learn-ukrainian.github.io

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).

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.

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.

Run the canonical read-only, versioned semantic review authorized by one bounded track-completion ledger, or an explicitly diagnostic standalone review that cannot complete a module. A normal BIO completion request routes through track-completion, which owns call and repair budgets.

Inspect, rename, archive, restore, or proof-gated-clean an exact Codex task family with native app mutations, previews, reconciliation, and receipts.

Prepare, name, resume, validate, and confirm a durable fleet-wide task rollover with the shared task-identity envelope and strict continuity packet. Use when any supported agent or harness approaches context exhaustion, reports pending or resumed rollover state, must reconcile a replacement title, or must prove continuity before predecessor cleanup.

Review SEMINAR track plans (FOLK, HIST, BIO, ISTORIO, LIT, OES, RUTH) using Wikipedia + Literary RAG + VESUM. Finds factual errors, ghost sources, decolonization issues.

Fact-check BUILT seminar content (FOLK, HIST, BIO, ISTORIO, LIT and subtracks, OES, RUTH) against Wikipedia + Literary RAG + heritage dictionaries. Verifies every factual claim, catches ghost facts / ghost sources / confident fabrication, and runs decolonization + russicism checks. For built module CONTENT — not plans (use plan-review-seminar for plans, content-review for core levels).

Post-build module quality review. Checks plan adherence, linguistic accuracy, pedagogical quality, activities, vocabulary completeness, engagement.

Review CORE level plans (A1-C2, PRO) using State Standard 2024 + textbook RAG + VESUM. Finds bad vocab, wrong grammar scope, Russianisms, factual errors.

Batch prompt-review + content-review across multiple modules using parallel subagents. Writes reports to audit/ and orchestration/, then aggregates cross-module findings and proposes template auto-fixes.

Apply fixes from plan review reports. Reads audit reports, shows proposed changes for approval, then applies them. Respects plan versioning rules.

Analyze orchestration folders to find prompt/context engineering problems. Every friction report is a prompt engineering bug report.

Validate pipeline prompt templates. Finds unreplaced placeholders, contradictions between templates, stale instructions.

Atomic rebuild for BIO (Ukrainian Biographies). Narrative Engine v5.0 (Slim Skill + Rich Phase Prompts).

Atomic rebuild for Core A (A1, A2, B1 M01-05). Narrative Engine v5.0 (Slim Skill + Rich Phase Prompts).

Atomic rebuild for Core B (B1 M06+, B2, C1, C2, PRO). Narrative Engine v5.0 (Slim Skill + Rich Phase Prompts).

Atomic rebuild for HIST (Ukrainian History). Narrative Engine v5.0 (Slim Skill + Rich Phase Prompts).

Atomic rebuild for ISTORIO (Ukrainian Historiography). Narrative Engine v5.0 (Slim Skill + Rich Phase Prompts).

Atomic rebuild for LIT track (all literary genres). Narrative Engine v5.0 (Slim Skill + Rich Phase Prompts). Supports genre parameter.

Atomic rebuild for OES (Old East Slavic Era, X-XIII century). Narrative Engine v5.0 (Slim Skill + Rich Phase Prompts).

Atomic rebuild for RUTH (Ruthenian / Middle Ukrainian, XIV-XVIII century). Narrative Engine v5.0 (Slim Skill + Rich Phase Prompts).

Tier 3 structural rebuild for BIO. Targets 5000+ words, academic decolonization, and biographical agency analysis. Triggers on "/full-rebuild bio N-M".

Tier 3 structural rebuild for ISTORIO. Focuses on historiographical mapping and source criticism (4000+ words). Triggers on "/full-rebuild istorio N-M".

Tier 3 structural rebuild for LIT track. Aesthetic analysis, intertextuality, and canon reclamation (4500+ words). Triggers on "/full-rebuild lit N-M".

Tier 3 structural rebuild for OES. Targets 4000+ words, historical linguistics (Yer falling, Pleophony), and manuscript analysis. Triggers on "/full-rebuild oes N-M".

Tier 3 structural rebuild for RUTH. Focuses on Baroque stylistics (Chancery vs. Polemic) and 4000+ word expansion. Triggers on "/full-rebuild ruth N-M".

Adversarial final review for otaman-built modules. Runs in a NEW session (separate from builder/reviewer) to maintain independence. Catches what automated audit and Green Team missed.

Activity enrichment + review. Wrapper around build_module_v5.py --restart-from activities.

Content sprint — prose only. Wrapper around build_module_v5.py --restart-from content.