원클릭으로
methodology
Unified development methodology - IV&V, pipeline, quality gates
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Unified development methodology - IV&V, pipeline, quality gates
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
| name | methodology |
| description | Unified development methodology - IV&V, pipeline, quality gates |
| disable-model-invocation | true |
Every piece of work follows this pipeline in order:
| Phase | Name | What Happens |
|---|---|---|
| 1 | KICK | Work item created, assigned, context gathered |
| 2 | COLLECT | Requirements collected, existing code analyzed |
| 3 | SPEC | Specifications written (acceptance criteria, edge cases) |
| 4 | CHECK | Specs reviewed, approved before any code |
| 5 | BUILD | Code written following TDD (specs → tests → code → refactor) |
| 6 | MERGE | PR created, reviewed, E2E tested, merged |
Key rule: No code before specs are approved (Phase 4 → Phase 5).
The 18-stage pipeline orchestrator (dev-02:30092) enforces context isolation between builder and tester:
All work items (FIX-, CR-, FB-, WI-) use EXACTLY these 4 statuses:
| Status | Meaning | Who Sets It |
|---|---|---|
| pending | Not started | Default |
| started | Work in progress | Agent/supervisor when work begins |
| untested | Code deployed, awaiting user verification | Agent/supervisor after deploy |
| accepted | Formally accepted by user | USER ONLY — NEVER set by agent |
This is NOT the same as session reporting. When a worker reports to a supervisor about their session, they use DONE/PARTIAL/BLOCKED. Those are session report statuses, not work item statuses.
Work items are tracked in TRACKER.md in the project's run directory. Update status there when it changes.
For the full 18-stage automated pipeline, use the orchestrator at dev-02:30092. For manual work, follow the 6-phase pipeline above.
Load CI/CD pipeline configuration and deployment information when working with automation or deployments
Load database relationships, shared resources, and schema information when working with data models or database configuration
Load development environment information including folder structure, OrbStack setup, and system configuration
Load port mappings for all projects when working with networking, docker-compose, or service configuration
Load GitHub/GitLab repository information when working with git, CI/CD, or repository management
Load server information, infrastructure details, and access patterns when working with deployment or server configuration