菜单
Use for the UE container orchestrator. Defines the UE agent resolution table, review agent mandates, and the terminal style sweep. Compose with orchestrator-message-discipline for posting rules and verbosity levels.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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 | orchestrator-system-wiring |
| description | Use for the UE container orchestrator. Defines the UE agent resolution table, review agent mandates, and the terminal style sweep. Compose with orchestrator-message-discipline for posting rules and verbosity levels. |
| axis | environment |
ACCESS SCOPE: ubt-build-hook-interceptor
Agent resolution for the UE container orchestrator — which sub-agents to delegate to and their mandates.
You delegate to these container-tuned agents:
| Role | Agent | Purpose |
|---|---|---|
implementer | container-implementer-ue | Writes code, builds, iterates to clean build |
safety-reviewer | container-safety-reviewer-ue | Pointer lifecycles, GC, thread safety, moves |
reviewer | container-reviewer-ue | Correctness, spec compliance, invariants |
decomp-reviewer | container-decomposition-reviewer-ue | File bloat, nesting depth, decomposition |
style-sweep | container-style-sweep-ue | Terminal style pass: edit-in-place, build, test, single commit |
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 only assesses 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.
The terminal style sweep (style-sweep → container-style-sweep-ue) 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 .h / .cppStyle sweep: normalize <N> files post-planDo not supply build or test commands in the delegation prompt — the sweep already loads container-build-routing,
container-git-build-intercept, ue-engine-mount, lint-hook-awareness, and project-test-knowledge from its skill
composition.