --create-dirs -o .claude/agents/deep-reasoner.md https://raw.githubusercontent.com/thomascasali/claude-kb-workflow/main/agents/deep-reasoner.md $ curl -fsSL --create-dirs -o .claude/agents/devops.md https://raw.githubusercontent.com/thomascasali/claude-kb-workflow/main/agents/devops.md $ curl -fsSL --create-dirs -o .claude/agents/fast-worker.md https://raw.githubusercontent.com/thomascasali/claude-kb-workflow/main/agents/fast-worker.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-dev.md https://raw.githubusercontent.com/thomascasali/claude-kb-workflow/main/agents/frontend-dev.md $ curl -fsSL --create-dirs -o .claude/agents/integrations.md https://raw.githubusercontent.com/thomascasali/claude-kb-workflow/main/agents/integrations.md $ curl -fsSL --create-dirs -o .claude/agents/mobile-dev.md https://raw.githubusercontent.com/thomascasali/claude-kb-workflow/main/agents/mobile-dev.md $ curl -fsSL --create-dirs -o .claude/agents/realtime-dev.md https://raw.githubusercontent.com/thomascasali/claude-kb-workflow/main/agents/realtime-dev.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/thomascasali/claude-kb-workflow/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security.md https://raw.githubusercontent.com/thomascasali/claude-kb-workflow/main/agents/security.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 (6)
brainstorming-designdebugging-sistematicodeploy-productioneducational-presentationflutter-productionverifica-prima-di-completare
Subagents (13)
| README-AGENTI | — |
| backend-dev model: sonnet | Sviluppo backend Laravel (PHP) e Node.js/Express - API, modelli, migrazioni, servizi, queue. Usalo per implementare feature backend nei progetti dell'ecosistema. |
| ci-cd model: sonnet | CI/CD e release - GitHub Actions tag-triggered, build Flutter iOS/Android (runner macOS self-hosted, Codemagic), firma, store deploy, secrets di pipeline. Usalo per pipeline e rilasci. |
| database model: sonnet | Database - MySQL, MongoDB, PostgreSQL, Firestore: schema, migrazioni, indici, query lente, backup. Usalo per lavoro su schema e dati. |
| deep-reasoner model: opus | Fasi ad alto ragionamento - architettura, debug complesso, design di algoritmi. Pensa a fondo, restituisci una conclusione concisa su cui l'orchestratore possa agire. |
| devops model: sonnet | DevOps - Docker/Traefik/deploy.sh su VPS, reti, certificati, backup. Usalo per deploy, container e infrastruttura. |
| fast-worker model: sonnet | Compiti meccanici - parti standard, test, formattazione, modifiche semplici. Esegui in modo efficiente. |
| frontend-dev model: sonnet | Sviluppo frontend Vue 3 e React - componenti, store, routing, Tailwind/MUI, build Vite. Usalo per implementare UI e viste. |
| integrations model: sonnet | Integrazioni esterne - Stripe, SumUp, email SMTP, push FCM, Telegram, API AI. Usalo per collegare servizi terzi seguendo i pattern KB. |
| mobile-dev model: sonnet | Sviluppo mobile Flutter/Dart - Riverpod/Provider, build iOS via runner macOS/self-hosted, CI tag-triggered, store deploy. Usalo per le app mobile dei progetti. |
| realtime-dev model: sonnet | Real-time - Socket.io, WebSocket, Pusher, MQTT/ESP32, WebRTC: room, stato server-authoritative, riconnessioni. Usalo per feature real-time e IoT. |
| reviewer model: opus | Code review, debug complesso e QA - analisi cause radice, regressioni, verifica pre-deploy. Usalo per rivedere lavoro fatto o inchiodare bug. |
| security model: opus | Sicurezza - JWT/auth, social login Google+Apple (standard KB), CORS, hardening, gestione secret. Usalo per superfici di autenticazione e sicurezza. |
Slash commands (5)
/kb-ingest/kb-lint/kb-output/kb-promote/kb-query
Similar rigs
GinVlad/claude-saas-template
Claude Code template for building SaaS with agentic AI coordination. 5-stage workflow
Orchestrator 612 tok ·
jeroromano/claude-code-orchestration-template
—
Pragmatist 2.2k tok ·
navox-labs/agents
15-agent AI engineering team for Claude Code. Full sprint cycle: Think, Plan, Build, Review, Test, Ship, Reflect. Zero dependencies.
Orchestrator 5.1k tok ·
IntuitivePhella/AI-PhellOS
Portable AI development workflow template and CLI for spec-driven, test-aware software delivery with Codex, Claude Code, and other coding agents.
Orchestrator 3.1k tok ·