shode666/shode-house
Multi-agent software engineering OS for Claude Code / Cowork — 19 agents in 7 teams, evidence-driven quality gates, domain experts (fintech/ERP/SAP/trading/insurance), token-aware context routing, behavioral A/B eval
field: FintechAI / ML workflow: Testing & TDDPR / code reviewFrontend & designSecurity reviewPlanning & specs
stack: Python
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
up to ~7.1k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Heavy · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add context7 -- npx -y @upstash/context7-mcp@latest $ npx degit shode666/shode-house/.claude ./rig-shode-house # 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.
$ claude mcp add context7 -- npx -y @upstash/context7-mcp@latest $ npx degit shode666/shode-house/.agents/skills/beads .claude/skills/beads $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/api-contract .claude/skills/api-contract $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/ask .claude/skills/ask $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/automate-test .claude/skills/automate-test $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/caveman .claude/skills/caveman $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/data-migration .claude/skills/data-migration $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/decompose .claude/skills/decompose $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/dev-gate .claude/skills/dev-gate $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/diagnose .claude/skills/diagnose $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/domain-core .claude/skills/domain-core $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/drain .claude/skills/drain $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/incident .claude/skills/incident $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/review-checklist .claude/skills/review-checklist $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/secure .claude/skills/secure $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/shode-house-deliverable .claude/skills/shode-house-deliverable $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/shode-house-discipline .claude/skills/shode-house-discipline $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/shode-house-routing .claude/skills/shode-house-routing $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/shode-house-workflow .claude/skills/shode-house-workflow $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/slo .claude/skills/slo $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/ui-test .claude/skills/ui-test $ npx degit shode666/shode-house/plugins/shode-house-antigravity/skills/web-q .claude/skills/web-q
$ curl -fsSL --create-dirs -o .claude/agents/build.md https://raw.githubusercontent.com/shode666/shode-house/main/agents/build.md $ curl -fsSL --create-dirs -o .claude/agents/design.md https://raw.githubusercontent.com/shode666/shode-house/main/agents/design.md $ curl -fsSL --create-dirs -o .claude/agents/operate.md https://raw.githubusercontent.com/shode666/shode-house/main/agents/operate.md $ curl -fsSL --create-dirs -o .claude/agents/plan.md https://raw.githubusercontent.com/shode666/shode-house/main/agents/plan.md $ curl -fsSL --create-dirs -o .claude/agents/secure.md https://raw.githubusercontent.com/shode666/shode-house/main/agents/secure.md $ curl -fsSL --create-dirs -o .claude/agents/verify.md https://raw.githubusercontent.com/shode666/shode-house/main/agents/verify.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| Context7 | npm | 1.2k |
Skills (21)
beadsapi-contractaskautomate-testcavemandata-migrationdecomposedev-gatediagnosedomain-coredrainincidentreview-checklistsecureshode-house-deliverableshode-house-disciplineshode-house-routingshode-house-workflowsloui-testweb-q
Subagents (6)
| build model: sonnet | Implements authorized features and fixes across the project stack (frontend, backend, business logic, databases, integration) with behavior tests; staff-grade briefs cover cross-team consistency, tech |
| design model: claude-fable-5 | UX research, information architecture, wireframes and design tokens, design system, accessibility (WCAG 2.2 AA), the ui review axis (Phase 3a), and design-run requests. Design authority; has no Bash a |
| operate model: sonnet | Runs delivery and reliability - Docker-first setup, CI/CD, IaC, deploy builds (Phase 5), and SLO, error budget, incident, runbook and postmortem work (Phase 6). Deploys only what is authorized. |
| plan model: sonnet | Product discovery, requirements and acceptance criteria, architecture and ADR, the spec review axis, and domain consult or the domain review axis (a domain reference loaded). Never writes product code |
| secure model: claude-fable-5 | Threat modeling (STRIDE/LINDDUN, Phase 1c), the security review axis, SAST/DAST, secrets management, pen testing and security headers. Sole owner of security depth; does not yield to "low risk". |
| verify model: sonnet | Independently verifies a change on one axis per spawn - standards (7-dimension code review, unit-test quality) or runtime (integration, contracts, end-to-end, load, accessibility automation). Requirem |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | bd prime --hook-json |
Slash commands (6)
/ask/consult/design-system/implement/init/review
Similar rigs
shode666/claude-skill-shode-house
Multi-agent software engineering OS for Claude Code / Cowork — 19 agents in 7 teams, evidence-driven quality gates, domain experts (fintech/ERP/SAP/trading/insurance), token-aware context routing, behavioral A/B eval
Orchestrator 7.1k tok · · Q23
pham-canh/space-harness
Model-agnostic harness kit for coding agents: capability profiles, context pruning, measured baselines. MIT.
Orchestrator 365 tok · · Q0
ooodnakov/ooodnakov-config
Opinionated eproducible personal dotfiles for Linux, Windows, and macOS machines.
Pragmatist 3.8k tok · · Q0
webdevtodayjason/dev-kit
Portable Claude Code dev workflow — skills, commands, agents, security hooks, and a CLAUDE.md template. One-install onboarding; ships zero credentials.
Skill Collector 2.4k tok · · Q0