gateway-backend
Route backend tasks to the right library skill. Detects intent and returns specific skill file paths to load.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Route backend tasks to the right library skill. Detects intent and returns specific skill file paths to load.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Deterministic AI development workflow orchestrator. Manages task boards (.jonggrang/jonggrang-tasks.json), runs 16-phase pipelines (BUGFIX/SMALL/MEDIUM/LARGE), installs lifecycle hooks for Claude Code and OpenCode, and coordinates five specialist roles (Lead/Developer/Reviewer/TestLead/Tester). Use when planning features, executing multi-step development workflows, or orchestrating AI coding agents. Run via npx jonggrang.
16-phase feature orchestration workflow. Runs in the main thread as Kernel Mode. Coordinates the Lead→Developer→Reviewer→TestLead→Tester assembly line.
Protocol for agents to write structured outputs that survive session resets and are findable by the orchestrator.
GitHub workflow automation with the gh CLI — pull requests, issues, releases, the REST/GraphQL API, and safe message escaping. Auth via GH_TOKEN (set in global settings, attached to the sandbox env).
GitLab workflow automation with the glab CLI — merge requests, issues, CI, releases, and safe message escaping. Auth via GITLAB_TOKEN (set in global settings, attached to the sandbox env).
Prevents premature exit and infinite loops. Three mechanisms: Completion Promises, Scratchpads, Loop Detection.
| name | gateway-backend |
| description | Route backend tasks to the right library skill. Detects intent and returns specific skill file paths to load. |
| type | gateway |
| tier | core |
| domains | ["backend","api","services"] |
| trigger | backend logic, server-side code, Node.js, Go, Python, Express, FastAPI, Rust, service layer, business logic |
You are the Backend Gateway. Your job is to detect intent from the current task and return the exact library skill paths that should be loaded. Do NOT execute the task — only route to the right knowledge.
Read the task description and match against these patterns:
| Intent Keywords | Load Skill |
|---|---|
tdd, test-driven, red-green, failing test first | skills/library/backend/developing-with-tdd/SKILL.md |
debug, diagnose, trace, investigate, root cause | skills/library/backend/debugging-systematically/SKILL.md |
auth, jwt, oauth, session, token, login | skills/library/backend/implementing-auth/SKILL.md |
middleware, interceptor, pipeline, chain | skills/library/backend/writing-middleware/SKILL.md |
cache, redis, memcache, invalidate | skills/library/backend/caching-strategies/SKILL.md |
queue, worker, job, background task, async | skills/library/backend/async-job-queues/SKILL.md |
websocket, realtime, socket.io, sse | skills/library/backend/realtime-connections/SKILL.md |
error handling, exception, retry, circuit breaker | skills/library/backend/error-handling-patterns/SKILL.md |
rate limit, throttle, ddos | skills/library/security/rate-limiting/SKILL.md |
Return ONLY this — no prose:
GATEWAY_BACKEND:
Domain: backend
Skills to load:
- [absolute/path/to/SKILL.md]
- [absolute/path/to/SKILL.md]
Instructions: Read the above skill files before proceeding with your task.
If no specific skill matches, return:
GATEWAY_BACKEND:
Domain: backend
Skills to load: none (proceed with general backend patterns)