메뉴
How to monitor V7 curriculum builds — the Monitor tool command template, mandatory --worktree isolation, the JSONL event fields v7_build.py/linear_pipeline.py emit, and the Monitor API for state queries without running a build. Use whenever launching or watching a `scripts/build/v7_build.py` run.
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
Run or resume the manifest-derived curriculum lifecycle for one active track. Use when an operator asks to process a track in manifest order, select built, unbuilt, stale, or one-module scope, or resume an exact coordinator run. Route every acquired module through curriculum-preparation or track-completion; do not use for an uncoordinated standalone module.
Prepare, audit, or resume missing or stale prerequisite evidence for one manifest target, one track missing-only scan, or one bounded homogeneous packet by using the canonical curriculum readiness evaluator. Use for preparation-scoped work before a learner-module build or when curriculum-lifecycle explicitly delegates preparation. Do not use to build learner modules, coordinate a track, run post-build review, certify, publish, or deploy.
Complete one active Ukrainian curriculum module through a canonical CORE-or-seminar workflow. Use for built modules that need the versioned post-build gate, unbuilt modules that need plan review and V7 construction before that gate, interrupted module completion runs that must resume from a durable ledger, or non-PASS modules that need root-cause repair, fresh review, independent cross-family review, and publication.
Model-agnostic orchestrator playbook for driving ONE epic/track lane end-to-end over the fleet-comms message plane. Invoke this when you are launched as an epic/track driver (Grok, Sonnet-5, Gemini/AGY, Kimi, or Claude) via a start-<model>.sh --epic launch and told to "drive this epic". Teaches the METHOD — topology → route → dispatch → settle → cross-family review → merge → handoff — and defers all live roster/routing DATA to /api/rules and model_catalog.yaml. Not for main-orchestrator cold-start (that has its own hook) and not for writing a single module (use $track-completion).
Audit prompt sizes across build orchestration dirs. Surfaces sections that dominate the prompt (>40%), tracks per-phase budget vs the model's context window, and checks whether directives in the prompt were actually covered in the response.
Canonical code/infra closeout workflow — freezes scope, resolves the exact review target (local/commit/branch/PR), runs a non-mutating review, resolves a cross-family reviewer, and requires separate behavior proof for user-visible code or infrastructure changes. Never use as a learner-content semantic gate.
| name | build-monitoring |
| description | How to monitor V7 curriculum builds — the Monitor tool command template, mandatory --worktree isolation, the JSONL event fields v7_build.py/linear_pipeline.py emit, and the Monitor API for state queries without running a build. Use whenever launching or watching a `scripts/build/v7_build.py` run. |
NEVER poll builds with ScheduleWakeup or manual loops. Use the Monitor tool:
Agents may run V7 builds during autonomous orchestration — always pass --worktree (PR #1952) so the build runs in .worktrees/builds/{level}-{slug}-{stamp}/ and main stays clean.
Monitor(
command=".venv/bin/python -u scripts/build/v7_build.py {level} {slug} 2>&1 | grep --line-buffered '^{\"event\"'",
description="V7 build events for {level}/{slug}",
persistent=True,
timeout_ms=3600000
)
v7_build.py emits JSONL events from the wrapper and linear_pipeline.py: single-module lifecycle notifications such as phase_done, review_score, and module_done; writer/reviewer telemetry such as writer_cot_emit, writer_tool_call, writer_end_gate, writer_tool_theatre, phase_writer_summary, mcp_config_resolved, reviewer_dim_evidence, reviewer_audit_call, and phase_review_summary; and correction diagnostics writer_correction_unparseable, reviewer_fixes_unparseable, reviewer_fixes_anchor_unmatched. Each line becomes a notification — zero polling overhead.
For state queries without running builds, use the Monitor API (docs/MONITOR-API.md):
/api/state/track-health/a1/api/state/failing?track=a2/api/state/build-status/a1