메뉴
Agent resolution table, review mandates, and terminal style sweep for the scaffold development orchestrator running inside a Docker container against the ue-claude-scaffold project.
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
Use for any container agent that posts progress to the coordination server's message board. Defines the curl format, channels, message types, payload conventions, posting responsibilities, and verbosity levels.
Use when a review agent must produce structured output. Defines the BLOCKING/NOTE/Summary/Verdict template, the two-tier confidence rubric, and the JSON shadow block consumed by POST /tasks/:id/reviews. Compose with review-process and a domain skill.
Use when an agent evaluates the output of other agents or decides whether work meets the bar. Enforces rigorous quality standards — reject shortcuts, demand evidence, no rubber-stamping.
Use when an agent is the FSM arbitrator on a durable task. Defines the two triggers, the three ruling types, the POST contract, the addendum-file rules for contradiction rulings, and the 409 handling. Project-agnostic.
Tells container agents where the Unreal Engine source tree is mounted inside the container, so they can grep and read engine headers to verify API signatures and class hierarchies.
Use when an agent must review code changes. Defines the universal review sequence — identify files, read context, check against domain criteria, score, filter. Compose with a domain skill and review-output-schema.
| name | scaffold-system-wiring |
| description | Agent resolution table, review mandates, and terminal style sweep for the scaffold development orchestrator running inside a Docker container against the ue-claude-scaffold project. |
| axis | environment |
| Role | Agent | Purpose |
|---|---|---|
implementer | scaffold-implementer | Writes TypeScript, shell scripts, agent/skill markdown |
safety-reviewer | scaffold-safety-reviewer | SQL injection, input validation, shell injection |
reviewer | scaffold-correctness-reviewer | Logic, spec compliance, async correctness, API contracts |
decomp-reviewer | scaffold-decomposition-reviewer | File bloat, module sprawl, DRY violations |
style-sweep | scaffold-style-sweep | Terminal style pass: edit-in-place, build, test, single commit. Never touches React component discipline. |
Note: there is no per-phase style-reviewer row in this wiring. Style normalisation runs once at the end of the plan as the terminal style sweep (see Style Sweep Commands below, and the Final Stage — Style Sweep section of orchestrator-phase-protocol).
Each reviewer assesses only its own dimension. Do not ask the safety reviewer about naming — naming lives under style, which is handled by the terminal sweep, not per-phase review. The split is intentional -- smaller context windows with focused attention catch more issues than one overloaded pass.
These agents have scaffold conventions, TypeScript patterns, and enforcement baked into their definitions. Your delegation prompts should focus on what to do (the phase requirements, file lists, specification), not how to work (build commands, style rules, environment details).
The terminal style sweep (style-sweep → scaffold-style-sweep) sources its build and test commands from the environment skills it composes — see that agent's definition for the exact commands. Your delegation prompt to the sweep provides:
<branch-base>..HEAD)git diff <branch-base>..HEAD --name-only, filtered to the scaffold's source extensions (.ts, .tsx, .sh, and .md under agents/, dynamic-agents/, or skills/)Style sweep: normalize <N> files post-planDo not supply build or test commands in the delegation prompt — the sweep already loads scaffold-environment, scaffold-server-patterns, scaffold-dashboard-patterns, typescript-async-safety, and scaffold-test-format from its skill composition.