Dimkox/Getzilla
AI speed. Engineering discipline. Getzilla lets an AI write code for your project and checks that code before it is allowed to stay.
stack: Python
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 Dimkox/Getzilla/.claude ./rig-getzilla # 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 Dimkox/Getzilla/.agents/skills/ai-rag-change .claude/skills/ai-rag-change $ npx degit Dimkox/Getzilla/.agents/skills/api-event-change .claude/skills/api-event-change $ npx degit Dimkox/Getzilla/.agents/skills/bitrix-development .claude/skills/bitrix-development $ npx degit Dimkox/Getzilla/.agents/skills/bugfix-workflow .claude/skills/bugfix-workflow $ npx degit Dimkox/Getzilla/.agents/skills/data-change .claude/skills/data-change $ npx degit Dimkox/Getzilla/.agents/skills/enterprise-integration .claude/skills/enterprise-integration $ npx degit Dimkox/Getzilla/.agents/skills/feature-workflow .claude/skills/feature-workflow $ npx degit Dimkox/Getzilla/.agents/skills/frontend-change .claude/skills/frontend-change $ npx degit Dimkox/Getzilla/.agents/skills/getzilla-delivery .claude/skills/getzilla-delivery $ npx degit Dimkox/Getzilla/.agents/skills/incident-response .claude/skills/incident-response $ npx degit Dimkox/Getzilla/.agents/skills/legacy-modernization .claude/skills/legacy-modernization $ npx degit Dimkox/Getzilla/.agents/skills/release-readiness .claude/skills/release-readiness $ npx degit Dimkox/Getzilla/.agents/skills/security-sensitive-change .claude/skills/security-sensitive-change $ npx degit Dimkox/Getzilla/.agents/skills/seo-landing .claude/skills/seo-landing $ npx degit Dimkox/Getzilla/.agents/skills/task-triage .claude/skills/task-triage $ npx degit Dimkox/Getzilla/.agents/skills/verification-evidence .claude/skills/verification-evidence
$ curl -fsSL --create-dirs -o .claude/agents/ai_architect.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/ai_architect.md $ curl -fsSL --create-dirs -o .claude/agents/ai_implementer.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/ai_implementer.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/bitrix_architect.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/bitrix_architect.md $ curl -fsSL --create-dirs -o .claude/agents/bitrix_implementer.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/bitrix_implementer.md $ curl -fsSL --create-dirs -o .claude/agents/bitrix_reviewer.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/bitrix_reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/code_reviewer.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/code_reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/data_architect.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/data_architect.md $ curl -fsSL --create-dirs -o .claude/agents/data_implementer.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/data_implementer.md $ curl -fsSL --create-dirs -o .claude/agents/data_reviewer.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/data_reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/docs_researcher.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/docs_researcher.md $ curl -fsSL --create-dirs -o .claude/agents/frontend_implementer.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/frontend_implementer.md $ curl -fsSL --create-dirs -o .claude/agents/general_implementer.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/general_implementer.md $ curl -fsSL --create-dirs -o .claude/agents/integration_architect.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/integration_architect.md $ curl -fsSL --create-dirs -o .claude/agents/integration_implementer.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/integration_implementer.md $ curl -fsSL --create-dirs -o .claude/agents/php_implementer.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/php_implementer.md $ curl -fsSL --create-dirs -o .claude/agents/release_reviewer.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/release_reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/repo_explorer.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/repo_explorer.md $ curl -fsSL --create-dirs -o .claude/agents/security_reviewer.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/security_reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/task_analyst.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/task_analyst.md $ curl -fsSL --create-dirs -o .claude/agents/test_reviewer.md https://raw.githubusercontent.com/Dimkox/Getzilla/main/.claude/agents/test_reviewer.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "python3 -c \"import os,pathlib,runpy,sys;t='.grok/hooks/pre_tool_use.py';p=pathlib.Path;d=p.cwd();e=[p(os.environ[k]) for k in ('CLAUDE_PROJECT_DIR','QWEN_PROJECT_DIR','GEMINI_PROJECT_DIR') if os.environ.get(k)];f=next(q/t for q in (*e,d,*d."
}
]
}
]
}
} Skills (16)
ai-rag-changeapi-event-changebitrix-developmentbugfix-workflowdata-changeenterprise-integrationfeature-workflowfrontend-changegetzilla-deliveryincident-responselegacy-modernizationrelease-readinesssecurity-sensitive-changeseo-landingtask-triageverification-evidence
Subagents (21)
| ai_architect | Design LLM/RAG/eval changes with tenant and safety boundaries. |
| ai_implementer | Implement LLM, RAG, prompt, embedding, or evaluation changes. |
| architect | Produce a bounded design for standard or high-risk delivery work. |
| bitrix_architect | Design Bitrix/D7 module, event, cache, and install-path changes. |
| bitrix_implementer | Implement Bitrix customizations under local/ using D7 APIs. |
| bitrix_reviewer | Review Bitrix diffs for core edits, lifecycle symmetry, and cache/permissions. |
| code_reviewer | Independent review of the final diff against task scope, any applicable change package and contracts. |
| data_architect | Design migrations, indexes, backfills, and analytical projections. |
| data_implementer | Implement versioned SQL/migrations, backfills, and search/analytics projections. |
| data_reviewer | Review schema, query, backfill, and recovery evidence. |
| docs_researcher | Recover facts from repository docs, ADRs, and contracts. Do not invent APIs. |
| frontend_implementer | Implement browser UI, client state, accessibility, and e2e coverage. |
| general_implementer | Default write owner for generic application changes. |
| integration_architect | Design external-system adapters, outbox, and reconciliation. |
| integration_implementer | Implement adapters, webhooks, and sync jobs against canonical models. |
| php_implementer | Implement PHP application changes with tests and conservative compatibility. |
| release_reviewer | Release/go-no-go review of rollback, observability, and remaining risk. |
| repo_explorer | Read-only map of repository structure, tests, and impact surface. |
| security_reviewer | Review authz, secrets, PII, tenant isolation, and irreversible actions. |
| task_analyst | Clarify outcomes, constraints, and acceptance criteria before design. |
| test_reviewer | Review test adequacy, characterization coverage, and verification evidence. |
Hooks (9)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | python3 -c "import os,pathlib,runpy,sys;t='.grok/hooks/session_start.py';p=pathlib.Path;d=p.cwd();e=[p(os.environ[k]) for k in ('CLAUDE_PROJECT_DIR','QWEN_PROJECT_DIR','GEMINI_PROJECT_DIR') if os.environ.get(k)];f=next(q/t for q in (*e,d,*d |
| UserPromptSubmit | * | python3 -c "import os,pathlib,runpy,sys;t='.grok/hooks/user_prompt_submit.py';p=pathlib.Path;d=p.cwd();e=[p(os.environ[k]) for k in ('CLAUDE_PROJECT_DIR','QWEN_PROJECT_DIR','GEMINI_PROJECT_DIR') if os.environ.get(k)];f=next(q/t for q in (*e |
| PreToolUse | * | python3 -c "import os,pathlib,runpy,sys;t='.grok/hooks/pre_tool_use.py';p=pathlib.Path;d=p.cwd();e=[p(os.environ[k]) for k in ('CLAUDE_PROJECT_DIR','QWEN_PROJECT_DIR','GEMINI_PROJECT_DIR') if os.environ.get(k)];f=next(q/t for q in (*e,d,*d. |
| PostToolUse | * | python3 -c "import os,pathlib,runpy,sys;t='.grok/hooks/post_tool_use.py';p=pathlib.Path;d=p.cwd();e=[p(os.environ[k]) for k in ('CLAUDE_PROJECT_DIR','QWEN_PROJECT_DIR','GEMINI_PROJECT_DIR') if os.environ.get(k)];f=next(q/t for q in (*e,d,*d |
| PreCompact | * | python3 -c "import os,pathlib,runpy,sys;t='.grok/hooks/pre_compact.py';p=pathlib.Path;d=p.cwd();e=[p(os.environ[k]) for k in ('CLAUDE_PROJECT_DIR','QWEN_PROJECT_DIR','GEMINI_PROJECT_DIR') if os.environ.get(k)];f=next(q/t for q in (*e,d,*d.p |
| SubagentStart | * | python3 -c "import os,pathlib,runpy,sys;t='.grok/hooks/subagent_start.py';p=pathlib.Path;d=p.cwd();e=[p(os.environ[k]) for k in ('CLAUDE_PROJECT_DIR','QWEN_PROJECT_DIR','GEMINI_PROJECT_DIR') if os.environ.get(k)];f=next(q/t for q in (*e,d,* |
| SubagentStop | * | python3 -c "import os,pathlib,runpy,sys;t='.grok/hooks/subagent_stop.py';p=pathlib.Path;d=p.cwd();e=[p(os.environ[k]) for k in ('CLAUDE_PROJECT_DIR','QWEN_PROJECT_DIR','GEMINI_PROJECT_DIR') if os.environ.get(k)];f=next(q/t for q in (*e,d,*d |
| Stop | * | python3 -c "import os,pathlib,runpy,sys;t='.grok/hooks/stop_gate.py';p=pathlib.Path;d=p.cwd();e=[p(os.environ[k]) for k in ('CLAUDE_PROJECT_DIR','QWEN_PROJECT_DIR','GEMINI_PROJECT_DIR') if os.environ.get(k)];f=next(q/t for q in (*e,d,*d.par |
| SessionEnd | * | python3 -c "import os,pathlib,runpy,sys;t='.grok/hooks/session_end.py';p=pathlib.Path;d=p.cwd();e=[p(os.environ[k]) for k in ('CLAUDE_PROJECT_DIR','QWEN_PROJECT_DIR','GEMINI_PROJECT_DIR') if os.environ.get(k)];f=next(q/t for q in (*e,d,*d.p |
Cursor rules (8)
getzilla/00-core · alwaysgetzilla/10-securitygetzilla/20-pythongetzilla/30-contracts-datagetzilla/40-testsgetzilla/50-agent-runtimegetzilla/60-frontendgetzilla/70-delivery
Similar rigs
VasulenkoIllia/claude-code-base
Claude Code setup for macOS on Apple Silicon: global rules, guard hooks with tests, skills and review agents. Installs into ~/.claude from a tag, with a snapshot and one-command rollback. README in English and Ukrainian.
Orchestrator 657 tok · · Q15
Dipen-Dedania/agent-pulse
Know what your agents are doing
Orchestrator 1.7k tok · · Q15
Yuutokata/claude-code-setup
🔄 One Claude Code setup for my desktop and MacBook, synced through git, with guardrails that keep secrets out.
Fort Knox 1.1k tok · · Q48
cfrs2005/claude-init
Claude Code 中文开发套件 - 为中国开发者定制的零门槛 AI 编程环境。一键安装完整中文化体验,集成 MCP 服务器、智能上下文管理、安全扫描,支持免翻墙访问。让 AI 编程更简单。
Orchestrator 1.5k tok · · Q0