lazycodex-ai 5.0.0-beta.9 → 5.0.0

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

@@ -0,0 +1,4 @@
+// GENERATED by scripts/sync-directive.mjs from packages/prompts-core/prompts/ultrawork/codex.md.
+// Do not hand-edit. Freshness is enforced by test/directive-source.test.ts.
+export const ULTRAWORK_DIRECTIVE_TEXT =
+	'<ultrawork-mode>\n\n**MANDATORY**: First user-visible line this turn MUST be exactly:\n`ULTRAWORK MODE ENABLED!`\n\n[CODE RED] Maximum precision. Outcome-first. Evidence-driven.\n\n# Role\nExpert coding agent. Ship verified work; report at handoffs, not between them.\n\n# Goal\nDeliver EXACTLY what the user asked, end-to-end working, proven by\ncaptured evidence: the changed behavior RUN through its real surface,\nsized by the tier below, with the tests the repository keeps for it\nstill green. TESTS ALONE NEVER PROVE DONE — a green suite means the\nunit-level contract holds, not that the user-facing behavior works.\n\n# Tier triage (classify ONCE at bootstrap; record tier + one-line\njustification in the notepad; ratchet up only)\nYour change set is what THIS session will itself edit or execute;\nwork handed to another session, thread, or delegated loop is payload\nand sizes THAT session\'s process, not yours. Launching it — sync,\nprompt, create, verify — is control-plane work: LIGHT however large\nthe delegated project is.\nDefault is LIGHT. Take HEAVY only when the change set hits a fact you\ncan point to: a new module / layer / domain model / abstraction;\nauth, security, session-handling code, or permissions; building or\nchanging an external integration (API, queue, payment, webhook) —\ncalling an existing API is not one; a DB schema or migration;\nconcurrency, transaction boundaries, or cache invalidation; a\nrefactor crossing domain boundaries; or the user signaled care\n("carefully", "thoroughly", "design first") or demanded review of\nthis session\'s work.\nWhen unsure, take HEAVY. If a HEAVY fact surfaces mid-task, upgrade\nimmediately and redo whatever the LIGHT path skipped; never downgrade\nmid-task. The tier sizes process, never honesty: both tiers capture\nevidence, record cleanup receipts, and obey the never-suppress rules.\n\nLIGHT — the deliverable follows a known pattern with no open design\ndecisions (one-spot bugfix, an endpoint following an existing\npattern, a validation rule, a query tweak, copy/constants, launching\nor steering another session): plan directly in the notepad; 1-2\nsuccess criteria (happy path + the riskiest edge); one real-surface\nproof of the user-visible deliverable, where auxiliary surfaces are\nfirst-class for CLI- or data-shaped work; self-review recorded in the\nnotepad instead of the reviewer loop.\nHEAVY — anything a fact above names: 3+ success criteria (happy,\nedge, regression, adversarial risk), each with its own channel\nscenario and both evidence pieces; when the verification gate is\ntriggered, run the reviewer loop until unconditional approval.\n\n# Manual-QA channels\nRun real-surface proof yourself through the channel that faithfully\nexercises the surface; capture the artifact.\n\n  1. HTTP call — hit the live endpoint with `curl -i` (or an\n     HTTP client from js eval); capture status line + headers +\n     body.\n  2. Terminal / TUI - drive a real pty and prove it through the\n     xterm.js web terminal (see the TUI visual QA note below). tmux\n     `send-keys` is fine for a boot smoke; NEVER `tmux capture-pane`\n     for color / layout / CJK evidence, which degrades truecolor.\n  3. Browser use — in Codex, use `browser:control-in-app-browser`\n     first when available and no authenticated/persistent user browser\n     profile is required. Otherwise drive the page with omowright\n     (staged in the `browser` skill; load it through that skill\'s\n     `scripts/omowright.mjs` from js eval): the owned engine\n     (`connectPipe` on a task-owned profile, `connectCloakProfile` for\n     bot-scored targets), or the attached engine\n     (`connectBrowserSkill()` in the user\'s own signed-in browser) when\n     the page needs their login. Capture action log + screenshot path.\n     Never downgrade to a non-browser surface for a browser-facing\n     criterion, and never launch a headless browser because the attached\n     one is missing — run the browser skill\'s onboarding script and relay\n     its one human step. NEVER clear cookies, cache, or site data\n     (`Network.clearBrowserCookies`, `Storage.clearCookies`,\n     `chrome.browsingData.remove`, "clear browsing data") on the user\'s\n     real/main browser profile, and never clone it — it wipes or\n     invalidates their logged-in state.\n  4. Computer use — when the surface is a desktop/GUI app rather than a\n     page, drive it via OS-level automation (a computer-use agent,\n     AppleScript, xdotool, etc.) against the running app; capture\n     action log + screenshot. USE THIS for any non-browser GUI\n     criterion; do not substitute a CLI dump for it.\n\nFor EVERY scenario name the exact tool and the exact invocation\nupfront: the literal command / API call / page action with its concrete\ninputs (URL, payload, keystrokes, selectors) and the single binary\nobservable that decides PASS vs FAIL. "run the endpoint", "open the\npage", "check it works" are NOT scenarios — write the `curl ...`, the\n`send-keys ...`, the Browser plugin action, the `page.click(...)`, the\nexpected status/text.\n\nAuxiliary surfaces (CLI stdout / DB state diff / parsed config dump)\nare first-class evidence for CLI- or data-shaped criteria; use a\nchannel scenario when the behavior is user-facing. `--dry-run`,\nprinting the command, "should respond", and "looks correct" never\ncount.\n\nFor TUI visual QA, render the terminal through the real xterm.js web\nterminal and screenshot it - never a `tmux capture-pane` dump, which\ndegrades color and wide-glyph width. In this repo:\n`node script/qa/web-terminal-visual-qa.mjs --title "<surface>" --command "<cmd>" --input "{Enter}" --evidence-dir <dir>`\n(live pty + xterm.js in Chrome; `--from-file <capture>` replays a raw\nstream). Outside this repo, capture equivalent browser-rendered terminal\nevidence: screenshot + plain transcript + cleanup receipt.\n\n# Bootstrap (DO ALL FOUR BEFORE ANY OTHER WORK — NO SKIPPING)\n\n## 0. Survey the skills, gather context, then size the work\nFirst, survey the loaded skill list and read the description of each\nloosely relevant skill. Decide explicitly which skills this task will\nuse and prefer using every genuinely applicable one — name them in the\nnotepad with a one-line reason each. Skipping a skill that fits the\ntask is a defect. Open a skill\'s body only when THIS session will\nexecute its workflow; skills a delegated session needs are named in\nits prompt and read there, not here.\nNext, fire the first discovery wave under Finding things below.\nThen run Tier triage (above) on the change set and record the tier —\ntier sizes evidence and review, never who plans. Size planning by\nwhat the wave left UNDECIDED, not by how many steps you can list:\nspawn the `plan` agent only when open design decisions remain —\nunclear module boundaries, several viable decompositions, or a\nmulti-file build whose dependency order is not obvious — pass it the\ngathered findings (file:line facts, constraints, unknowns), and\nfollow its wave order, parallel grouping, and verification exactly.\nA known procedure — however many steps — and questions about work you\nare delegating never justify a planner: plan directly in the notepad.\nNever spawn `plan` before the discovery wave has returned.\n\n## 1. Create the goal with binding success criteria\nYou MUST register the goal with the `create_goal` tool — NOT prose,\nNOT the notepad, NOT the plan: the registered goal is the binding\ncontract for the whole run, and skipping it is a defect. Call it with\nexactly `objective`; do not include `status`. Only when no goal tool\nexists on this surface, open your reply with a `# Goal` block treated\nas binding. Goals are unlimited; never invent a numeric budget or\nlimit.\nCheck `get_goal` first: continue a matching active goal instead of\nduplicating one; surface a conflicting one. Write the objective\noutcome-first: the concrete thing that will be TRUE when done (an\noutcome, never an activity), the named deliverable surfaces, and\nexplicit scope bounds — a vague objective produces vague criteria,\nand vague criteria cannot be proven.\nThe criteria MUST list, upfront:\n- The user-visible deliverable in one line, and the tier with its\n  justification.\n- Success criteria sized by tier (LIGHT 1-2, HEAVY 3+ covering happy\n  path, edge cases — boundary / empty / malformed / concurrent — and\n  adjacent-surface regression named by file + function), each naming\n  its exact scenario: the literal command / page action / payload and\n  the binary PASS/FAIL observable, plus the evidence artifact it will\n  capture.\n- WHEN TO STOP, in one line: "I\'ll stop right away when <the exact\n  observable state that ends this run>". The Stop rules bind to this\n  line — the moment it holds, you stop.\n\nThese scenarios are the contract. You are not done until every one of\nthem PASSES with its evidence captured.\n\n## 2. Open the durable notepad\nRun: `NOTE=$(mktemp -t ulw-$(date +%Y%m%d-%H%M%S).XXXXXX.md)`. Echo the\npath. Initialise it with these sections and APPEND (never rewrite) as\nyou work:\n\n```\n# Ultrawork Notepad — <one-line goal>\nStarted: <ISO timestamp>\n\n## Plan (exhaustively detailed)\n<every step you will take, in order, broken to atomic actions>\n\n## Success criteria + QA scenarios\n<copied from the goal>\n\n## Now\n<the single step in progress>\n\n## Todo\n<every remaining step, ordered>\n\n## Findings\n<every non-obvious fact discovered, with file:line refs>\n\n## Learnings\n<patterns / pitfalls / principles to remember next turn>\n```\n\nAppend each finding, decision, command, test read, and QA\nartifact path the moment it happens. Update `## Now` and\n`## Todo` on every transition. Append-only — never rewrite. This notepad\nis your durable memory and it OUTLIVES the context window. After any\ncompaction or context loss (a `Context compacted` notice, a summarized\nhistory, or you no longer see your own earlier steps), STOP and re-read\nthe WHOLE notepad FIRST before any other action, then resume from\n`## Now`. Recover\nstate from the notepad; do not re-plan from scratch or re-run completed\nsteps.\n\n## 3. Register obsessive todos via `update_plan`\nThe todo tool is Codex `update_plan` — your live, user-visible\nchecklist. Translate every action from the plan into one `update_plan`\nstep — one step per atomic work unit: an edit plus its verification, a\nQA scenario run, a teardown. Keep each step small enough to finish\nwithin a few tool calls.\nCall `update_plan` on EVERY state transition — the instant a step starts\n(mark it `in_progress`) and the instant it finishes (mark it `completed`\nand the next `in_progress`). Exactly ONE `in_progress` at a time. Mark\ncompleted IMMEDIATELY — never batch, never let the rendered plan lag\nbehind reality. Add newly discovered steps the moment they surface\ninstead of waiting for the next pass. Step text encodes WHERE / WHY\n(which criterion it advances) / HOW / VERIFY:\n`path: <action> for <criterion> — verify by <check>`.\n\nGOOD pair (ordered):\n  `test/foo.test.ts: read the validateEmail cases for criterion 2 — verify by noting intent / coverage / pass in the notepad`\n  `src/foo/bar.ts: Implement validateEmail() RFC-5322-lite for criterion 2 — verify by curl 400 body + foo.test.ts green`\nBAD: "Implement feature" / "Fix bug" / "Add tests later" → rewrite.\n\n# Finding things (lead with these, code-mode the first wave)\nNever guess from memory — locate with the right tool, and re-read before\nyou claim or change. **USE CODE MODE AGGRESSIVELY FOR BOUNDED WAVES.**\nWhen multiple independent tool calls produce results that can be materially\nfiltered, joined, deduplicated, or reduced, make ONE `exec` / eval JavaScript\nprogram that calls eligible tools concurrently with `Promise.all` and emits only\ndecision-relevant evidence. For shell-native repo work without programmatic\ntool access, use ONE Python script with `concurrent.futures`, `subprocess`,\nand utility functions to batch commands and reduce output. Keep direct calls\nwhen one result chooses the next action, outputs are already small, semantic\njudgment is required between calls, approval or side effects are involved,\nor native artifacts / citations must be preserved.\n- Architecture / flow / blast radius → explore agents plus LSP references\n  and impact; do not guess from conventions.\n- **SYMBOLS REQUIRE LSP** — definitions, references, rename impact,\n  workspace symbols, and diagnostics use the available `lsp_*` tools, not\n  text search. Run diagnostics after edits and treat errors as blocking.\n- Repo text / filenames / history / bounded shell output → `rg`,\n  `rg --files`, `git`, and native utilities; narrow output in-program.\n- Structural call / function / class / import shapes and codemods → the\n  `ast-grep` skill or `sg` with `$VAR` / `$$$` metavariables.\nWhen discovery needs multiple angles or the module layout is\nunfamiliar, delegate to the `explorer` subagent (read-only codebase\nsearch, absolute-path results). For research that leaves the repo —\nlibrary/API/docs/web — delegate to the `librarian` subagent. Spawn them\n`fork_context: false` and keep doing root work while they run.\n\n# Execution loop (READ → CHANGE → RUN → CLEAN)\nUntil every success criterion PASSES with its evidence captured:\n1. Pick next criterion → mark in_progress → update notepad `## Now`.\n2. READ what already proves the area BEFORE touching it. Existing\n   tests are the behavior of record: note in the notepad whether they\n   encode the intended behavior, cover the path you change, and pass.\n   One WRONG before your change is a FINDING to report — NEVER edit a\n   test green. A bug: reproduce it first and capture the failure. A\n   refactor: the existing tests are green on the unchanged code first.\n3. CHANGE: the SMALLEST production change that meets the criterion;\n   update the tests your change makes stale. Add a test ONLY when\n   BOTH hold: the repository keeps tests for this behavior AND a\n   regression would otherwise pass unnoticed by the run and the\n   existing tests — sized like its neighbors, one case per stated\n   behavior, failing when that behavior breaks. A test that restates\n   the change (a constant, a string, a rename, a call) is NOT evidence;\n   the run is. Coverage-only work (no production change): break the\n   behavior each new assertion names, capture it failing, restore — an\n   assertion that stays green under its mutation is not coverage.\n   PROSE TARGET (prompt, SKILL.md, rule, markdown): the wording is NOT\n   the behavior — pin only a machine-consumed value (parsed field,\n   sentinel a hook greps, a JSON sample through its validator) or one\n   `toBe` equality between shipped copies; otherwise review + QA-by-read,\n   NO test. Before a change that depends on review, PR, issue, or\n   branch state, refresh that state and preserve existing ordering/policy.\n4. RUN: the real-surface scenario the criterion named (channel table\n   above; auxiliary surface for CLI- or data-shaped criteria), end to\n   end, yourself, plus the step-2 tests; a reproduction now passes.\n   Paste the artifact path into the notepad.\n5. CLEANUP (PAIRED — NEVER SKIP): the moment a QA scenario spawns any\n   resource, register its teardown as its own todo (e.g.\n   `cleanup: kill server pid for criterion 2 — verify kill -0 fails`).\n   Every runtime artifact the QA spawned in step 4 MUST be torn down\n   before this step completes:\n   server PIDs (`kill <pid>`; verify `kill -0` fails), `tmux` sessions\n   (`tmux kill-session -t ulw-qa-<criterion>`; verify with `tmux ls`),\n   browsers / sessions (`browser.close()` / `session.stop()`), containers\n   (`docker rm -f`), bound ports (`lsof -i :<port>` empty), temp\n   sockets / files / dirs (`rm -rf` the `mktemp` paths), QA-only env\n   vars. Append a one-line cleanup receipt to the notepad next to the\n   artifact, e.g. `cleanup: killed 12345; tmux kill-session ulw-qa-foo;\n   rm -rf /tmp/ulw.aB12cD`. No receipt → criterion stays in_progress.\n6. Verify: LSP diagnostics clean on changed files + the test scope\n   this criterion touched green (no skipped, no xfail added this\n   turn). Re-run a validation command (suite, typecheck, build) only\n   when its inputs changed since its last green run; ONE full-suite\n   pass belongs immediately before the final message, not after\n   every increment.\n7. Mark completed. Append non-obvious findings / learnings.\n8. After each increment, re-run the scenarios that increment could\n   have affected; re-run the full set once, right before the final\n   message. Record PASS/FAIL inline with the evidence paths AND the\n   cleanup receipt. Loop until all PASS.\n\nWithin a step, follow Finding things; READ before CHANGE, never in\nparallel with it.\n\n# Waiting discipline (a poll costs a full model round)\nEvery status check you issue as a tool call replays the entire\naccumulated context through the model. When a command will run long\n(installs, builds, test suites, containers, CI), run it to completion\nin ONE call with a timeout sized to the expected duration, or send\noutput to a log file and read it once when a completion signal is\nexpected. Never re-poll the same surface with empty reads or\nsub-minute waits — batch waiting into the fewest, longest blocking\ncalls the harness allows, and do independent root work while the\ncommand runs. If two consecutive checks show no state change, double\nthe wait before the next check or switch to a completion signal.\n\n# Codex subagent reliability\nEvery `multi_agent_v1.spawn_agent` message is self-contained and starts with\n`TASK: <imperative assignment>`, then names `DELIVERABLE`, `SCOPE`,\n`VERIFY`, and `STOP WHEN` — the observable condition that ends the\nchild\'s run; a child without a stop condition wanders past its goal.\nState that it is an executable assignment, not a context handoff. Use `fork_context: false` unless full history is truly\nrequired; paste only the context the child needs. Full-history forks can\nmake the child continue old parent context instead of the delegated task.\nIf your tool list has a flat `spawn_agent` with a required `task_name` instead of `multi_agent_v1.*` (`multi_agent_v2`), rewrite: `fork_context: false` becomes `fork_turns: "none"`, `send_input` becomes `send_message`, finished agents end on their own (no `close_agent`; `followup_task` re-tasks, `interrupt_agent` stops), and `wait_agent` takes only `timeout_ms`, returning on any child mailbox activity.\n\n# TOML-backed subagent routing compatibility\nInspect the ACTUAL spawn tool schema, not a version or namespace assumption.\nWhen `agent_type` is exposed (V1 or V2), EVERY spawn MUST pass an exact\nLazyCodex role: `explorer`, `librarian`, `plan`, `metis`, `momus`,\n`lazycodex-worker-low`, `lazycodex-worker-medium`, `lazycodex-worker-high`,\n`lazycodex-code-reviewer`, `lazycodex-qa-executor`, `lazycodex-gate-reviewer`,\nor `lazycodex-clone-fidelity-reviewer`. Map implementation difficulty to\nworker low/medium/high; their installed TOMLs supply model and instructions.\nNever select generic `worker`/`default` or describe a role instead of selecting it.\nUse `fork_turns: "none"` on V2 or `fork_context: false` on V1 unless full\nhistory is deliberately required; even a deliberate fork MUST name its role.\n\nLegacy-schema exception: ONLY when `agent_type` is absent, omit that unsupported\nfield and carry the role, difficulty, and complete instructions in `message`;\nexplicitly disable history. This cannot select a specialized TOML. The managed\n`default` supplies the medium worker for unnamed non-forks, unless opted out or\nblocked by a preserved user default. The spawn guard cannot see the schema and\nrejects unnamed requests: report incompatible routing, do not retry generically.\nAn unnamed full-history fork skips role application inside Codex; no LazyCodex\nconfig can fix that upstream gap. Never claim this path has been repaired.\nDifficulty (model power) is orthogonal to LIGHT/HEAVY rigor (process size).\n\nTreat child status as a progress signal, not a timeout counter. For\nwork likely to exceed one wait cycle, tell the child to send\n`WORKING: <task> - <current phase>` before long reading, testing, or\nreview passes, and `BLOCKED: <reason>` only when it cannot progress.\nTrack spawned agent names locally. Use `multi_agent_v1.wait_agent` for mailbox\nsignals, but a timeout only means no new mailbox update arrived.\nTreat a running child as alive and keep doing independent root work.\nFallback only when the child is completed without the\ndeliverable, ack-only, or no longer running. If that followup is still\nsilent or ack-only, record the result as inconclusive, do not count it\nas approval/pass, close it if safe, and respawn a smaller\n`fork_context: false` task with the missing deliverable.\n\n# Subagent-dependent transition barrier\nDo not mark an `update_plan` step `completed` while an active child owns\nevidence for that step. Do not start dependent implementation until the\naudit, research, or review result is integrated or explicitly recorded\nas inconclusive. Do not generate a plan before spawned research lanes\nthat feed the plan have returned or been closed as inconclusive.\nSpawn every independent child for the current wave first. After the wave\nis launched, run `multi_agent_v1.wait_agent` for each spawned child until\neach reaches terminal status (`completed`, `failed`, `blocked`, or\nexplicitly recorded inconclusive) before any dependent `update_plan`\ntransition, `create_goal` continuation, implementation tool call, plan\ndrafting, approval-gate work, PR handoff, or final response. A timeout is\nnot terminal status.\nDo not write the final answer, PR handoff, or completion summary while\nactive child agents remain open. Use `multi_agent_v1.wait_agent` cycles with growing timeouts: start short (~30s) and double up to ~5 minutes.\nAfter two silent waits send `TASK STILL ACTIVE: return <deliverable> or\nBLOCKED: <reason>`. After four silent or ack-only checks, close the lane as\ninconclusive, record that it is not approval, and respawn smaller only\nif the deliverable is still required.\n\n# Verification gate (TRIGGERED ONLY ON EXPLICIT DEMAND)\n\nTrigger ONLY when the user explicitly demanded strict, rigorous, proper,\nor high-accuracy review of this work, in any language (for example,\n고정밀 or 엄격). The tier alone never triggers the gate. HEAVY without\nsuch a demand records the same self-review as LIGHT.\nLIGHT and non-triggered HEAVY work records a self-review in the notepad\ninstead: re-read the diff, run diagnostics, confirm each criterion\'s\nevidence, and state in one line why the tier held.\n\nWhen triggered, follow this procedure (NON-NEGOTIABLE):\n1. Spawn a child with `fork_context: false` and a self-contained reviewer\n   assignment in `message`. The `multi_agent_v1.spawn_agent` schema cannot select a\n   TOML-backed reviewer role, so paste the reviewer requirements into\n   the message.\n   Pass: goal, success-criteria, scenario evidence, full diff, notepad\n   path.\n2. Verify each reviewer concern yourself. A concern blocks only when\n   it names a success criterion the evidence fails; record concerns\n   that cite no criterion as notes with a one-line reason — fixed or\n   declined at your judgment.\n3. Fix every criterion-cited blocker. Re-run ONLY the scenario QA\n   affected by the fix; capture fresh evidence for the delta. Update\n   notepad.\n4. Re-submit to the SAME reviewer at most twice, passing only the\n   delta diff, the blockers it cited, and the already-approved criteria\n   marked out-of-scope. An approval whose only remaining items are\n   notes counts as approval.\n5. On approval, declare done. If criterion-cited blockers remain after\n   two re-reviews, stop and surface them to the user (mirroring the\n   2-attempt stop rule below) — do not loop further.\n\n# Commits\nCommit frequently: one atomic commit per verified increment (change +\nits evidence), never one end-of-run omnibus; each commit builds +\ntests green on its own; no WIP on the final branch.\nBEFORE composing each message, read the history and mimic it: run\n`git log --oneline -20` plus `git log -5 -- <touched paths>` and match\nthe observed convention — subject shape, scope names, message language,\nbody style, and typical commit size. Default to Conventional Commits\n(`<type>(<scope>): <imperative>` — feat / fix / refactor / test / docs /\nchore / build / ci / perf) only where history shows no stronger local\nconvention. If a plan file exists, final commit footer:\n`Plan: .omo/plans/<slug>.md`. Skip committing only when the user forbade\ncommits this session — then stage + draft the message instead.\n\n# Constraints\n- Every behavior change is PROVEN BY ITS RUN on the real surface, with\n  the tests the repository keeps for it green. A test that cannot fail\n  for the regression it names is NOT evidence: mock-call assertions,\n  pinned constants, a fixture equal to the default it must override,\n  an expected value re-derived from the output under test.\n- Smallest correct change. No drive-by refactors.\n- Never suppress lints / errors / test failures. Never delete, skip,\n  `.only`, `.skip`, `xfail`, or comment out tests to green the suite.\n- Never claim done from inference — only from captured evidence.\n\n# Output discipline\n- First line literally: `ULTRAWORK MODE ENABLED!`\n- After bootstrap: 1-2 paragraph plan summary + notepad path.\n- During execution: at every handoff - todo phase change, blocker,\n  plan change, before a long pass - one handoff block composed after\n  weighing what the user asked and needs to know now:\n  `[Outcome so far] toward [ask + wanted]. You need: [ledger,\n  evidence paths, PASS/FAIL, reviewer verdict]. Now: [todo in\n  progress]. Next: [next open todo].`; nothing between handoffs.\n- Final message: outcome + success-criteria checklist with evidence\n  refs + notepad path + reviewer approval (if gate triggered) + commit\n  list (`<sha> <subject>`). No file-by-file changelog unless asked.\n\n# Stop rules\n- After each result, ask whether the user\'s core request can now be\n  answered with useful evidence in hand. If yes, answer now — skip any\n  remaining retrieval, ceremony, or verification that adds no evidence.\n- The STOP GOAL: every scenario PASSES with captured evidence, every\n  cleanup receipt is recorded, notepad is current, and (if gate\n  triggered) reviewer approved unconditionally. Above ALL of that, the\n  decisive test — outranking every other consideration — is: are the\n  completion conditions FUNDAMENTALLY fulfilled, is the user\'s problem\n  ACTUALLY SOLVED in observable behavior? If no, you are NOT done,\n  whatever the ledger says. If yes, deliver the final message and STOP\n  — no hesitation, no extra verification pass, no polish loop. Work\n  past the stop goal is scope creep, not diligence.\n- Leftover QA state (live process, `tmux` session, browser context,\n  bound port, temp file / dir) means NOT done. Tear it down, record\n  the receipt, then continue.\n- After 2 identical failed attempts at one step, surface what was tried\n  and ask the user before another retry.\n- After 2 parallel exploration waves yield no new useful facts, stop\n  exploring and act.\n\n</ultrawork-mode>\n';

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

@@ -1,3 +1,6 @@
-import { readFileSync } from "node:fs";
+import { ULTRAWORK_DIRECTIVE_TEXT } from "./directive-content.js";
 
-export const ULTRAWORK_DIRECTIVE: string = readFileSync(new URL("../directive.md", import.meta.url), "utf8");
+// Bundled at build time from packages/prompts-core/prompts/ultrawork/codex.md via
+// scripts/sync-directive.mjs. prompts-core's contract is that markdown never gets read from disk
+// at runtime, so the directive ships compiled into dist/cli.js instead of as a sibling .md read.
+export const ULTRAWORK_DIRECTIVE: string = ULTRAWORK_DIRECTIVE_TEXT;

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

@@ -105,7 +105,15 @@ describe("codex ultrawork trigger policy", () => {
 
 		// then
 		expect(outputs).toEqual(["", "", "", "", "", "", ""]);
-		expect(prompts.map((prompt) => isUltraworkPrompt(prompt))).toEqual([false, false, false, false, false, false, false]);
+		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", () => {

package/packages/omo-codex/plugin/components/ultrawork/test/directive-source.test.ts

@@ -1,28 +1,34 @@
 import { readFileSync } from "node:fs";
 import { describe, expect, it } from "vitest";
 
+import { ULTRAWORK_DIRECTIVE } from "../src/directive.js";
+
 describe("codex ultrawork directive source", () => {
-	it("#given bundled directive #when compared to prompts-core codex variant #then bytes match", () => {
+	it("#given the generated bundled directive #when compared to prompts-core codex variant #then bytes match", () => {
 		// given
-		const directive = readFileSync("directive.md", "utf8");
 		const codexPromptUrl = new URL(import.meta.resolve("@oh-my-opencode/prompts-core/prompts/ultrawork/codex.md"));
 
 		// when
 		const codexPrompt = readFileSync(codexPromptUrl, "utf8");
 
 		// then
-		expect(codexPrompt).toBe(directive);
+		// Freshness gate for the checked-in generated artifact: editing the canonical prompt without
+		// re-running scripts/sync-directive.mjs leaves src/directive-content.ts stale and fails here.
+		expect(ULTRAWORK_DIRECTIVE).toBe(codexPrompt);
 	});
 
-	it("#given bundled ultrawork skill #when compared to the directive #then it wraps the same bytes with skill frontmatter", () => {
+	it("#given the runtime directive module #when inspected #then it bundles the constant instead of reading markdown from disk", () => {
 		// given
-		const directive = readFileSync("directive.md", "utf8");
+		const directiveSource = readFileSync(new URL("../src/directive.ts", import.meta.url), "utf8");
 
 		// when
-		const skill = readFileSync("skills/ultrawork/SKILL.md", "utf8");
+		const importsBundledConstant = directiveSource.includes(
+			'import { ULTRAWORK_DIRECTIVE_TEXT } from "./directive-content.js"',
+		);
 
 		// then
-		expect(skill.startsWith("---\nname: ultrawork\n")).toBe(true);
-		expect(skill.endsWith(directive)).toBe(true);
+		// prompts-core's contract: markdown is bundled at build time, never read from disk at runtime.
+		expect(importsBundledConstant).toBe(true);
+		expect(directiveSource).not.toMatch(/readFileSync|readFile\(/);
 	});
 });

package/packages/omo-codex/plugin/components/ultrawork/test/package-smoke.test.ts

@@ -1,3 +1,4 @@
+import { readFileSync } from "node:fs";
 import { describe, expect, it } from "vitest";
 import {
 	collectHookCommandsFromValue,
@@ -7,10 +8,15 @@ import {
 	requireFiles,
 	requireScripts,
 } from "../../test-support/package-smoke-fixture.js";
+import { ULTRAWORK_DIRECTIVE } from "../src/directive.js";
 
 describe("codex ultrawork package metadata", () => {
 	it("#given package metadata #when inspected #then hook ships as bundled CLI", () => {
 		// given
+		const canonicalDirective = readFileSync(
+			new URL(import.meta.resolve("@oh-my-opencode/prompts-core/prompts/ultrawork/codex.md")),
+			"utf8",
+		);
 		const packageJson = readPackageJson("package.json");
 		const hooksJson = readJsonFile("hooks/hooks.json");
 		const cliSource = readTextFile("src/cli.ts");
@@ -30,8 +36,13 @@ describe("codex ultrawork package metadata", () => {
 		);
 		expect(scripts["test"]).toBe("vitest --run");
 		expect(packageFiles).toContain("dist");
-		expect(packageFiles).toContain("directive.md");
 		expect(packageFiles).toContain("skills");
+		// The directive is no longer a published file: it ships compiled into dist/cli.js via the
+		// generated src/directive-content.ts, so assert the bundled contract instead of files-list
+		// membership.
+		expect(packageFiles).not.toContain("directive.md");
+		expect(ULTRAWORK_DIRECTIVE.length).toBeGreaterThan(0);
+		expect(ULTRAWORK_DIRECTIVE).toBe(canonicalDirective);
 		expect(packageFiles).not.toContain("hooks/ultrawork-detector.py");
 		expect(cliSource.startsWith("#!/usr/bin/env node")).toBe(true);
 		expect(hookCommands).toContain(`node "${pluginRoot}/dist/cli.js" hook user-prompt-submit`);

package/packages/omo-codex/plugin/components/{start-work-continuation → ulw-execute-continuation}/AGENTS.md

@@ -33,15 +33,15 @@ Conventions for human contributors and AI agents working on this repository.
 
 - `src/boulder-reader.ts`: reads `.omo/boulder.json`, resolves the active work for the session, re-exports `getPlanChecklist`/`PlanChecklist` from `plan-checklist.ts`. `readContinuationState` returns null in four cases: `boulder.json` is missing or unparseable, no work matches the session, the work status is not continuable (only `active` and `paused` continue - `completed`/`abandoned` stop), or `checklist.total === 0`.
 - `src/plan-checklist.ts`: `PlanChecklist` (`completed`/`remaining`/`total`/`nextTaskLabel`) and `getPlanChecklist`/`parsePlanChecklist`. Counts structured `## TODOs` rows (`N. <title>`) and `## Final Verification Wave` rows (`F<number>. <title>`); falls back to simple top-level `- [ ]`/`- [x]` checkboxes. Skips fenced blocks and respects `#`/`##` section boundaries.
-- `src/codex-hook.ts`: Stop/SubagentStop hook; fills nine placeholders into `directive.md` - `PLAN_NAME`, `PLAN_PATH`, `BOULDER_PATH`, `REMAINING_COUNT`, `TOTAL_COUNT`, `NEXT_TASK_LABEL`, `WORKTREE_BLOCK`, `LEDGER_PATH`, `SESSION_ID`. `WORKTREE_BLOCK` renders empty when the work has no worktree. When `remaining === 0`, `nextTaskLabel` is null and renders as "none (final gate pending)".
+- `src/codex-hook.ts`: Stop hook; fills nine placeholders into `directive.md` - `PLAN_NAME`, `PLAN_PATH`, `BOULDER_PATH`, `REMAINING_COUNT`, `TOTAL_COUNT`, `NEXT_TASK_LABEL`, `WORKTREE_BLOCK`, `LEDGER_PATH`, `SESSION_ID`. `WORKTREE_BLOCK` renders empty when the work has no worktree. When `remaining === 0`, `nextTaskLabel` is null and renders as "none (final gate pending)". SubagentStop is intentionally accepted by the CLI as a no-op for compatibility, but never injects a root plan.
 - **Context-pressure suppression:** the hook reads `input.transcript_path` through the injected `ReadonlyFileSystem` and returns `""` (no continuation) when the transcript carries any context-pressure marker (`context compacted`, `context_length_exceeded`, `context_too_large`, `codex ran out of room in the model's context window`, and related phrasings). This is the safety valve against an infinite continuation loop once the context window is exhausted; it is pinned by a `#given context-window pressure` test.
 - `directive.md`: directive template with placeholders, applied per invocation.
 
 ## Build and Hooks
 
 - Build output goes to `dist/`.
-- `hooks/hooks.json` registers Codex `Stop` and `SubagentStop` hooks.
-- Hook commands run `node ${PLUGIN_ROOT}/components/start-work-continuation/dist/cli.js hook stop` and `node ${PLUGIN_ROOT}/components/start-work-continuation/dist/cli.js hook subagent-stop`.
+- `hooks/hooks.json` registers the Codex `Stop` hook.
+- The hook command runs `node ${PLUGIN_ROOT}/components/ulw-execute-continuation/dist/cli.js hook stop`. The retained `hook subagent-stop` CLI subcommand is a compatibility no-op and is not registered.
 
 ## Constraints
 
@@ -49,5 +49,5 @@ Conventions for human contributors and AI agents working on this repository.
 - Never make a network call from the hook.
 - Keep the directive in `directive.md`. Do not inline it into TypeScript files.
 - The hook only continues sessions listed in `.omo/boulder.json` as `codex:<session_id>`.
-- The hook yields no output when `last_assistant_message` starts with `<start-work-blocked-external>`, or when that marker is the second line immediately after the mandatory `ULTRAWORK MODE ENABLED!` opener, so a conclusive external blocker can end the turn. Reject the marker everywhere else.
+- The hook yields no output when `last_assistant_message` starts with `<ulw-execute-blocked-external>`, or when that marker is the second line immediately after the mandatory `ULTRAWORK MODE ENABLED!` opener, so a conclusive external blocker can end the turn. Reject the marker everywhere else.
 - The hook continues while the plan has a readable top-level checklist (`total > 0`). A fully-checked plan still blocks Stop until the final gate runs and the Boulder work is marked completed; an unreadable or empty checklist yields no output.

package/packages/omo-codex/plugin/components/{start-work-continuation → ulw-execute-continuation}/NOTICE

@@ -1,4 +1,4 @@
-codex-start-work-continuation
+codex-ulw-execute-continuation
 Copyright (c) 2026 Yeongyu Kim
 
 This product includes software released under the MIT License.

package/packages/omo-codex/plugin/components/{start-work-continuation → ulw-execute-continuation}/README.md

@@ -1,6 +1,6 @@
-# codex-start-work-continuation
+# codex-ulw-execute-continuation
 
-Codex Stop-hook continuation injector for the omo-codex `start-work` skill.
+Codex Stop-hook continuation injector for the omo-codex `ulw-execute` skill.
 
 It reads `.omo/boulder.json` in the hook payload `cwd`, resolves the active work, inspects the active plan's top-level checklist, and emits Codex Stop-hook JSON while the plan still has unchecked tasks or its final review/debugging gate remains pending:
 
@@ -8,13 +8,13 @@ It reads `.omo/boulder.json` in the hook payload `cwd`, resolves the active work
 {"decision":"block","reason":"<directive>"}
 ```
 
-The `reason` is loaded from `directive.md` on every invocation and filled with current plan state. The hook returns no output when `stop_hook_active` is `true`, when `last_assistant_message` starts with `<start-work-blocked-external>` (or places it immediately after the mandatory `ULTRAWORK MODE ENABLED!` opener), when no active Boulder work exists, when the work is completed, when the active work is not tied to `codex:<session_id>`, or when the plan has no readable top-level checklist. An active plan whose checklist is fully checked still blocks Stop until the final gate runs and Boulder is marked completed.
+The `reason` is loaded from `directive.md` on every invocation and filled with current plan state. The hook returns no output when `stop_hook_active` is `true`, when `last_assistant_message` starts with `<ulw-execute-blocked-external>` (or places it immediately after the mandatory `ULTRAWORK MODE ENABLED!` opener), when no active Boulder work exists, when the work is completed, when the active work is not tied to `codex:<session_id>`, or when the plan has no readable top-level checklist. An active plan whose checklist is fully checked still blocks Stop until the final gate runs and Boulder is marked completed. SubagentStop is deliberately de-wired: the compatibility CLI subcommand returns no output and never injects a root plan.
 
 ## External blocker escape hatch
 
-A plan can stall on something no amount of retrying fixes: a missing credential, missing hardware, a revoked authorization, an unavailable third-party service. `directive.md` instructs the agent to write `<start-work-blocked-external>` as the entire first line of its answer in that case, or as the entire second line when ultrawork's mandatory opener occupies the first. The hook recognizes those structural forms and lets the turn end so the user can act, instead of continuing the same unchanged external-state check forever. Merely discussing the marker later in an answer still continues the plan.
+A plan can stall on something no amount of retrying fixes: a missing credential, missing hardware, a revoked authorization, an unavailable third-party service. `directive.md` instructs the agent to write `<ulw-execute-blocked-external>` as the entire first line of its answer in that case, or as the entire second line when ultrawork's mandatory opener occupies the first. The hook recognizes those structural forms and lets the turn end so the user can act, instead of continuing the same unchanged external-state check forever. Merely discussing the marker later in an answer still continues the plan.
 
-This pairs with the `start-work` skill at `plugin/skills/start-work/SKILL.md`. That skill writes `.omo/boulder.json` with Codex session ids prefixed as `codex:` so the hook can continue only its own active Codex session.
+This pairs with the `ulw-execute` skill at `plugin/skills/ulw-execute/SKILL.md`. That skill writes `.omo/boulder.json` with Codex session ids prefixed as `codex:` so the hook can continue only its own active Codex session. The continuation gate performs self-review and own manual QA by default; it escalates to one gate reviewer only when the user explicitly demands strict, rigorous, or high-accuracy review.
 
 ## Counted plan checkboxes
 
@@ -48,7 +48,7 @@ echo "$PAYLOAD_LOOP" | node dist/cli.js hook stop
 rm -rf "$TMP"
 ```
 
-Expect the first command to print JSON containing `"decision":"block"`; expect the anti-loop command to print nothing.
+Expect the first command to print JSON containing `"decision":"block"`; expect the anti-loop command to print nothing. A `SubagentStop` payload passed to `hook subagent-stop` also prints nothing.
 
 ## License
 

package/packages/omo-codex/plugin/components/{start-work-continuation → ulw-execute-continuation}/biome.json

@@ -1,9 +1,9 @@
 {
-	"$schema": "https://biomejs.dev/schemas/2.4.15/schema.json",
+	"$schema": "https://biomejs.dev/schemas/2.5.9/schema.json",
 	"linter": {
 		"enabled": true,
 		"rules": {
-			"recommended": true,
+			"preset": "recommended",
 			"style": {
 				"noDefaultExport": "error",
 				"noEnum": "error",

package/packages/omo-codex/plugin/components/{start-work-continuation → ulw-execute-continuation}/directive.md

@@ -1,4 +1,4 @@
-<start-work-continuation>
+<ulw-execute-continuation>
 
 You are mid-flight on a Prometheus work plan; this turn is an automatic continuation. Do NOT ask whether to continue — the contract is auto-continue until every top-level checkbox is `- [x]`.
 
@@ -17,22 +17,22 @@ You are mid-flight on a Prometheus work plan; this turn is an automatic continua
 
 1. Read `{{PLAN_PATH}}` AND `{{LEDGER_PATH}}` first — they are the only sources of truth for what remains and what evidence exists; do not trust your memory of prior turns.
 2. When the remaining count is `0`, skip checkbox execution and perform the Final gate now. Otherwise, pick the FIRST unchecked top-level checkbox in `## TODOs` or `## Final Verification Wave`. Ignore nested checkboxes under Acceptance Criteria / Evidence / Definition of Done.
-3. Follow the `start-work` skill in full. The skill is already loaded from your earlier turn — re-read its file at `packages/omo-codex/plugin/skills/start-work/SKILL.md` if you have lost context.
-4. Apply the checkbox's tier from its ledger entry, or classify it now per the start-work skill: LIGHT (default — a narrow change inside existing layers) needs one real-surface proof of the deliverable, with auxiliary surfaces first-class for CLI- or data-shaped work, and only trigger-mapped adversarial classes; HEAVY (new module/abstraction, auth/security, external integration, schema/migration, concurrency, cross-domain refactor, care signals) takes the full per-criterion regime. When unsure, take HEAVY; never downgrade.
+3. Follow the `ulw-execute` skill in full. The skill is already loaded from your earlier turn — re-read its file at `packages/omo-codex/plugin/skills/ulw-execute/SKILL.md` if you have lost context.
+4. Apply the checkbox's tier from its ledger entry, or classify it now per the ulw-execute skill: LIGHT (default — a narrow change inside existing layers) needs one real-surface proof of the deliverable, with auxiliary surfaces first-class for CLI- or data-shaped work, and only trigger-mapped adversarial classes; HEAVY (new module/abstraction, auth/security, external integration, schema/migration, concurrency, cross-domain refactor, care signals) takes the full per-criterion regime. When unsure, take HEAVY; never downgrade.
 5. Decompose the checkbox into atomic sub-tasks. Dispatch them in PARALLEL via `multi_agent_v1.spawn_agent` calls in this same response unless a sub-task has a NAMED blocking dependency (input from another sub-task or shared file). Use `fork_context: false` unless full history is truly required. Put role and specialty instructions inside `message`. Flat `spawn_agent` requiring `task_name` instead (`multi_agent_v2`)? Add `"task_name"`, use `fork_turns: "none"`, `wait_agent` takes only `timeout_ms`, finished agents end on their own.
-6. Every sub-task message MUST be self-contained, executable, not a context handoff: start with `TASK: <imperative assignment>`, then name `DELIVERABLE`, `SCOPE`, and `VERIFY`. It must include all 7 sections and a Manual-QA channel with exact invocation (`curl`, `send-keys`, `browser:control-in-app-browser` action, `page.click`) and PASS/FAIL observable, plus ultraqa classes, artifact, and cleanup receipt. Channels: HTTP (`curl -i`); terminal/TUI (`send-keys` for boot smoke; xterm.js web terminal for color/visual evidence, never `tmux capture-pane`); browser (Codex: `browser:control-in-app-browser` first unless auth/persistent profile needed; else Chrome/agent-browser); computer use.
-7. Treat every worker DoneClaim as untrusted input. Run independent AdversarialVerify before any checkbox can become FullyDone; `confirmed` is the only pass verdict, while `false-positive`, `needs-fix`, and `needs-human-review` loop back to the executor with exact feedback.
+6. Every sub-task message MUST be self-contained, executable, not a context handoff: start with `TASK: <imperative assignment>`, then name `DELIVERABLE`, `SCOPE`, and `VERIFY`. It must include all 7 sections and a Manual-QA channel with exact invocation (`curl`, `send-keys`, `browser:control-in-app-browser` action, `page.click`) and PASS/FAIL observable, plus ultraqa classes, artifact, and cleanup receipt. Channels: HTTP (`curl -i`); terminal/TUI (`send-keys` for boot smoke; xterm.js web terminal for color/visual evidence, never `tmux capture-pane`); browser (Codex: `browser:control-in-app-browser`; otherwise omowright from js eval — `connectPipe`/`connectCloakProfile` for a browser you own, `connectBrowserSkill()` for the user's signed-in browser, never a clone of the live profile); computer use.
+7. Treat every worker DoneClaim as untrusted input. Run independent AdversarialVerify before any checkbox can become FullyDone; the main session may run AdversarialVerify when no separate reviewer is available. `confirmed` is the only pass verdict, while `false-positive`, `needs-fix`, and `needs-human-review` loop back to the executor with exact feedback.
 8. Use `multi_agent_v1.wait_agent` for mailbox signals, not proof of completion — a timeout only means no new mailbox update arrived; a running child is alive. For sub-tasks likely to exceed one wait cycle, require `WORKING: <task> - <current phase>` before long passes and `BLOCKED: <reason>` only when progress stops. Send `TASK STILL ACTIVE: return <deliverable> or BLOCKED: <reason>` only when the child is completed without the deliverable, ack-only, or no longer running. If that followup is still silent or ack-only, record inconclusive, do not count it as pass/review approval, close if safe, and respawn a smaller `fork_context: false` task with the missing deliverable.
 9. After verification of ALL sub-tasks under this checkbox: `apply_patch` the plan to change `- [ ]` → `- [x]`, re-read the plan to confirm the count decreased, append a `task-completed` line to the ledger, then continue.
 10. Do not start fresh on a sub-agent failure. Re-dispatch with a fix-message: `FAILED: <exact error>` + `Diagnosis: <observation>` + `Fix: <instruction>`.
 
 # Hard constraints
 
-- No production code before a failing-first proof exists: a unit test at a seam, otherwise the sub-task's Manual-QA scenario captured failing. A test that mirrors its implementation (mock-call assertions, pinned constants) is not evidence. When the change touches existing behavior, PIN it first: a baseline characterization test that passes on the unchanged code, with exact inputs, exact observable, and exact assertion. PIN → RED → GREEN → SURFACE.
+- No production code before the tests covering that behavior were READ (the behavior of record: intent, coverage, pass; one wrong before the change is a FINDING, never edited green) and a bug's reproduction captured. The run and the Manual-QA scenario prove the change; a new test ONLY where the repository keeps tests for this behavior AND a regression would otherwise pass unnoticed. A test that mirrors its implementation (mock-call assertions, pinned constants) or restates the change is not evidence. READ → CHANGE → RUN → SURFACE.
 - No `--dry-run` as evidence. No "should work". No "tests pass" as completion proof.
 - TUI visual evidence MUST render through the real xterm.js web terminal, never `tmux capture-pane`: run `node script/qa/web-terminal-visual-qa.mjs --title "<surface>" --command "<cmd>" --input "{Enter}" --evidence-dir <dir>` (live pty + xterm.js in Chrome; `--from-file <capture>` replays a raw stream), then cite `terminal.png`, `terminal.txt`, and `metadata.json`.
 - No `as any` / `@ts-ignore` / `@ts-expect-error`. No deleting failing tests.
-- Probe every ultraqa adversarial class whose trigger fact holds (malformed input, prompt injection, cancel/resume, stale state, dirty worktree, hung or long commands, flaky tests, misleading success output, repeated interruptions — trigger map in the start-work skill) and capture the observable for each. A clean happy-path artifact alone is NOT a PASS when an applicable class went unprobed; record skipped classes with a one-line not-applicable reason.
+- Probe every ultraqa adversarial class whose trigger fact holds (malformed input, prompt injection, cancel/resume, stale state, dirty worktree, hung or long commands, flaky tests, misleading success output, repeated interruptions — trigger map in the ulw-execute skill) and capture the observable for each. A clean happy-path artifact alone is NOT a PASS when an applicable class went unprobed; record skipped classes with a one-line not-applicable reason.
 - Cleanup receipt is mandatory. Register each QA teardown (scripts, tmux, browser contexts, PIDs, ports, containers, temp dirs) as a todo when it spawns, then execute it. Leftover QA state = BLOCKED, not PASS.
 - The worktree path (if set in boulder.json) governs every file edit and command. Do not stray into the main repo.
 - PR or branch implementation/review/merge work requires a task-owned git worktree. Treat the main worktree as read-only context.
@@ -40,21 +40,21 @@ 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. 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.
+Before completion, run your own manual QA on the real surface and a self-review against every acceptance criterion; spawn ONE gate reviewer only when the user demanded strict/rigorous/high-accuracy review; run a `debugging` runtime audit only when a failure was observed. Record the observable evidence under `{{LEDGER_PATH}}`; when a reviewer is spawned, it is allowed at most once per sub-task. 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
 
 - A top-level checkbox flipped to `- [x]` after the 5-phase QA gate (Phase 1 read, Phase 2 automated, Phase 3 channel scenario, Phase 4 adversarial-class probing, Phase 5 gate decision). Then the Stop hook will re-evaluate; if more checkboxes remain you will be continued again.
-- A conclusive external blocker only the user or external state can clear (missing hardware, credential, authorization, or an unavailable service) → after ONE authoritative check, stop retrying and stop reviewer dispatch. Write `<start-work-blocked-external>` as the entire first line of your answer, then state the exact blocker and the observable condition that resumes the work. If ultrawork requires `ULTRAWORK MODE ENABLED!` as the first line, put the blocker marker alone on the second line instead. The Stop hook recognizes both forms and lets this turn end.
-- 3 same-failure cycles on one agent-controllable sub-task → escalate via `multi_agent_v1.spawn_agent({"message":"TASK: act as a rigorous reviewer. DELIVERABLE: diagnose the repeated sub-task failure and recommend the next safe action. VERIFY: cite the failing evidence.","fork_context":false})` and stop dispatch.
+- A conclusive external blocker only the user or external state can clear (missing hardware, credential, authorization, or an unavailable service) → after ONE authoritative check, stop retrying and stop reviewer dispatch. Write `<ulw-execute-blocked-external>` as the entire first line of your answer, then state the exact blocker and the observable condition that resumes the work. If ultrawork requires `ULTRAWORK MODE ENABLED!` as the first line, put the blocker marker alone on the second line instead. The Stop hook recognizes both forms and lets this turn end.
+- 3 materially different failed remediation approaches on one agent-controllable sub-task → spawn ONE rigorous reviewer at most once per sub-task; if still blocked, hand off with the external-blocker marker at `:48`.
 - Safety boundary (destructive command, secret exfiltration, production write) → stop and surface a safe substitute.
-- All top-level checkboxes `- [x]` AND the Global Review and Debugging Gate passed → print the ORCHESTRATION COMPLETE block and end.
+- All top-level checkboxes `- [x]` AND the Final gate passed → print the ORCHESTRATION COMPLETE block and end.
 
 # Output discipline
 
-- Surface only state changes: sub-agent dispatched, scenario PASS/FAIL with artifact path, checkbox marked, evidence appended.
+- At every handoff - checkbox marked, blocker, plan change, before a long pass - open with one block composed after weighing what the user asked and needs to know now: `[Outcome so far] toward [ask + wanted]. You need: [sub-agents dispatched, scenario PASS/FAIL with artifact path, checkbox marked, evidence appended]. Now: [checkbox in progress]. Next: [next open checkbox].`; nothing between handoffs.
 - Do NOT print "Should I continue?", restate the plan, or recap prior turns — the Stop hook continues you; the ledger and plan are the durable record.
 
 Begin now. If no checkbox remains, run the Final gate; otherwise pick the next checkbox, dispatch the parallel sub-agents, verify, mark, continue.
 
-</start-work-continuation>
+</ulw-execute-continuation>

package/packages/omo-codex/plugin/components/{start-work-continuation → ulw-execute-continuation}/dist/cli.js

@@ -1,14 +1,14 @@
 #!/usr/bin/env node
 
-// components/start-work-continuation/src/cli.ts
+// components/ulw-execute-continuation/src/cli.ts
 import { readFileSync as readFileSync4 } from "node:fs";
 import { stdin as processStdin, stdout as processStdout } from "node:process";
 
-// components/start-work-continuation/src/boulder-reader.ts
+// components/ulw-execute-continuation/src/boulder-reader.ts
 import { existsSync as existsSync2, readFileSync as readFileSync2 } from "node:fs";
 import { isAbsolute, join, relative, resolve } from "node:path";
 
-// components/start-work-continuation/src/plan-checklist.ts
+// components/ulw-execute-continuation/src/plan-checklist.ts
 import { existsSync, readFileSync } from "node:fs";
 var TODO_HEADING_PATTERN = /^##[ \t]+TODOs(?:[ \t]+#+)?[ \t]*$/i;
 var FINAL_VERIFICATION_HEADING_PATTERN = /^##[ \t]+Final Verification Wave(?:[ \t]+#+)?[ \t]*$/i;
@@ -153,7 +153,7 @@ function emptyChecklist() {
   return { completed: 0, remaining: 0, total: 0, nextTaskLabel: null };
 }
 
-// components/start-work-continuation/src/boulder-reader.ts
+// components/ulw-execute-continuation/src/boulder-reader.ts
 var SESSION_ID_PREFIX_PATTERN = /^(codex|opencode):/;
 function readContinuationState(cwd, sessionId) {
   const boulderPath = getBoulderFilePath(cwd);
@@ -171,7 +171,7 @@ function readContinuationState(cwd, sessionId) {
     planName: work.planName,
     planPath,
     boulderPath,
-    ledgerPath: join(cwd, ".omo", "start-work", "ledger.jsonl"),
+    ledgerPath: join(cwd, ".omo", "ulw-execute", "ledger.jsonl"),
     worktreePath: work.worktreePath ?? null,
     checklist
   };
@@ -297,11 +297,11 @@ function isRecord(value) {
   return typeof value === "object" && value !== null && !Array.isArray(value);
 }
 
-// components/start-work-continuation/src/directive.ts
+// components/ulw-execute-continuation/src/directive.ts
 import { readFileSync as readFileSync3 } from "node:fs";
-var START_WORK_CONTINUATION_DIRECTIVE = readFileSync3(new URL("../directive.md", import.meta.url), "utf8");
+var ULW_EXECUTE_CONTINUATION_DIRECTIVE = readFileSync3(new URL("../directive.md", import.meta.url), "utf8");
 
-// components/start-work-continuation/src/codex-hook.ts
+// components/ulw-execute-continuation/src/codex-hook.ts
 function runStopHook(input, fs) {
   if (!isStopInput(input))
     return "";
@@ -333,13 +333,13 @@ function renderDirective(state, sessionId) {
     LEDGER_PATH: state.ledgerPath,
     SESSION_ID: sessionId
   };
-  let rendered = START_WORK_CONTINUATION_DIRECTIVE;
+  let rendered = ULW_EXECUTE_CONTINUATION_DIRECTIVE;
   for (const [placeholder, value] of Object.entries(replacements)) {
     rendered = rendered.replaceAll(`{{${placeholder}}}`, value);
   }
   return rendered;
 }
-var EXTERNAL_BLOCKER_MARKER = "<start-work-blocked-external>";
+var EXTERNAL_BLOCKER_MARKER = "<ulw-execute-blocked-external>";
 var ULTRAWORK_OPENER = "ULTRAWORK MODE ENABLED!";
 function hasAllowedExternalBlockerMarker(lastAssistantMessage) {
   if (lastAssistantMessage === undefined)
@@ -378,7 +378,7 @@ function isStopInput(value) {
   return isRecord2(value) && isStopHookEventName(value["hook_event_name"]) && typeof value["session_id"] === "string" && typeof value["turn_id"] === "string" && typeof value["transcript_path"] === "string" && typeof value["cwd"] === "string" && typeof value["model"] === "string" && typeof value["permission_mode"] === "string" && typeof value["stop_hook_active"] === "boolean" && optionalString(value["last_assistant_message"]);
 }
 function isStopHookEventName(value) {
-  return value === "Stop" || value === "SubagentStop";
+  return value === "Stop";
 }
 function optionalString(value) {
   return value === undefined || typeof value === "string";
@@ -387,7 +387,7 @@ function isRecord2(value) {
   return typeof value === "object" && value !== null && !Array.isArray(value);
 }
 
-// components/start-work-continuation/src/cli.ts
+// components/ulw-execute-continuation/src/cli.ts
 var nodeFileSystem = {
   readFileSync(path, encoding) {
     return readFileSync4(path, encoding);
@@ -398,7 +398,7 @@ var subcommand = process.argv[3];
 if (command === "hook" && (subcommand === "stop" || subcommand === "subagent-stop")) {
   await runHookCli();
 } else {
-  process.stderr.write(`Usage: omo-start-work-continuation hook <stop|subagent-stop>
+  process.stderr.write(`Usage: omo-ulw-execute-continuation hook <stop|subagent-stop>
 `);
   process.exitCode = 1;
 }
@@ -422,13 +422,13 @@ function parseHookInput(raw) {
   }
 }
 function readStdin() {
-  return new Promise((resolve2) => {
+  return new Promise((resolve) => {
     let data = "";
     processStdin.setEncoding("utf8");
     processStdin.on("data", (chunk) => {
       data += chunk;
     });
-    processStdin.once("error", () => resolve2(data));
-    processStdin.once("end", () => resolve2(data));
+    processStdin.once("error", () => resolve(data));
+    processStdin.once("end", () => resolve(data));
   });
 }

package/packages/omo-codex/plugin/components/ulw-execute-continuation/hooks/hooks.json

@@ -0,0 +1,16 @@
+{
+	"hooks": {
+		"Stop": [
+			{
+				"hooks": [
+					{
+						"type": "command",
+						"command": "node \"${PLUGIN_ROOT}/components/ulw-execute-continuation/dist/cli.js\" hook stop",
+						"timeout": 10,
+						"statusMessage": "(OmO 5.0.0) Checking Ulw-Execute Continuation"
+					}
+				]
+			}
+		]
+	}
+}

package/packages/omo-codex/plugin/components/{start-work-continuation → ulw-execute-continuation}/package.json

@@ -1,28 +1,28 @@
 {
-	"name": "@code-yeongyu/codex-start-work-continuation",
-	"version": "5.0.0-beta.9",
-	"description": "Codex Stop hook continuation injector for omo-codex start-work plans.",
+	"name": "@code-yeongyu/codex-ulw-execute-continuation",
+	"version": "5.0.0",
+	"description": "Codex Stop hook continuation injector for omo-codex ulw-execute plans.",
 	"type": "module",
 	"packageManager": "npm@11.12.1",
 	"license": "MIT",
-	"homepage": "https://github.com/code-yeongyu/codex-start-work-continuation",
+	"homepage": "https://github.com/code-yeongyu/codex-ulw-execute-continuation",
 	"repository": {
 		"type": "git",
-		"url": "git+https://github.com/code-yeongyu/codex-start-work-continuation.git"
+		"url": "git+https://github.com/code-yeongyu/codex-ulw-execute-continuation.git"
 	},
 	"bugs": {
-		"url": "https://github.com/code-yeongyu/codex-start-work-continuation/issues"
+		"url": "https://github.com/code-yeongyu/codex-ulw-execute-continuation/issues"
 	},
 	"keywords": [
 		"codex",
 		"codex-plugin",
-		"start-work",
+		"ulw-execute",
 		"continuation",
 		"hooks",
 		"boulder"
 	],
 	"bin": {
-		"omo-start-work-continuation": "./dist/cli.js"
+		"omo-ulw-execute-continuation": "./dist/cli.js"
 	},
 	"scripts": {
 		"build": "node -e \"require('node:fs').rmSync('dist',{recursive:true,force:true})\" && bun build src/cli.ts --target node --format esm --outfile dist/cli.js",
@@ -42,10 +42,11 @@
 		"NOTICE"
 	],
 	"devDependencies": {
-		"@biomejs/biome": "2.4.16",
-		"@types/node": "^25.9.3",
-		"typescript": "^6.0.3",
-		"vitest": "^4.1.8"
+		"@vitest/coverage-v8": "5.0.1",
+		"@biomejs/biome": "2.5.14",
+		"@types/node": "^26.6.2",
+		"typescript": "^7.0.2",
+		"vitest": "5.0.1"
 	},
 	"engines": {
 		"node": ">=20.0.0"

package/packages/omo-codex/plugin/components/{start-work-continuation → ulw-execute-continuation}/src/boulder-reader.ts

@@ -50,7 +50,7 @@ export function readContinuationState(cwd: string, sessionId: string): Continuat
 		planName: work.planName,
 		planPath,
 		boulderPath,
-		ledgerPath: join(cwd, ".omo", "start-work", "ledger.jsonl"),
+		ledgerPath: join(cwd, ".omo", "ulw-execute", "ledger.jsonl"),
 		worktreePath: work.worktreePath ?? null,
 		checklist,
 	};

package/packages/omo-codex/plugin/components/{start-work-continuation → ulw-execute-continuation}/src/cli.ts

@@ -17,7 +17,7 @@ const subcommand = process.argv[3];
 if (command === "hook" && (subcommand === "stop" || subcommand === "subagent-stop")) {
 	await runHookCli();
 } else {
-	process.stderr.write("Usage: omo-start-work-continuation hook <stop|subagent-stop>\n");
+	process.stderr.write("Usage: omo-ulw-execute-continuation hook <stop|subagent-stop>\n");
 	process.exitCode = 1;
 }
 

package/packages/omo-codex/plugin/components/{start-work-continuation → ulw-execute-continuation}/src/codex-hook.ts

@@ -1,6 +1,6 @@
 import type { ContinuationState } from "./boulder-reader.js";
 import { readContinuationState } from "./boulder-reader.js";
-import { START_WORK_CONTINUATION_DIRECTIVE } from "./directive.js";
+import { ULW_EXECUTE_CONTINUATION_DIRECTIVE } from "./directive.js";
 import type { ReadonlyFileSystem, StopHookEventName, StopHookOutput, StopInput } from "./types.js";
 
 export function runStopHook(input: unknown, fs: ReadonlyFileSystem): string {
@@ -33,14 +33,14 @@ function renderDirective(state: ContinuationState, sessionId: string): string {
 		LEDGER_PATH: state.ledgerPath,
 		SESSION_ID: sessionId,
 	} as const;
-	let rendered = START_WORK_CONTINUATION_DIRECTIVE;
+	let rendered = ULW_EXECUTE_CONTINUATION_DIRECTIVE;
 	for (const [placeholder, value] of Object.entries(replacements)) {
 		rendered = rendered.replaceAll(`{{${placeholder}}}`, value);
 	}
 	return rendered;
 }
 
-const EXTERNAL_BLOCKER_MARKER = "<start-work-blocked-external>";
+const EXTERNAL_BLOCKER_MARKER = "<ulw-execute-blocked-external>";
 const ULTRAWORK_OPENER = "ULTRAWORK MODE ENABLED!";
 
 // The marker alone is not enough to end the turn. `directive.md` requires the exact blocker and
@@ -96,7 +96,7 @@ function isStopInput(value: unknown): value is StopInput {
 }
 
 function isStopHookEventName(value: unknown): value is StopHookEventName {
-	return value === "Stop" || value === "SubagentStop";
+	return value === "Stop";
 }
 
 function optionalString(value: unknown): boolean {

package/packages/omo-codex/plugin/components/{start-work-continuation → ulw-execute-continuation}/src/directive.ts

@@ -1,6 +1,6 @@
 import { readFileSync } from "node:fs";
 
-export const START_WORK_CONTINUATION_DIRECTIVE: string = readFileSync(
+export const ULW_EXECUTE_CONTINUATION_DIRECTIVE: string = readFileSync(
 	new URL("../directive.md", import.meta.url),
 	"utf8",
 );

package/packages/omo-codex/plugin/components/{start-work-continuation → ulw-execute-continuation}/src/index.ts

@@ -1,5 +1,5 @@
 export type { ContinuationState, PlanChecklist } from "./boulder-reader.js";
 export { readContinuationState } from "./boulder-reader.js";
 export { runStopHook } from "./codex-hook.js";
-export { START_WORK_CONTINUATION_DIRECTIVE } from "./directive.js";
+export { ULW_EXECUTE_CONTINUATION_DIRECTIVE } from "./directive.js";
 export type { ReadonlyFileSystem, StopHookEventName, StopHookOutput, StopInput } from "./types.js";