oh-my-opencode 4.18.2 → 4.19.0

package/packages/omo-codex/plugin/components/start-work-continuation/test/boulder-reader.test.ts

@@ -1,40 +1,44 @@
-import { mkdirSync, mkdtempSync, rmSync, writeFileSync } from "node:fs";
+import { mkdirSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
 import { tmpdir } from "node:os";
 import { join } from "node:path";
 import { afterEach, describe, expect, it } from "vitest";
 import { getPlanChecklist, readContinuationState } from "../src/boulder-reader.js";
 
 const cleanupRoots: string[] = [];
+const SCAFFOLD_PLAN_MARKDOWN = readFileSync(new URL("./fixtures/plan-scaffold.md", import.meta.url), "utf8");
 
 afterEach(() => {
 	for (const root of cleanupRoots.splice(0)) rmSync(root, { recursive: true, force: true });
 });
 
 describe("start-work plan checklist consumption", () => {
-	it("#given top-level completed and incomplete checkboxes #when parsed #then counts remaining and total", () => {
+	it("#given scaffold headings and canonical numbered rows #when parsed #then structured totals and next label match", () => {
 		// given
-		const planPath = createPlan(
-			["# Plan", "", "## TODOs", "- [ ] First", "- [x] Done", "- [X] Also done", "- [ ] Second"].join("\n"),
-		);
+		const planPath = createPlan(SCAFFOLD_PLAN_MARKDOWN);
 
 		// when
 		const checklist = getPlanChecklist(planPath);
 
 		// then
-		expect(checklist).toEqual({ completed: 2, remaining: 2, total: 4, nextTaskLabel: "First" });
+		expect(checklist).toEqual({
+			completed: 2,
+			remaining: 2,
+			total: 4,
+			nextTaskLabel: "1. Implement checklist parser parity",
+		});
 	});
 
 	it("#given nested checkboxes #when parsed #then ignores non-column-zero items", () => {
 		// given
 		const planPath = createPlan(
-			["## TODOs", "- [ ] Top-level", "  - [ ] Nested", "\t- [ ] Tab nested", "- [x] Complete"].join("\n"),
+			["## TODOs", "- [ ] 1. Top-level", "  - [ ] Nested", "\t- [ ] Tab nested", "- [x] 2. Complete"].join("\n"),
 		);
 
 		// when
 		const checklist = getPlanChecklist(planPath);
 
 		// then
-		expect(checklist).toEqual({ completed: 1, remaining: 1, total: 2, nextTaskLabel: "Top-level" });
+		expect(checklist).toEqual({ completed: 1, remaining: 1, total: 2, nextTaskLabel: "1. Top-level" });
 	});
 
 	it("#given checkboxes outside counted sections #when parsed #then ignores unrelated top-level tasks", () => {
@@ -44,12 +48,12 @@ describe("start-work plan checklist consumption", () => {
 				"# Plan",
 				"- [ ] Preamble task",
 				"## TODOs",
-				"- [ ] Build hook",
+				"- [ ] 1. Build hook",
 				"## Acceptance Criteria",
 				"- [ ] Acceptance item",
 				"## Final Verification Wave",
-				"- [x] Run tests",
-				"- [ ] Run smoke",
+				"- [x] F1. Run tests",
+				"- [ ] F2. Run smoke",
 			].join("\n"),
 		);
 
@@ -57,18 +61,184 @@ describe("start-work plan checklist consumption", () => {
 		const checklist = getPlanChecklist(planPath);
 
 		// then
-		expect(checklist).toEqual({ completed: 1, remaining: 2, total: 3, nextTaskLabel: "Build hook" });
+		expect(checklist).toEqual({ completed: 1, remaining: 2, total: 3, nextTaskLabel: "1. Build hook" });
 	});
 
 	it("#given all top-level tasks complete #when parsed #then next task is null", () => {
 		// given
-		const planPath = createPlan(["## TODOs", "- [x] First", "- [X] Second"].join("\n"));
+		const planPath = createPlan(
+			["## Todos", "- [x] 1. First", "- [X] 2. Second", "## Final verification wave", "- [x] F1. Final"].join("\n"),
+		);
+
+		// when
+		const checklist = getPlanChecklist(planPath);
+
+		// then
+		expect(checklist).toEqual({ completed: 3, remaining: 0, total: 3, nextTaskLabel: null });
+	});
+
+	it("#given no structured headings #when parsed #then legacy top-level checkbox fallback remains", () => {
+		// given
+		const planPath = createPlan(["# Plan", "- [ ] First", "- [x] Done", "  - [ ] Nested"].join("\n"));
+
+		// when
+		const checklist = getPlanChecklist(planPath);
+
+		// then
+		expect(checklist).toEqual({ completed: 1, remaining: 1, total: 2, nextTaskLabel: "First" });
+	});
+
+	it("#given a heading-free legacy star checklist #when parsed #then fallback behavior is preserved", () => {
+		// given
+		const planPath = createPlan(["# Plan", "* [ ] First", "* [x] Done", "  * [ ] Nested"].join("\n"));
+
+		// when
+		const checklist = getPlanChecklist(planPath);
+
+		// then
+		expect(checklist).toEqual({ completed: 1, remaining: 1, total: 2, nextTaskLabel: "First" });
+	});
+
+	it("#given noncanonical structured rows #when parsed #then only exact positive-number grammar is counted", () => {
+		// given
+		const planPath = createPlan(
+			[
+				"## Todos",
+				"- [ ] 0. Zero is invalid",
+				"- [ ] 01. Leading zero is invalid",
+				"* [ ] 2. Star marker is invalid",
+				"-[ ] 3. Missing spaces are invalid",
+				"- [ ] 4. Canonical implementation",
+				"## Final verification wave",
+				"- [ ] F0. Zero final verifier is invalid",
+				"- [ ] F01. Leading zero final verifier is invalid",
+				"- [x] F2. Canonical final verifier",
+			].join("\n"),
+		);
+
+		// when
+		const checklist = getPlanChecklist(planPath);
+
+		// then
+		expect(checklist).toEqual({
+			completed: 1,
+			remaining: 1,
+			total: 2,
+			nextTaskLabel: "4. Canonical implementation",
+		});
+	});
+
+	it("#given fenced examples and a higher-level heading #when parsed #then section scope excludes them", () => {
+		// given
+		const planPath = createPlan(
+			[
+				"## Todos",
+				"- [ ] 1. Counted implementation",
+				"```md",
+				"- [ ] 2. Fenced example",
+				"```",
+				"# Appendix",
+				"- [ ] 3. Appendix checkbox",
+				"## Final verification wave",
+				"- [x] F1. Counted verifier",
+			].join("\n"),
+		);
+
+		// when
+		const checklist = getPlanChecklist(planPath);
+
+		// then
+		expect(checklist).toEqual({
+			completed: 1,
+			remaining: 1,
+			total: 2,
+			nextTaskLabel: "1. Counted implementation",
+		});
+	});
+
+	it("#given a child heading inside TODOs #when parsed #then canonical rows remain in the parent section", () => {
+		// given
+		const planPath = createPlan(["## TODOs", "- [x] 1. First task", "### Notes", "- [ ] 2. Second task"].join("\n"));
+
+		// when
+		const checklist = getPlanChecklist(planPath);
+
+		// then
+		expect(checklist).toEqual({ completed: 1, remaining: 1, total: 2, nextTaskLabel: "2. Second task" });
+	});
+
+	it("#given a four-backtick fence containing triple-backtick examples #when parsed #then shorter fences do not close it", () => {
+		// given
+		const planPath = createPlan(
+			[
+				"## Todos",
+				"- [x] 1. Counted implementation",
+				"````md",
+				"```ts",
+				"- [ ] 2. Fenced example",
+				"```",
+				"````",
+				"## Final verification wave",
+				"- [ ] F1. Counted verifier",
+			].join("\n"),
+		);
+
+		// when
+		const checklist = getPlanChecklist(planPath);
+
+		// then
+		expect(checklist).toEqual({
+			completed: 1,
+			remaining: 1,
+			total: 2,
+			nextTaskLabel: "F1. Counted verifier",
+		});
+	});
+
+	it("#given structured headings with ATX closing markers #when parsed #then canonical tasks remain structured", () => {
+		// given
+		const planPath = createPlan(
+			["## TODOs ##", "- [ ] 1. Implement", "## Final Verification Wave ###", "- [ ] F1. Verify"].join("\n"),
+		);
+
+		// when
+		const checklist = getPlanChecklist(planPath);
+
+		// then
+		expect(checklist).toEqual({
+			completed: 0,
+			remaining: 2,
+			total: 2,
+			nextTaskLabel: "1. Implement",
+		});
+	});
+
+	it("#given inline backtick code before a canonical task #when parsed #then it does not open a fence", () => {
+		// given
+		const planPath = createPlan(["## TODOs", "```example```", "- [ ] 1. Implement"].join("\n"));
+
+		// when
+		const checklist = getPlanChecklist(planPath);
+
+		// then
+		expect(checklist.total).toBe(1);
+		expect(checklist.nextTaskLabel).toBe("1. Implement");
+	});
+
+	it("#given a heading-free fenced checkbox example #when parsed #then legacy fallback ignores it", () => {
+		// given
+		const planPath = createPlan(["````md", "- [ ] 1. Example only", "````"].join("\n"));
 
 		// when
 		const checklist = getPlanChecklist(planPath);
 
 		// then
-		expect(checklist).toEqual({ completed: 2, remaining: 0, total: 2, nextTaskLabel: null });
+		expect(checklist).toEqual({
+			completed: 0,
+			remaining: 0,
+			total: 0,
+			nextTaskLabel: null,
+		});
 	});
 });
 
@@ -77,7 +247,7 @@ describe("start-work boulder state reader", () => {
 		// given
 		const workspace = createWorkspace({
 			boulderJson: createBoulderJson({ status: "active", sessionIds: ["codex:sess_abc"] }),
-			planMarkdown: "# Plan\n\n## TODOs\n- [ ] First\n- [x] Done\n- [ ] Second\n",
+			planMarkdown: SCAFFOLD_PLAN_MARKDOWN,
 		});
 
 		// when
@@ -90,7 +260,12 @@ describe("start-work boulder state reader", () => {
 			boulderPath: join(workspace, ".omo", "boulder.json"),
 			ledgerPath: join(workspace, ".omo", "start-work", "ledger.jsonl"),
 			worktreePath: null,
-			checklist: { completed: 1, remaining: 2, total: 3, nextTaskLabel: "First" },
+			checklist: {
+				completed: 2,
+				remaining: 2,
+				total: 4,
+				nextTaskLabel: "1. Implement checklist parser parity",
+			},
 		});
 	});
 
@@ -98,7 +273,7 @@ describe("start-work boulder state reader", () => {
 		// given
 		const workspace = createWorkspace({
 			boulderJson: createBoulderJson({ status: "completed", sessionIds: ["codex:sess_abc"] }),
-			planMarkdown: "# Plan\n\n## TODOs\n- [ ] First\n",
+			planMarkdown: "# Plan\n\n## TODOs\n- [ ] 1. First\n",
 		});
 
 		// when
@@ -112,7 +287,7 @@ describe("start-work boulder state reader", () => {
 		// given
 		const workspace = createWorkspace({
 			boulderJson: createBoulderJson({ status: "paused", sessionIds: ["codex:sess_abc"] }),
-			planMarkdown: "# Plan\n\n## TODOs\n- [ ] First\n",
+			planMarkdown: "# Plan\n\n## TODOs\n- [ ] 1. First\n",
 		});
 
 		// when
@@ -120,14 +295,14 @@ describe("start-work boulder state reader", () => {
 
 		// then
 		expect(state?.planName).toBe("launch-plan");
-		expect(state?.checklist).toEqual({ completed: 0, remaining: 1, total: 1, nextTaskLabel: "First" });
+		expect(state?.checklist).toEqual({ completed: 0, remaining: 1, total: 1, nextTaskLabel: "1. First" });
 	});
 
 	it("#given active codex work with no remaining checklist items #when state is read #then final gate continuation remains present", () => {
 		// given
 		const workspace = createWorkspace({
 			boulderJson: createBoulderJson({ status: "active", sessionIds: ["codex:sess_abc"] }),
-			planMarkdown: "# Plan\n\n## TODOs\n- [x] First\n",
+			planMarkdown: "# Plan\n\n## TODOs\n- [x] 1. First\n",
 		});
 
 		// when
@@ -155,7 +330,7 @@ describe("start-work boulder state reader", () => {
 		// given
 		const workspace = createWorkspace({
 			boulderJson: "{",
-			planMarkdown: "# Plan\n\n## TODOs\n- [ ] First\n",
+			planMarkdown: "# Plan\n\n## TODOs\n- [ ] 1. First\n",
 		});
 
 		// when
@@ -169,7 +344,7 @@ describe("start-work boulder state reader", () => {
 		// given
 		const workspace = createWorkspace({
 			boulderJson: createBoulderJson({ status: "active", sessionIds: ["sess_abc"] }),
-			planMarkdown: "# Plan\n\n## TODOs\n- [ ] First\n",
+			planMarkdown: "# Plan\n\n## TODOs\n- [ ] 1. First\n",
 		});
 
 		// when
@@ -201,7 +376,7 @@ describe("start-work boulder state reader", () => {
 				started_at: "2026-06-12T00:00:00.000Z",
 				session_ids: ["codex:sess_abc"],
 			}),
-			planMarkdown: "# Plan\n\n## TODOs\n- [ ] First\n",
+			planMarkdown: "# Plan\n\n## TODOs\n- [ ] 1. First\n",
 		});
 
 		// when

package/packages/omo-codex/plugin/components/start-work-continuation/test/cli.test.ts

@@ -6,6 +6,7 @@ import { execPath } from "node:process";
 import { afterEach, describe, expect, it } from "vitest";
 
 const cleanupRoots: string[] = [];
+const SCAFFOLD_PLAN_MARKDOWN = readFileSync(new URL("./fixtures/plan-scaffold.md", import.meta.url), "utf8");
 
 afterEach(() => {
 	for (const root of cleanupRoots.splice(0)) rmSync(root, { recursive: true, force: true });
@@ -25,8 +26,8 @@ describe("start-work continuation CLI", () => {
 		expect(result.status).toBe(0);
 		const output = parseStopHookOutput(result.stdout);
 		expect(output.decision).toBe("block");
-		expect(output.reason).toContain("Remaining top-level checkboxes: `2` of `3`");
-		expect(output.reason).toContain("Next incomplete task: `Task one`");
+		expect(output.reason).toContain("Remaining top-level checkboxes: `2` of `4`");
+		expect(output.reason).toContain("Next incomplete task: `1. Implement checklist parser parity`");
 		expect(output.reason).toContain("Your session id in boulder.json: `codex:s1`");
 	});
 
@@ -106,7 +107,7 @@ function createWorkspace(sessionIds: readonly string[]): string {
 	const root = mkdtempSync(join(tmpdir(), "codex-continuation-cli-"));
 	cleanupRoots.push(root);
 	mkdirSync(join(root, ".omo", "plans"), { recursive: true });
-	writeFileSync(join(root, ".omo", "plans", "plan.md"), "## TODOs\n\n- [ ] Task one\n- [x] Done\n- [ ] Task two\n");
+	writeFileSync(join(root, ".omo", "plans", "plan.md"), SCAFFOLD_PLAN_MARKDOWN);
 	const work = {
 		work_id: "w1",
 		active_plan: ".omo/plans/plan.md",

package/packages/omo-codex/plugin/components/start-work-continuation/test/codex-hook.test.ts

@@ -1,4 +1,4 @@
-import { mkdirSync, mkdtempSync, rmSync, writeFileSync } from "node:fs";
+import { mkdirSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
 import { tmpdir } from "node:os";
 import { join } from "node:path";
 import { afterEach, describe, expect, it } from "vitest";
@@ -8,6 +8,7 @@ import type { ReadonlyFileSystem, StopInput } from "../src/types.js";
 
 const DEFAULT_WORKSPACE = "/repo";
 const cleanupRoots: string[] = [];
+const SCAFFOLD_PLAN_MARKDOWN = readFileSync(new URL("./fixtures/plan-scaffold.md", import.meta.url), "utf8");
 
 afterEach(() => {
 	for (const root of cleanupRoots.splice(0)) rmSync(root, { recursive: true, force: true });
@@ -49,7 +50,7 @@ describe("start-work Stop hook", () => {
 				status: "active",
 				worktreePath: "/tmp/worktree",
 			}),
-			planMarkdown: ["# Plan", "", "## TODOs", "- [ ] First", "- [x] Done", "- [ ] Second"].join("\n"),
+			planMarkdown: SCAFFOLD_PLAN_MARKDOWN,
 		});
 		const fs = createMemoryFs();
 
@@ -62,8 +63,8 @@ describe("start-work Stop hook", () => {
 		expect(parsed.reason).toContain("- Plan: `launch-plan`");
 		expect(parsed.reason).toContain(`- Plan file: \`${join(workspace, ".omo", "plans", "plan.md")}\``);
 		expect(parsed.reason).toContain(`- Boulder state: \`${join(workspace, ".omo", "boulder.json")}\``);
-		expect(parsed.reason).toContain("- Remaining top-level checkboxes: `2` of `3`");
-		expect(parsed.reason).toContain("- Next incomplete task: `First`");
+		expect(parsed.reason).toContain("- Remaining top-level checkboxes: `2` of `4`");
+		expect(parsed.reason).toContain("- Next incomplete task: `1. Implement checklist parser parity`");
 		expect(parsed.reason).toContain("- Worktree: `/tmp/worktree`");
 		expect(parsed.reason).toContain(`- Ledger: \`${join(workspace, ".omo", "start-work", "ledger.jsonl")}\``);
 		expect(parsed.reason).toContain("- Your session id in boulder.json: `codex:sess_abc`");
@@ -73,7 +74,7 @@ describe("start-work Stop hook", () => {
 		// given
 		const workspace = createWorkspace({
 			boulderJson: createBoulderJson({ sessionIds: ["codex:sess_abc"], status: "active" }),
-			planMarkdown: ["# Plan", "", "## TODOs", "- [x] Done"].join("\n"),
+			planMarkdown: ["# Plan", "", "## TODOs", "- [x] 1. Done"].join("\n"),
 		});
 		const fs = createMemoryFs();
 

package/packages/omo-codex/plugin/components/start-work-continuation/test/fixtures/plan-scaffold.md

@@ -0,0 +1,15 @@
+# Scaffold Parser Parity
+
+## Todos
+- [ ] 1. Implement checklist parser parity
+  - [ ] Nested acceptance detail
+- [x] 2. Preserve completed implementation rows
+- [ ] Missing numeric prefix must be ignored
+
+## Acceptance Criteria
+- [ ] Outside tracked sections must be ignored
+
+## Final verification wave
+- [ ] F1. Exercise the Codex Stop surface
+- [X] F2. Preserve completed final verification rows
+- [ ] 3. Wrong final-wave label must be ignored

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 4.18.2) Checking Thread Title Hygiene"
+						"statusMessage": "(OmO 4.19.0) Checking Thread Title Hygiene"
 					}
 				]
 			}

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

@@ -1,6 +1,6 @@
 {
 	"name": "@sisyphuslabs/codex-teammode",
-	"version": "4.18.2",
+	"version": "4.19.0",
 	"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 4.18.2) Recording Session Telemetry"
+						"statusMessage": "(OmO 4.19.0) Recording Session Telemetry"
 					}
 				]
 			}

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

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-telemetry",
-	"version": "4.18.2",
+	"version": "4.19.0",
 	"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.md

@@ -13,19 +13,19 @@ Conventions for human contributors and AI agents working on this repository.
 
 ## Layout
 
-- `src/cli.ts` — `UserPromptSubmit` hook CLI. Reads JSON on stdin, writes a compact `<ultrawork-mode>` skill pointer to stdout when the keyword matches (full directive as fallback), exits 0 otherwise.
-- `src/codex-hook.ts` — pure detector/hook behavior; skips on context-pressure/recovery transcripts and when the directive is already in the transcript.
-- `src/skill-pointer.ts` — `buildUltraworkAdditionalContext()`: emits the <4096-byte pointer (Codex App truncates large hook output) directing the model to `create_goal` then read the bundled `ultrawork` skill; falls back to the full `ULTRAWORK_DIRECTIVE` when the plugin skills tree is absent. Pointer size + `ulw-loop` mirror byte-identity pinned by `plugin/test/ultrawork-skill-pointer.test.mjs`.
-- `directive.md` — bundled ultrawork directive text.
-- `skills/ultrawork/SKILL.md` — full directive as a skill, generated by `scripts/sync-directive.mjs`; pinned byte-for-byte to `directive.md` by `test/directive-source.test.ts`. `plugin/scripts/sync-skills.mjs` materializes it into the aggregate `plugin/skills/` tree the pointer path targets.
-- `skills/ulw-plan/` — dual-maintained copy of the ulw-plan skill (component copy wins over `packages/shared-skills/skills/ulw-plan/` in sync-skills; keep both in step by hand).
-- `agents/*.toml` — bundled Codex agent role files. Installed as regular files into `CODEX_HOME/agents/` by `src/cli/install-codex/link-cached-plugin-agents.ts` at install time. Public `sisyphuslabs` installs source them from Codex's installed-marketplace snapshot, not the versioned plugin cache, so they survive Codex auto-update cache pruning and temporary snapshot cleanup. No runtime `SessionStart` hook is involved.
-- `hooks/hooks.json` — registers the prompt-detector hook only.
-- `.codex-plugin/plugin.json` — Codex plugin manifest. Marketplace metadata lives here, not in `package.json`.
+- `src/cli.ts`: `UserPromptSubmit` hook CLI. Reads JSON on stdin, writes a compact `<ultrawork-mode>` skill pointer to stdout when the keyword matches (full directive as fallback), exits 0 otherwise.
+- `src/codex-hook.ts`: pure detector/hook behavior; skips on context-pressure/recovery transcripts and when the directive is already in the transcript.
+- `src/skill-pointer.ts`: `buildUltraworkAdditionalContext()`: emits the <4096-byte pointer (Codex App truncates large hook output) directing the model to `create_goal` then read the bundled `ultrawork` skill; falls back to the full `ULTRAWORK_DIRECTIVE` when the plugin skills tree is absent. Pointer size + `ulw-loop` mirror byte-identity pinned by `plugin/test/ultrawork-skill-pointer.test.mjs`.
+- `directive.md`: bundled ultrawork directive text.
+- `skills/ultrawork/SKILL.md`: full directive as a skill, generated by `scripts/sync-directive.mjs`; pinned byte-for-byte to `directive.md` by `test/directive-source.test.ts`. `plugin/scripts/sync-skills.mjs` materializes it into the aggregate `plugin/skills/` tree the pointer path targets.
+- `skills/ulw-plan/`: dual-maintained copy of the ulw-plan skill (component copy wins over `packages/shared-skills/skills/ulw-plan/` in sync-skills; keep both in step by hand).
+- `agents/*.toml`: bundled Codex agent role files. Installed as regular files into `CODEX_HOME/agents/` by `src/cli/install-codex/link-cached-plugin-agents.ts` at install time. Public `sisyphuslabs` installs source them from Codex's installed-marketplace snapshot, not the versioned plugin cache, so they survive Codex auto-update cache pruning and temporary snapshot cleanup. No runtime `SessionStart` hook is involved.
+- `hooks/hooks.json`: registers the prompt-detector hook only.
+- `.codex-plugin/plugin.json`: Codex plugin manifest. Marketplace metadata lives here, not in `package.json`.
 
 ## Constraints
 
-- Never let the hook block a turn — exit code is always 0.
+- Never let the hook block a turn. Exit code is always 0.
 - Never make a network call from the hook.
 - Keep the directive in `directive.md`. Do not inline it into TypeScript files.
 - Keep bundled agent role prompts concise and model-specific; measure prompt length when changing them.

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

@@ -1,8 +1,8 @@
 name = "momus"
-description = "Deep plan reviewer. Verifies a work plan is executable: references exist, tasks are startable, QA scenarios are concrete. Runs at Ultra and may take a long time; callers must wait for its terminal result instead of cancelling or duplicating it. Issues OKAY, ITERATE, or REJECT. Read-only."
+description = "Deep plan reviewer. Verifies a work plan is executable: references exist, tasks are startable, QA scenarios are concrete. Runs at High and may take a long time; callers must wait for its terminal result instead of cancelling or duplicating it. Issues OKAY, ITERATE, or REJECT. Read-only."
 nickname_candidates = ["Reviewer"]
-model = "gpt-5.6-sol"
-model_reasoning_effort = "ultra"
+model = "gpt-5.6-terra"
+model_reasoning_effort = "high"
 
 developer_instructions = """
 Role: plan reviewer. You verify a work plan is executable and its references are valid. You are a blocker-finder, not a perfectionist: your job is to UNBLOCK work. Read-only - you never write plans or code.

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 4.18.2) Checking Ultrawork Trigger"
+						"statusMessage": "(OmO 4.19.0) Checking Ultrawork Trigger"
 					}
 				]
 			}

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

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-ultrawork",
-	"version": "4.18.2",
+	"version": "4.19.0",
 	"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/ulw-plan/SKILL.md

@@ -24,24 +24,28 @@ After grounding, make ONE judgment, record `intent: clear|unclear` plus `review_
 
 - **OVERRIDE - explicit ask wins:** if the user explicitly asks to be questioned or interviewed ("ask me", "interview me", "why aren't you asking me" - in any language), route **CLEAR**, run the interview, and turn the adopt-default filter OFF: the user has claimed the forks, so every surviving one is ASKED, not defaulted. This beats the OUTCOME test below, even on a fuzzy brief.
 - **CLEAR** - the user knows the outcome; the only open items are preferences/tradeoffs the repo cannot answer (genuine owner-decisions). Read **`references/intent-clear.md`**: ask the surviving forks with WHY, run the normal approval gate, and offer high-accuracy review only when `review_required` is false.
-- **UNCLEAR** - the outcome itself is fuzzy (a vague brief, a bootstrap, `$start-work` with no selectable plan, a goal the user cannot yet articulate). Asking would offload your own job onto the user. Read **`references/intent-unclear.md`**: research maximally, adopt and ANNOUNCE best-practice defaults, do NOT ask the user extra questions, and run high-accuracy review AUTOMATICALLY (unless Classify sized the work Trivial).
+- **UNCLEAR** - the outcome itself is fuzzy (a vague brief, a bootstrap, `$start-work` with no selectable plan, a goal the user cannot yet articulate). Asking would offload your own job onto the user. Read **`references/intent-unclear.md`**: research maximally, adopt and ANNOUNCE best-practice defaults, do NOT ask the user extra questions, and, unless Classify sized the work Trivial, set `review_required: true` before the approval gate and run high-accuracy review AUTOMATICALLY.
 - **ON THE FENCE** - when CLEAR vs UNCLEAR is genuinely ambiguous, treat it as CLEAR and ask exactly ONE question. A user wrongly silenced is worse than one extra question. The dominant failure to guard against is mis-routing a CLEAR request to UNCLEAR, which silently applies defaults and overrides forks the user wanted to own.
 
 WORKED: "add a 5/min-per-IP rate-limit to `/login`" = CLEAR. "make auth better" = UNCLEAR.
 
 Both intent paths ALSO read **`references/full-workflow.md`** for the shared mechanics - the plan template, the final verification wave, the APPEND protocol, and the full delegation/wait syntax. Read the phase you are in.
 
-## RUN THE SCRIPT - do not hand-build the plan files
+## RUN THE SCRIPT - do not hand-build artifacts
 
-Before writing any plan or draft by hand, RUN:
+As soon as `<slug>` and intent are known, before recording draft state, RUN:
 
 ```
-node "<skill-root>/scripts/scaffold-plan.mjs" <slug> [--clear|--unclear]
+node "<skill-root>/scripts/scaffold-plan.mjs" <slug> [--clear|--unclear] --draft-only [--review-required]
 ```
 
-(Replace `<skill-root>` with this skill's own directory; `bun` is an accepted substitute for `node`.) It creates `.omo/drafts/<slug>.md` (your durable, compaction-safe resume point) and `.omo/plans/<slug>.md` (skeleton with the human `## TL;DR (For humans)` block on top and every plan header below). Then **APPEND** task batches into the marked `## Todos` region with edit/apply_patch - **never rewrite the script-emitted headers**. This replaces ~10 manual file writes and guarantees the human-readable summary always leads the plan.
+(Replace `<skill-root>` with this skill's own directory; `bun` is accepted.) This creates only `.omo/drafts/<slug>.md`, the compaction-safe resume point; it does not create a plan before approval. Include `--review-required` when an explicit modifier requires review or the classified route is non-Trivial UNCLEAR, so the first durable write contains the complete pending review request. After approval, rerun without `--draft-only` to create `.omo/plans/<slug>.md`, then **APPEND** task batches into `## Todos` - never rewrite script-emitted headers.
 
-Run it ONCE at plan generation. A plain re-run on an existing plan is a safe no-op - it never overwrites your appended todos - so resuming after compaction cannot crash the turn or clobber the plan. Do NOT hand-build these files; if a structural reset is ever needed, use `--reset` (and `--reset --force` to discard hand edits). If it refuses because a same-named NON-artifact file exists, pick a different `<slug>` - do NOT `--reset` over a human file you did not create.
+Both invocations are resume-safe no-ops for artifacts already present. Do NOT hand-build them; use `--reset` only for a structural reset (`--reset --force` discards edits). If a same-named non-artifact file exists, choose another slug.
+
+## Plan artifact producer contract
+
+When producing the plan, encode every executable item as a column-zero Markdown task row: implementation rows MUST match `- [ ] N. <title>` (where `N` is a positive decimal integer), and final-verifier rows MUST match `- [ ] F<number>. <title>`. Prose headings, numbered paragraphs, and ordinary bullets are not task substitutes and MUST NOT be counted as implementation or final-verifier tasks. Before handoff, run a structural self-check over the plan: verify that every implementation row and final-verifier row is column-zero, matches its required grammar, and appears in the intended `## Todos` or `## Final verification wave` section; verify that no prose heading or bullet is being used as a task; and repair the plan before handoff if any check fails.
 
 ## Universal invariants (hold on every path)
 
@@ -58,7 +62,7 @@ Run it ONCE at plan generation. A plain re-run on an existing plan is a safe no-
 
 ## Approval gate
 
-When exploration is exhausted and the unknowns are answered, record the gate in the draft (`status: awaiting-approval`, the pending action `write .omo/plans/<slug>.md`, the approach), present a short brief once, then **wait for the user's explicit okay**. Read their next reply as a decision (approve / scope-change / still-unclear). Full gate mechanics: `references/full-workflow.md`.
+When exploration is exhausted and the unknowns are answered, record the gate in the draft (`status: awaiting-approval`, approach, and the next workflow action), present a short brief once, then **wait for the user's explicit okay**. Approval authorizes plan creation only; any already-required review runs afterward under its existing authorization. Full mechanics: `references/full-workflow.md`.
 
 ## Delegation (Codex-native)