oh-my-opencode 4.19.0 → 4.19.2

package/packages/omo-codex/plugin/components/lsp/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-lsp",
-	"version": "4.19.0",
+	"version": "4.19.2",
 	"description": "Codex plugin that exposes Language Server Protocol tools and post-edit diagnostics.",
 	"type": "module",
 	"packageManager": "npm@11.12.1",

package/packages/omo-codex/plugin/components/rules/dist/cli.js

@@ -3854,6 +3854,17 @@ var POST_COMPACT_MIN_RESERVED_TOKENS = 8000;
 var POST_COMPACT_MIN_GUIDE_CHARS = 500;
 var FALLBACK_CONTEXT_WINDOW_TOKENS = 200000;
 var MODEL_CONTEXT_BUDGETS = [
+  { slug: "gpt-5.6-sol", contextWindowTokens: 372000, effectivePercent: DEFAULT_EFFECTIVE_CONTEXT_WINDOW_PERCENT },
+  {
+    slug: "gpt-5.6-terra",
+    contextWindowTokens: 372000,
+    effectivePercent: DEFAULT_EFFECTIVE_CONTEXT_WINDOW_PERCENT
+  },
+  {
+    slug: "gpt-5.6-luna",
+    contextWindowTokens: 372000,
+    effectivePercent: DEFAULT_EFFECTIVE_CONTEXT_WINDOW_PERCENT
+  },
   { slug: "gpt-5.5", contextWindowTokens: 272000, effectivePercent: DEFAULT_EFFECTIVE_CONTEXT_WINDOW_PERCENT },
   { slug: "gpt-5.4-mini", contextWindowTokens: 272000, effectivePercent: DEFAULT_EFFECTIVE_CONTEXT_WINDOW_PERCENT },
   {

package/packages/omo-codex/plugin/components/rules/hooks/hooks.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook session-start",
 						"timeout": 10,
-						"statusMessage": "(OmO 4.19.0) Loading Project Rules"
+						"statusMessage": "(OmO 4.19.2) Loading Project Rules"
 					}
 				]
 			}
@@ -19,7 +19,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook user-prompt-submit",
 						"timeout": 10,
-						"statusMessage": "(OmO 4.19.0) Loading Project Rules"
+						"statusMessage": "(OmO 4.19.2) Loading Project Rules"
 					}
 				]
 			}
@@ -32,7 +32,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook post-tool-use",
 						"timeout": 10,
-						"statusMessage": "(OmO 4.19.0) Matching Project Rules"
+						"statusMessage": "(OmO 4.19.2) Matching Project Rules"
 					}
 				]
 			}
@@ -45,7 +45,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook post-compact",
 						"timeout": 10,
-						"statusMessage": "(OmO 4.19.0) Resetting Project Rule Cache"
+						"statusMessage": "(OmO 4.19.2) Resetting Project Rule Cache"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/rules/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-rules",
-	"version": "4.19.0",
+	"version": "4.19.2",
 	"description": "Codex plugin that injects project rule files into model context through lifecycle hooks.",
 	"type": "module",
 	"packageManager": "npm@11.12.1",

package/packages/omo-codex/plugin/components/rules/src/post-compact-budget.ts

@@ -21,6 +21,17 @@ const POST_COMPACT_MIN_RESERVED_TOKENS = 8_000;
 const POST_COMPACT_MIN_GUIDE_CHARS = 500;
 const FALLBACK_CONTEXT_WINDOW_TOKENS = 200_000;
 const MODEL_CONTEXT_BUDGETS: readonly ModelContextBudget[] = [
+	{ slug: "gpt-5.6-sol", contextWindowTokens: 372_000, effectivePercent: DEFAULT_EFFECTIVE_CONTEXT_WINDOW_PERCENT },
+	{
+		slug: "gpt-5.6-terra",
+		contextWindowTokens: 372_000,
+		effectivePercent: DEFAULT_EFFECTIVE_CONTEXT_WINDOW_PERCENT,
+	},
+	{
+		slug: "gpt-5.6-luna",
+		contextWindowTokens: 372_000,
+		effectivePercent: DEFAULT_EFFECTIVE_CONTEXT_WINDOW_PERCENT,
+	},
 	{ slug: "gpt-5.5", contextWindowTokens: 272_000, effectivePercent: DEFAULT_EFFECTIVE_CONTEXT_WINDOW_PERCENT },
 	{ slug: "gpt-5.4-mini", contextWindowTokens: 272_000, effectivePercent: DEFAULT_EFFECTIVE_CONTEXT_WINDOW_PERCENT },
 	{

package/packages/omo-codex/plugin/components/rules/test/post-compact-budget.test.ts

@@ -76,6 +76,66 @@ describe("post-compact context budget", () => {
 		expect(budget.maxRuleChars).toBeLessThanOrEqual(budget.maxResultChars);
 	});
 
+	it("#given gpt-5.6-sol within its 372k window #when resolving post-compact budget #then keeps configured post-compact cap", () => {
+		// given
+		const transcriptPath = writeCompactedTranscript("A".repeat(541_500));
+
+		// when
+		const budget = withPostCompactBudget(CONFIG, { model: "gpt-5.6-sol", transcriptPath });
+
+		// then
+		expect(budget.maxRuleChars).toBe(CONFIG.postCompactMaxRuleChars);
+		expect(budget.maxResultChars).toBe(CONFIG.postCompactMaxResultChars);
+	});
+
+	it("#given gpt-5.6-terra within its 372k window #when resolving post-compact budget #then keeps configured post-compact cap", () => {
+		// given
+		const transcriptPath = writeCompactedTranscript("A".repeat(541_500));
+
+		// when
+		const budget = withPostCompactBudget(CONFIG, { model: "gpt-5.6-terra", transcriptPath });
+
+		// then
+		expect(budget.maxRuleChars).toBe(CONFIG.postCompactMaxRuleChars);
+		expect(budget.maxResultChars).toBe(CONFIG.postCompactMaxResultChars);
+	});
+
+	it("#given gpt-5.6-luna within its 372k window #when resolving post-compact budget #then keeps configured post-compact cap", () => {
+		// given
+		const transcriptPath = writeCompactedTranscript("A".repeat(541_500));
+
+		// when
+		const budget = withPostCompactBudget(CONFIG, { model: "gpt-5.6-luna", transcriptPath });
+
+		// then
+		expect(budget.maxRuleChars).toBe(CONFIG.postCompactMaxRuleChars);
+		expect(budget.maxResultChars).toBe(CONFIG.postCompactMaxResultChars);
+	});
+
+	it("#given provider-prefixed gpt-5.6 variant within its 372k window #when resolving post-compact budget #then keeps configured post-compact cap", () => {
+		// given
+		const transcriptPath = writeCompactedTranscript("A".repeat(541_500));
+
+		// when
+		const budget = withPostCompactBudget(CONFIG, { model: "openai/gpt-5.6-sol", transcriptPath });
+
+		// then
+		expect(budget.maxRuleChars).toBe(CONFIG.postCompactMaxRuleChars);
+		expect(budget.maxResultChars).toBe(CONFIG.postCompactMaxResultChars);
+	});
+
+	it("#given unknown model with the same transcript #when resolving post-compact budget #then keeps the 200k fallback floor", () => {
+		// given
+		const transcriptPath = writeCompactedTranscript("A".repeat(541_500));
+
+		// when
+		const budget = withPostCompactBudget(CONFIG, { model: "unknown-model", transcriptPath });
+
+		// then
+		expect(budget.maxResultChars).toBe(500);
+		expect(budget.maxRuleChars).toBe(500);
+	});
+
 	it("#given context pressure marker after compaction #when resolving post-compact budget #then shrinks projected rule injection", () => {
 		// given
 		const transcriptPath = writeCompactedPressureTranscript("small compacted summary");

package/packages/omo-codex/plugin/components/start-work-continuation/directive.md

@@ -40,7 +40,7 @@ You are mid-flight on a Prometheus work plan; this turn is an automatic continua
 
 # Final gate
 
-Before completion, satisfy all five `review-work` lanes and a `debugging` runtime audit; inconclusive lanes or an inconclusive audit fail. Each pass binds to the exact full commit SHA it reviewed. Immediately append a durable task-evidence record to `{{LEDGER_PATH}}` for every passing lane and the debugging audit with its name, full SHA, verdict, and report artifact/source. Before same-SHA reuse after any continuation or compaction, re-read the ledger record and verify the exact lane/SHA pair; memory, chat history, or an unstamped report is not coverage. New commits require fresh applicable coverage. Do not create a PR, PR handoff, branch handoff, merge, or final completion answer until this gate passes. For PR/branch work, stay in the task-owned worktree: create/update the PR, wait for CI/review/Cubic gates, merge by default unless explicitly opted out, then clean up. After the gate and lifecycle pass, mark the Boulder work completed before the final answer. Redact secrets, tokens, credentials, auth headers, cookies, env dumps, logs, and PII.
+Before completion, satisfy all five `review-work` lanes and a `debugging` runtime audit; inconclusive lanes or an inconclusive audit fail. Each pass binds to the exact full commit SHA it reviewed. Immediately append a durable task-evidence record to `{{LEDGER_PATH}}` for every passing lane and the debugging audit with its name, full SHA, verdict, and report artifact/source. Before same-SHA reuse after any continuation or compaction, re-read the ledger record and verify the exact lane/SHA pair; memory, chat history, or an unstamped report is not coverage. New commits require fresh applicable coverage. Do not create a PR, PR handoff, branch handoff, merge, or final completion answer until this gate passes. For PR/branch work, stay in the task-owned worktree: create/update the PR, wait for CI/review/Cubic gates, merge by default unless explicitly opted out, then clean up. After the gate and lifecycle pass, mark the Boulder work completed before the final answer. Redact secrets, tokens, credentials, auth headers, cookies, env dumps, logs, and PII. Honor the delivery mode recorded in the goal/ledger at session start: `--make-pr` hands off with the PR URL after the PR opens (merge only on explicit user ask); `--ship` keeps working until the PR is MERGED - CI and review gates fixed and addressed - then removes the worktree and syncs `.omo/` state back.
 
 # Stop conditions for THIS turn
 

package/packages/omo-codex/plugin/components/start-work-continuation/hooks/hooks.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/components/start-work-continuation/dist/cli.js\" hook stop",
 						"timeout": 10,
-						"statusMessage": "(OmO 4.19.0) Checking Start-Work Continuation"
+						"statusMessage": "(OmO 4.19.2) Checking Start-Work Continuation"
 					}
 				]
 			}
@@ -19,7 +19,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/components/start-work-continuation/dist/cli.js\" hook subagent-stop",
 						"timeout": 10,
-						"statusMessage": "(OmO 4.19.0) Checking Start-Work Continuation"
+						"statusMessage": "(OmO 4.19.2) Checking Start-Work Continuation"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/start-work-continuation/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-start-work-continuation",
-	"version": "4.19.0",
+	"version": "4.19.2",
 	"description": "Codex Stop hook continuation injector for omo-codex start-work plans.",
 	"type": "module",
 	"packageManager": "npm@11.12.1",

package/packages/omo-codex/plugin/components/teammode/hooks/hooks.json

@@ -8,7 +8,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook post-tool-use",
 						"timeout": 10,
-						"statusMessage": "(OmO 4.19.0) Checking Thread Title Hygiene"
+						"statusMessage": "(OmO 4.19.2) Checking Thread Title Hygiene"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/teammode/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@sisyphuslabs/codex-teammode",
-	"version": "4.19.0",
+	"version": "4.19.2",
 	"description": "Codex team-mode hook component that keeps background thread titles descriptive after create_thread.",
 	"type": "module",
 	"private": true,

package/packages/omo-codex/plugin/components/telemetry/hooks/hooks.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook session-start",
 						"timeout": 5,
-						"statusMessage": "(OmO 4.19.0) Recording Session Telemetry"
+						"statusMessage": "(OmO 4.19.2) Recording Session Telemetry"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/telemetry/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-telemetry",
-	"version": "4.19.0",
+	"version": "4.19.2",
 	"description": "Codex plugin component that emits omo-codex anonymous daily-active telemetry on SessionStart.",
 	"type": "module",
 	"packageManager": "npm@11.12.1",

package/packages/omo-codex/plugin/components/ultrawork/agents/lazycodex-clone-fidelity-reviewer.toml

@@ -1,8 +1,8 @@
 name = "lazycodex-clone-fidelity-reviewer"
 description = "Read-only LazyCodex clone / design-system fidelity reviewer. Verifies clone and design-port work is a rigorous, token-driven design system, not a pasted screenshot or hardcoded fake."
 nickname_candidates = ["Clone Fidelity Reviewer"]
-model = "gpt-5.6-sol"
-model_reasoning_effort = "xhigh"
+model = "gpt-5.6-terra"
+model_reasoning_effort = "high"
 
 developer_instructions = """
 Role: clone / design-system fidelity reviewer. Read-only.

package/packages/omo-codex/plugin/components/ultrawork/agents/lazycodex-code-reviewer.toml

@@ -1,8 +1,8 @@
 name = "lazycodex-code-reviewer"
 description = "Read-only LazyCodex code-quality reviewer. Audits diffs, tests, and risk with strict artifact-backed findings."
 nickname_candidates = ["Code Reviewer"]
-model = "gpt-5.6-sol"
-model_reasoning_effort = "xhigh"
+model = "gpt-5.6-terra"
+model_reasoning_effort = "medium"
 
 developer_instructions = """
 Role: code quality reviewer. Read-only.

package/packages/omo-codex/plugin/components/ultrawork/agents/lazycodex-gate-reviewer.toml

@@ -2,7 +2,7 @@ name = "lazycodex-gate-reviewer"
 description = "Read-only LazyCodex gate reviewer. Re-audits executor, code review, and QA artifacts before final approval."
 nickname_candidates = ["Gate Reviewer"]
 model = "gpt-5.6-sol"
-model_reasoning_effort = "high"
+model_reasoning_effort = "low"
 
 developer_instructions = """
 Role: final gate reviewer. Read-only.

package/packages/omo-codex/plugin/components/ultrawork/agents/lazycodex-worker-high.toml

@@ -2,7 +2,7 @@ name = "lazycodex-worker-high"
 description = "LazyCodex high-difficulty implementation worker, sized for LARGE changes: a new module or abstraction, a cross-module refactor, concurrency/security/migration work, or any real, complex, big problem that has ONE clear goal. Owns the smallest correct change and records evidence before claiming completion."
 nickname_candidates = ["High Worker"]
 model = "gpt-5.6-sol"
-model_reasoning_effort = "max"
+model_reasoning_effort = "medium"
 
 developer_instructions = """
 Role: implementation executor. You own the task end to end.

package/packages/omo-codex/plugin/components/ultrawork/agents/lazycodex-worker-medium.toml

@@ -1,8 +1,8 @@
 name = "lazycodex-worker-medium"
 description = "LazyCodex medium-difficulty implementation worker, sized for MID-SIZED changes: a standard feature inside existing layers, touching a few files along established patterns. Owns the smallest correct change and records evidence before claiming completion."
 nickname_candidates = ["Medium Worker"]
-model = "gpt-5.6-luna"
-model_reasoning_effort = "max"
+model = "gpt-5.6-terra"
+model_reasoning_effort = "high"
 
 developer_instructions = """
 Role: implementation executor. You own the task end to end.

package/packages/omo-codex/plugin/components/ultrawork/agents/plan.toml

@@ -2,7 +2,7 @@ name = "plan"
 description = "Strategic planning consultant for work with unresolved design uncertainty after discovery. Produces one executable plan; never implements. Writes the plan to .omo/plans/<slug>.md."
 nickname_candidates = ["Planner"]
 model = "gpt-5.6-sol"
-model_reasoning_effort = "max"
+model_reasoning_effort = "high"
 
 developer_instructions = """
 Role: strategic planning consultant. You produce a single, bulletproof, executable work plan only when discovery leaves unresolved design uncertainty.

package/packages/omo-codex/plugin/components/ultrawork/directive.md

@@ -404,13 +404,18 @@ Procedure (NON-NEGOTIABLE):
    2-attempt stop rule below) — do not loop further.
 
 # Commits
-Atomic, Conventional Commits (`<type>(<scope>): <imperative>` — feat /
-fix / refactor / test / docs / chore / build / ci / perf). One logical
-change per commit; each commit builds + tests green on its own. No WIP
-on the final branch. If a plan file exists, final commit footer:
-`Plan: .omo/plans/<slug>.md`. Do NOT auto-`git commit` unless the user
-requested or preauthorised this session — default is stage + draft
-message + present for approval.
+Commit frequently: one atomic commit per verified increment (RED→GREEN
++ its evidence), never one end-of-run omnibus; each commit builds +
+tests green on its own; no WIP on the final branch.
+BEFORE composing each message, read the history and mimic it: run
+`git log --oneline -20` plus `git log -5 -- <touched paths>` and match
+the observed convention — subject shape, scope names, message language,
+body style, and typical commit size. Default to Conventional Commits
+(`<type>(<scope>): <imperative>` — feat / fix / refactor / test / docs /
+chore / build / ci / perf) only where history shows no stronger local
+convention. If a plan file exists, final commit footer:
+`Plan: .omo/plans/<slug>.md`. Skip committing only when the user forbade
+commits this session — then stage + draft the message instead.
 
 # Constraints
 - Every behavior change needs a failing-first proof captured BEFORE

package/packages/omo-codex/plugin/components/ultrawork/dist/cli.js

@@ -60,7 +60,7 @@ function buildUltraworkAdditionalContext(options = {}) {
 }
 
 // components/ultrawork/src/codex-hook.ts
-var ULTRAWORK_CURRENT_PROMPT_PATTERN = /(?:ultrawork|ulw)/i;
+var ULTRAWORK_CURRENT_PROMPT_PATTERN = /(?:ultrawork|ulw(?!-(?:plan|research)))/i;
 var ULTRAWORK_DIRECTIVE_MARKER = "<ultrawork-mode>";
 var TRANSCRIPT_SEARCH_BYTES = 512000;
 var CONTEXT_PRESSURE_MARKERS = [

package/packages/omo-codex/plugin/components/ultrawork/hooks/hooks.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook user-prompt-submit",
 						"timeout": 5,
-						"statusMessage": "(OmO 4.19.0) Checking Ultrawork Trigger"
+						"statusMessage": "(OmO 4.19.2) Checking Ultrawork Trigger"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/ultrawork/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-ultrawork",
-	"version": "4.19.0",
+	"version": "4.19.2",
 	"description": "Codex plugin that injects the ultrawork orchestration directive and ships LazyCodex planning, review, QA, and gate agent roles.",
 	"type": "module",
 	"packageManager": "npm@11.12.1",

package/packages/omo-codex/plugin/components/ultrawork/skills/ultrawork/SKILL.md

@@ -411,13 +411,18 @@ Procedure (NON-NEGOTIABLE):
    2-attempt stop rule below) — do not loop further.
 
 # Commits
-Atomic, Conventional Commits (`<type>(<scope>): <imperative>` — feat /
-fix / refactor / test / docs / chore / build / ci / perf). One logical
-change per commit; each commit builds + tests green on its own. No WIP
-on the final branch. If a plan file exists, final commit footer:
-`Plan: .omo/plans/<slug>.md`. Do NOT auto-`git commit` unless the user
-requested or preauthorised this session — default is stage + draft
-message + present for approval.
+Commit frequently: one atomic commit per verified increment (RED→GREEN
++ its evidence), never one end-of-run omnibus; each commit builds +
+tests green on its own; no WIP on the final branch.
+BEFORE composing each message, read the history and mimic it: run
+`git log --oneline -20` plus `git log -5 -- <touched paths>` and match
+the observed convention — subject shape, scope names, message language,
+body style, and typical commit size. Default to Conventional Commits
+(`<type>(<scope>): <imperative>` — feat / fix / refactor / test / docs /
+chore / build / ci / perf) only where history shows no stronger local
+convention. If a plan file exists, final commit footer:
+`Plan: .omo/plans/<slug>.md`. Skip committing only when the user forbade
+commits this session — then stage + draft the message instead.
 
 # Constraints
 - Every behavior change needs a failing-first proof captured BEFORE

package/packages/omo-codex/plugin/components/ultrawork/skills/ulw-plan/SKILL.md

@@ -13,11 +13,30 @@ You are **Prometheus**, a planning consultant. You turn a vague or large request
 
 Outcome-first: explore a lot, ask few sharp questions - or none, when the intent is fuzzy (see routing) - and stop the moment the plan is done.
 
+## MANDATORY OPENING ANNOUNCEMENT
+
+The FIRST user-visible line of the turn that activates this skill MUST be exactly:
+
+`ULW-PLAN MODE ENABLED!`
+
+If another active mode mandates its own first line (ultrawork does), print that line first and this marker on the next line - both contracts stay satisfied.
+
+Directly under the marker, before any exploration, state the working contract once, in your own words, carrying ALL of these commitments:
+
+1. **Persona + no-implementation pledge** - from now on you work as Prometheus, a planning consultant, and you will never start implementation - no product-code edits, no implementer subagents - until the user explicitly says okay; even then, approval authorizes writing the plan only, and execution starts in a separate worker session (e.g. `$start-work`).
+2. **Workflow preview** - the order of what happens next: parallel read-only exploration (plus outside research when the repo cannot answer) until the open unknowns are resolved; the intent verdict from INTENT ROUTING, announced; questions to the user ONLY when a genuine owner-decision survives exploration - or when exploration and research both come back empty on a fork the plan cannot proceed without; then the approval brief, and the plan is written only after the explicit okay.
+
+Example opening (adapt the wording, keep every commitment):
+
+> ULW-PLAN MODE ENABLED!
+> From now on I am working as Prometheus, a planning consultant. I will not start any implementation until you explicitly say okay - and approval authorizes writing the plan only; execution starts separately (e.g. `$start-work`).
+> Next, in order: (1) parallel read-only exploration and research, (2) intent verdict announced (CLEAR or UNCLEAR, plus whether high-accuracy review is required), (3) questions only for the forks exploration cannot settle - or where research finds nothing on a blocking decision, (4) approval brief, then (5) the plan is written after your okay.
+
 ## INTENT ROUTING - pick ONE intent reference
 
 **Review modifiers are a gate trigger, not a style cue.** If the user says "high accuracy", "ultra high accuracy", "고정밀", "deep review", or equivalent - in ANY turn, even appended to a follow-up question and even after the plan already exists - set `review_required: true` in the draft: the dual high-accuracy review (native `momus` + the independent Codex CLI review) is now REQUIRED before handoff, and if the plan already exists you run it this same turn. Answering the current question more carefully does NOT satisfy it. This does NOT choose CLEAR/UNCLEAR and does NOT suppress interview.
 
-After grounding, make ONE judgment, record `intent: clear|unclear` plus `review_required`, **ANNOUNCE both to the user in one line**, then load ONE intent reference (you ALSO read `references/full-workflow.md` for the shared mechanics - see below). The test keys on whether the desired **OUTCOME** is clear, NOT on request length. The announcement is the user's first signal of whether they will be interviewed and whether high-accuracy review is already requested - never skip it.
+After grounding, make ONE judgment, record `intent: clear|unclear` plus `review_required`, **ANNOUNCE both to the user in one line**, then load ONE intent reference (you ALSO read `references/full-workflow.md` for the shared mechanics - see below). The test keys on whether the desired **OUTCOME** is clear, NOT on request length. This verdict line and the opening announcement above are the two mandatory user-visible signals of a planning session - it tells the user whether they will be interviewed and whether high-accuracy review is already requested; never skip either.
 
 > "Intent: **CLEAR**, review required - you specified the endpoint and asked for high accuracy. I will ask only the genuine forks, then run the high-accuracy review after approval."
 > "Intent: **UNCLEAR**, review required - 'make auth better' is open-ended and you asked for high accuracy. I will choose best-practice defaults, then run the high-accuracy review automatically."
@@ -89,5 +108,5 @@ Roles: `explorer` (internal patterns/conventions/tests), `librarian` (external d
 
 ## Stop rules
 
-- Plan file exists, template filled, every todo has references + acceptance + QA + commit, dependency matrix consistent, and any required high-accuracy receipts are recorded: present the summary, then (CLEAR without `review_required`) ask the start-or-high-accuracy question, or (CLEAR with `review_required` / UNCLEAR) report the review result - and stop. **Never begin execution yourself.**
+- Plan file exists, template filled, every todo has references + acceptance + QA + commit, dependency matrix consistent, and any required high-accuracy receipts are recorded: present the handoff explanation (Phase 4 delivery format in `references/full-workflow.md`), then (CLEAR without `review_required`) ask the start-or-high-accuracy question, or (CLEAR with `review_required` / UNCLEAR) report the review result - and stop. **Never begin execution yourself.**
 - Brief presented and `status: awaiting-approval` recorded: wait. Do not re-explore unless the user changes scope.

package/packages/omo-codex/plugin/components/ultrawork/skills/ulw-plan/references/full-workflow.md

@@ -168,6 +168,17 @@ Runs in parallel; ALL must APPROVE; surface results and wait for the user's expl
 - CLEAR with `review_required: true`: run the high-accuracy review before delivery, record receipts, then present the plan summary and review result. Do not ask whether to run the review; the user already asked.
 - UNCLEAR: run the high-accuracy review AUTOMATICALLY before presenting (unless Classify=Trivial), then present a brief that LEADS with the derived approach and the adopted defaults; still wait for the user's explicit okay.
 
+### Handoff explanation (the mandatory shape of every plan summary)
+
+Every "present the plan summary/brief" above delivers THIS structure, in the user's language, derived from the finished plan file (COUNT the rows - never estimate):
+
+1. **What this plan drives** - the work it performs, in 1-2 sentences.
+2. **End state** - the concrete things that will exist or behave differently once execution finishes.
+3. **Shape** - how many phases/waves and how many tasks: N implementation todos (`- [ ] N.` rows) + F final-verification tasks (`- [ ] F<n>.` rows).
+4. **Added beyond the request** - what exploration surfaced and you folded in that the user never explicitly asked for (edge cases, migrations, tests, rollback, docs), each with a one-line reason; say "none" if nothing was added.
+5. **Verification** - how completion will be proven: the final verification wave plus the key QA scenarios/commands.
+6. **Execution handoff** - the plan runs in a worker session via `$start-work <plan-name>`; introduce the options: `--worktree <absolute-path>` (task-owned worktree; required for PR/branch work), `--make-pr` (deliver as a PR; auto-creates a task-owned worktree), `--ship` (implies `--make-pr`, keeps working until the PR is reviewed and MERGED).
+
 ### High-accuracy review (dual review)
 The high-accuracy review is DUAL and both passes must return OKAY before handoff: (1) the native `momus` reviewer subagent, and (2) an independent Codex CLI review on gpt-5.6-sol at xhigh reasoning, run in a disposable isolated workspace and `CODEX_HOME` with the harness's normal approval and sandbox policy. Do not add flags that disable approvals or sandboxing. Momus runs at High and may take substantially longer than other agents. One round = exactly ONE `momus` + ONE independent review, dispatched together against the COMPLETE plan file (todos + TL;DR filled) at the draft's exact recorded `plan_path`. Keep Momus in flight and wait for its terminal result: elapsed time alone never justifies cancelling, duplicating, replacing, or treating it as failed. After both verdicts return, fix every cited issue and resubmit both fresh until each approves. CLEAR: runs when the user opts in or `review_required: true`. UNCLEAR: runs automatically unless Classify=Trivial.
 
@@ -212,6 +223,6 @@ If your tool list has a flat `spawn_agent` with a required `task_name` instead o
 Roles: `explorer`, `librarian`, `metis`, `momus`. Spawn long plan/reviewer agents in the background; between waits, back off — double the timeout up to ~5 minutes — instead of spinning short cycles. Require the child to send `WORKING: <task> - <phase>` before long passes and `BLOCKED: <reason>` only when progress stops. A wait timeout only means no new mailbox update arrived; treat a running child as alive. Fall back only when the child completed without the deliverable, is ack-only after followup, explicitly `BLOCKED:`, or no longer running; then respawn a smaller `fork_context: false` job. Close each agent after integrating its result.
 
 ## Stop rules
-- Plan file exists, template filled, every todo has references + acceptance + QA + commit, dependency matrix consistent, and any required high-accuracy receipts recorded: present the summary, then (CLEAR without `review_required`) ask the start-or-high-accuracy question, or (CLEAR with `review_required` / UNCLEAR) report the review result - and stop. Execution belongs to the worker, never to you.
+- Plan file exists, template filled, every todo has references + acceptance + QA + commit, dependency matrix consistent, and any required high-accuracy receipts recorded: present the handoff explanation (Phase 4 format), then (CLEAR without `review_required`) ask the start-or-high-accuracy question, or (CLEAR with `review_required` / UNCLEAR) report the review result - and stop. Execution belongs to the worker, never to you.
 - Brief presented and `status: awaiting-approval` recorded: wait. Do not re-explore unless the user changes scope.
 - Two research waves with no new useful facts: stop exploring, present the brief.

package/packages/omo-codex/plugin/components/ultrawork/skills/ulw-plan/references/intent-clear.md

@@ -30,7 +30,7 @@ CLEARANCE CHECK after each turn: objective defined? scope IN/OUT explicit? appro
 </interview>
 
 <approval_and_deliver>
-Run the durable approval gate (mechanics in `full-workflow.md`): present the brief once with findings (paths), the approach, and EVERY surviving owner-decision as an explicit question with your recommended option (a skipped one resolves to that default); then wait for the user's explicit okay. If "start now, or review first?" would be your ONLY question, you have defaulted forks you should have surfaced - list them first. After approval: scaffold the files, run mandatory Metis, APPEND the todos, fill the human TL;DR last. Then either run the dual high-accuracy review if `review_required: true`, or present the summary and ask ONE question - start work now, or run the dual high-accuracy review first? Never pick for the user when review was not requested; never begin execution.
+Run the durable approval gate (mechanics in `full-workflow.md`): present the brief once with findings (paths), the approach, and EVERY surviving owner-decision as an explicit question with your recommended option (a skipped one resolves to that default); then wait for the user's explicit okay. If "start now, or review first?" would be your ONLY question, you have defaulted forks you should have surfaced - list them first. After approval: scaffold the files, run mandatory Metis, APPEND the todos, fill the human TL;DR last. Then either run the dual high-accuracy review if `review_required: true`, or present the handoff explanation (full-workflow.md Phase 4 format) and ask ONE question - start work now, or run the dual high-accuracy review first? Never pick for the user when review was not requested; never begin execution.
 </approval_and_deliver>
 
 <worked_example>

package/packages/omo-codex/plugin/components/ultrawork/src/codex-hook.ts

@@ -2,7 +2,7 @@ import { readFileSync } from "node:fs";
 
 import { buildUltraworkAdditionalContext, type UltraworkAdditionalContextOptions } from "./skill-pointer.js";
 
-const ULTRAWORK_CURRENT_PROMPT_PATTERN = /(?:ultrawork|ulw)/i;
+const ULTRAWORK_CURRENT_PROMPT_PATTERN = /(?:ultrawork|ulw(?!-(?:plan|research)))/i;
 const ULTRAWORK_DIRECTIVE_MARKER = "<ultrawork-mode>";
 const TRANSCRIPT_SEARCH_BYTES = 512_000;
 const CONTEXT_PRESSURE_MARKERS = [

package/packages/omo-codex/plugin/components/ultrawork/test/codex-hook-trigger-policy.test.ts

@@ -88,6 +88,48 @@ describe("codex ultrawork trigger policy", () => {
 		expect(isUltraworkPrompt(prompt)).toBe(true);
 	});
 
+	it("#given prompt invokes ulw-plan or ulw-research skills #when hook runs #then does not emit directive", () => {
+		// given
+		const prompts = [
+			"$omo:ulw-plan refactor the auth module",
+			"omo:ulw-plan",
+			"/ulw-plan",
+			"ulw-plan",
+			"$omo:ulw-research how does the hook pipeline work",
+			"ulw-research",
+			"please run ULW-PLAN for this",
+		] as const;
+
+		// when
+		const outputs = prompts.map((prompt) => runUserPromptSubmitHook({ hook_event_name: "UserPromptSubmit", prompt }));
+
+		// then
+		expect(outputs).toEqual(["", "", "", "", "", "", ""]);
+		expect(prompts.map((prompt) => isUltraworkPrompt(prompt))).toEqual([false, false, false, false, false, false, false]);
+	});
+
+	it("#given prompt contains ultrawork or standalone ulw #when hook runs #then emits directive", () => {
+		// given
+		const prompts = [
+			"ultrawork this change",
+			"ulw",
+			"ulw ",
+			"ulw fix this failing test",
+			"ulw-loop keep iterating until green",
+		] as const;
+
+		// when
+		const outputs = prompts.map((prompt) => runUserPromptSubmitHook({ hook_event_name: "UserPromptSubmit", prompt }));
+
+		// then
+		for (const output of outputs) {
+			const parsed = parseHookOutput(output);
+			expect(parsed.hookSpecificOutput.hookEventName).toBe("UserPromptSubmit");
+			expect(parsed.hookSpecificOutput.additionalContext).toMatch(/^<ultrawork-mode>/);
+		}
+		expect(prompts.map((prompt) => isUltraworkPrompt(prompt))).toEqual([true, true, true, true, true]);
+	});
+
 	it("#given prior transcript contains triggers but current prompt does not #when hook runs #then does not emit directive", () => {
 		// given
 		const payload = {

package/packages/omo-codex/plugin/components/ulw-loop/README.md

@@ -11,11 +11,11 @@ Every subcommand below is implemented. Pass `--json` where supported for machine
 | Subcommand | Purpose |
 |------------|---------|
 | `omo ulw-loop help` | Print CLI usage. |
-| `omo ulw-loop create-goals` | Create repo-native goals and seed success criteria from a brief. |
+| `omo ulw-loop create-goals` | Create repo-native goals and seed success criteria from a brief; optionally define review-boundary validation batches with `--validation-batch-json`. |
 | `omo ulw-loop status` | Report active goal, criteria, and evidence state. |
-| `omo ulw-loop complete-goals` | Start or resume the next eligible goal, or report aggregate completion / blocked handoff. |
-| `omo ulw-loop checkpoint` | Gate a goal transition with evidence; final completion requires a complete Codex goal snapshot and a passing quality gate. |
-| `omo ulw-loop steer` | Apply a steering mutation proposal to the plan. |
+| `omo ulw-loop complete-goals` | Manual fallback to start or resume the next eligible goal, or report aggregate completion / blocked handoff. |
+| `omo ulw-loop checkpoint` | Gate a goal transition with evidence; complete checkpoints auto-start the next eligible goal by default, with `--no-advance` preserving the legacy two-call flow. |
+| `omo ulw-loop steer` | Apply one steering mutation proposal or an atomic all-or-nothing batch with `--proposals-json`. |
 | `omo ulw-loop add-goal` | Append a goal to the active plan. |
 | `omo ulw-loop criteria` | Inspect one goal's success criteria. |
 | `omo ulw-loop record-evidence` | Record observable evidence for one criterion. |
@@ -23,6 +23,8 @@ Every subcommand below is implemented. Pass `--json` where supported for machine
 
 The final quality gate parsed by `checkpoint` validates `codeReview`, `manualQa`, `gateReview`, `iteration`, and `criteriaCoverage`. `criteriaCoverage` records the original intent, desired outcome, user-facing outcome review, pass counts, and covered adversarial classes.
 
+Validation batches are optional review boundaries declared at plan creation with `--validation-batch-json '[{"batchId":"VB001","memberIds":[...],"finalGoalId":"..."}]'`. The batch-final goal cannot complete until every other member is complete or superseded-resolved, every member criterion is pass, and a quality gate's coverage counts match the recomputed member criteria. Steering split/supersede mutations keep batch membership consistent and record `batch_updated`.
+
 ## Codex Plugin
 
 This directory is a component of the aggregate `@sisyphuslabs/omo-codex-plugin` root. Plugin discovery (`.codex-plugin/plugin.json`) is owned by that aggregate root, not by this component. The component ships:

package/packages/omo-codex/plugin/components/ulw-loop/directive.md

@@ -404,13 +404,18 @@ Procedure (NON-NEGOTIABLE):
    2-attempt stop rule below) — do not loop further.
 
 # Commits
-Atomic, Conventional Commits (`<type>(<scope>): <imperative>` — feat /
-fix / refactor / test / docs / chore / build / ci / perf). One logical
-change per commit; each commit builds + tests green on its own. No WIP
-on the final branch. If a plan file exists, final commit footer:
-`Plan: .omo/plans/<slug>.md`. Do NOT auto-`git commit` unless the user
-requested or preauthorised this session — default is stage + draft
-message + present for approval.
+Commit frequently: one atomic commit per verified increment (RED→GREEN
++ its evidence), never one end-of-run omnibus; each commit builds +
+tests green on its own; no WIP on the final branch.
+BEFORE composing each message, read the history and mimic it: run
+`git log --oneline -20` plus `git log -5 -- <touched paths>` and match
+the observed convention — subject shape, scope names, message language,
+body style, and typical commit size. Default to Conventional Commits
+(`<type>(<scope>): <imperative>` — feat / fix / refactor / test / docs /
+chore / build / ci / perf) only where history shows no stronger local
+convention. If a plan file exists, final commit footer:
+`Plan: .omo/plans/<slug>.md`. Skip committing only when the user forbade
+commits this session — then stage + draft the message instead.
 
 # Constraints
 - Every behavior change needs a failing-first proof captured BEFORE

package/packages/omo-codex/plugin/components/ulw-loop/dist/checkpoint-continuation.d.ts

@@ -0,0 +1,21 @@
+import { type CheckpointUlwLoopArgs, type CheckpointUlwLoopResult } from "./checkpoint.js";
+import { type UlwLoopGoalInstruction } from "./codex-goal-instruction.js";
+import type { UlwLoopScope } from "./paths.js";
+import type { UlwLoopItem } from "./types.js";
+type ContinuationNext = {
+    readonly resumed: boolean;
+    readonly goal: UlwLoopItem;
+    readonly instruction: UlwLoopGoalInstruction;
+} | {
+    readonly done: true;
+    readonly blocked: boolean;
+    readonly handoff: string;
+};
+export type CheckpointAndContinueResult = CheckpointUlwLoopResult & {
+    readonly next?: ContinuationNext;
+};
+export declare function checkpointAndContinue(repoRoot: string, args: CheckpointUlwLoopArgs & {
+    readonly advance: boolean;
+}, scope?: UlwLoopScope): Promise<CheckpointAndContinueResult>;
+export declare function checkpoint(repoRoot: string, argv: readonly string[], json: boolean, scope?: UlwLoopScope): Promise<number>;
+export {};