lazycodex-ai 5.0.0-beta.9 → 5.0.0

package/packages/omo-codex/plugin/skills/ulw-research/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: ulw-research
-description: "Maximum-saturation research orchestration: ALWAYS proposes the final materials first (PDF+DOCX default), then parallel explore+librarian swarms across codebase, web, official docs, and OSS repos — max-roster teammode when the harness has it — with live journaling, a recursive EXPAND loop driven by leads workers return in message text, empirical verification by running code, and a cited synthesis with charts/Mermaid/assets behind a mandatory visual-QA gate. ACTIVATES ONLY on an explicit user demand for research — the word 'ulw-research' ('/ulw-research', '$ulw-research'), any 'ulw' research wording, 'ultradebate' or 'hyperdebate' research requests, or an explicit request for research / deep research / an ultra-precise investigation, in any language. Never self-activates for ordinary questions, debugging, or implementation context-gathering. While active it overrides exploration-bounding defaults: exhaustive coverage is the goal."
+description: "Runs maximum-saturation research with a cooperating team, claim-graph gating, and a cited, QA'd deliverable. Use when the user explicitly asks for research or a deep investigation, including any 'ulw' research wording."
 ---
 
 ## Codex Harness Tool Compatibility
@@ -12,17 +12,19 @@ This skill may include examples copied from the OpenCode harness. In Codex, do n
 | `call_omo_agent(subagent_type="explore", ...)` | `multi_agent_v1.spawn_agent({"message":"TASK: act as an explorer. ...","agent_type":"explorer","fork_context":false})` |
 | `call_omo_agent(subagent_type="librarian", ...)` | `multi_agent_v1.spawn_agent({"message":"TASK: act as a librarian. ...","agent_type":"librarian","fork_context":false})` |
 | `task(subagent_type="plan", ...)` | `multi_agent_v1.spawn_agent({"message":"TASK: act as a planning agent. ...","agent_type":"plan","fork_context":false})` |
-| `task(subagent_type="oracle", ...)` for final verification | `multi_agent_v1.spawn_agent({"message":"TASK: act as a rigorous reviewer. ...","agent_type":"lazycodex-gate-reviewer","fork_context":false})` |
-| `task(category="...", ...)` for implementation or QA | `multi_agent_v1.spawn_agent({"message":"TASK: act as an implementation or QA worker. ...","fork_context":false})` |
+| `task(subagent_type="oracle", ...)` for final verification | By default, record a self-review in the notepad: re-read the diff, run diagnostics, and capture evidence for every acceptance criterion. Only when the user demanded strict, rigorous, or high-accuracy review, use `multi_agent_v1.spawn_agent({"message":"TASK: act as a rigorous reviewer. ...","agent_type":"lazycodex-gate-reviewer","fork_context":false})`; include `fork_context: false`. |
+| `task(category="...", ...)` for implementation or QA | `multi_agent_v1.spawn_agent({"message":"TASK: act as an implementation or QA worker. ...","agent_type":"lazycodex-worker-medium","fork_context":false})` |
 | `background_output(task_id="...")` | `multi_agent_v1.wait_agent(...)` for mailbox signals |
 | `team_*(...)` | Use Codex native subagents via `multi_agent_v1.spawn_agent` and `multi_agent_v1.wait_agent`; use `multi_agent_v1.send_input` and `multi_agent_v1.close_agent` only when exposed in the active tools list |
 
-Role-specific behavior must be described in a self-contained `message`. Use `fork_context: false` to start the child with only the initial prompt (no parent history); use `fork_context: true` only when full parent history is truly required. Include any required conversation context, files, diffs, constraints, and requested skill names directly in the spawned agent's `message`. OMO installs these selectable agent roles into `~/.codex/agents/`: `explorer`, `librarian`, `plan`, `momus`, `metis`, `lazycodex-code-reviewer`, `lazycodex-qa-executor`, and `lazycodex-gate-reviewer` - pass the matching name as `agent_type` so the child gets that role's model and instructions. If the spawn tool exposes no `agent_type` parameter, omit it and describe the role inside `message`. If a code block below conflicts with this section, this section wins.
+Role-specific behavior must be described in a self-contained `message`. Use `fork_context: false` to start the child with only the initial prompt (no parent history); use `fork_context: true` only when full parent history is truly required. Include any required conversation context, files, diffs, constraints, and requested skill names directly in the spawned agent's `message`. OMO installs these selectable agent roles into `~/.codex/agents/`: `explorer`, `librarian`, `plan`, `momus`, `metis`, `lazycodex-code-reviewer`, `lazycodex-qa-executor`, and `lazycodex-gate-reviewer` - pass the matching name as `agent_type` so the child gets that role's model and instructions. Inspect the actual spawn schema: whenever `agent_type` is exposed, EVERY spawn MUST select an exact LazyCodex role, on V1 or V2. Implementation difficulty selects `lazycodex-worker-low`, `lazycodex-worker-medium`, or `lazycodex-worker-high`; clone QA can select `lazycodex-clone-fidelity-reviewer`. Never select generic `worker` or `default`. If a code block below conflicts with this section, this section wins.
 
-Codex exposes ONE of two subagent tool surfaces per session; check your own tool list and route accordingly. If `multi_agent_v1.*` tools exist, use the table above as written. If instead a flat `spawn_agent` with a required `task_name` exists (`multi_agent_v2`), rewrite every `multi_agent_v1.*` example: `multi_agent_v1.spawn_agent({...,"fork_context":false})` becomes `spawn_agent({"task_name":"<lowercase_digits_underscores>","message":...,"agent_type":...,"fork_turns":"none"})` (`"all"` only when full parent history is truly required); `send_input` becomes `send_message`; do not call `close_agent`/`resume_agent` (finished agents end on their own; `followup_task` re-tasks one, `interrupt_agent` stops one); `wait_agent` takes only `timeout_ms` and returns on any child mailbox activity. On the v2 surface `agent_type` may be ABSENT from the spawn schema (verified 2026-07-11: only `fork_turns`/`message`/`task_name`) — when absent, omit it and describe the role inside `message`; installed role TOMLs cannot be selected on that surface. If a code block below conflicts with this section, this section wins.
+Codex exposes ONE of two subagent tool surfaces per session; check your own tool list and route accordingly. If `multi_agent_v1.*` tools exist, use the table above as written. If instead a flat `spawn_agent` with a required `task_name` exists (`multi_agent_v2`), rewrite every `multi_agent_v1.*` example: `multi_agent_v1.spawn_agent({...,"fork_context":false})` becomes `spawn_agent({"task_name":"<lowercase_digits_underscores>","message":...,"agent_type":...,"fork_turns":"none"})` (`"all"` only when full parent history is truly required); `send_input` becomes `send_message`; do not call `close_agent`/`resume_agent` (finished agents end on their own; `followup_task` re-tasks one, `interrupt_agent` stops one); `wait_agent` takes only `timeout_ms` and returns on any child mailbox activity. Do not infer role support from V1/V2 or a model version. Legacy-schema exception: only if the actual schema lacks `agent_type`, omit that unsupported field and carry the complete role instructions in `message`, with history explicitly disabled. This cannot select a specialized TOML; an installed managed default supplies the medium worker for unnamed non-forks. The guard has no schema metadata and rejects unnamed calls, so report incompatible routing instead of retrying generically. Every deliberate full-history fork must still name its role: Codex skips role application on unnamed full-history forks, an upstream gap no LazyCodex default can repair. If a code block below conflicts with this section, this section wins. `fork_context` is rejected on `multi_agent_v2` (`fork_context is not supported in MultiAgentV2; use fork_turns instead`).
 
 When translating `load_skills=[...]`, include the requested skill names in the spawned agent's `message`. If a code block below conflicts with this section, this section wins.
 
+Omit optional keys you do not set. Never send `items: []`, `message: ""`, `model: ""`, `reasoning_effort: ""`, or `service_tier: ""` — Codex rejects them (`Items can't be empty`, `reasoning_effort must not be empty`).
+
 For work likely to exceed one wait cycle, require the child to send `WORKING: <task> - <current phase>` before long passes and `BLOCKED: <reason>` only when progress stops. A `multi_agent_v1.wait_agent` timeout only means no new mailbox update arrived; back off between waits (double the timeout up to ~5 minutes) instead of spinning short cycles. Treat a running child as alive. Fallback only when the child is completed without the deliverable, ack-only after followup, explicitly `BLOCKED:`, or no longer running.
 
 ---
@@ -52,10 +54,10 @@ The research is done when all of these hold:
 - Claims that were contested, undocumented, or performance-shaped were proven or refuted by executed code.
 - Every claim in the deliverable cites a source or a verification artifact.
 - Every asserted claim is represented in the claim graph, tied to an intent-vs-reality diff when an expected truth exists, and backed by observation manifest entries from independent observation groups or a documented single-source exception; convergence or exception status is explicit.
-- The format-proposal gate was asked and answered BEFORE the first wave, and the final materials match that answer.
-- The delivered artifact passed every delivery gate for this harness: visual QA on the rendered pages always, plus the proofread pass where the harness provides one (Phase 5).
+- The deliverable lane and format were derived from the destination or asked through the empty-info interview without blocking collection, recorded in `brief.md` with `answered_by`, and the final materials match that record.
+- The delivered artifact passed the delivery gates in order (static gates, layout gates, visual QA, and the proofread pass where the harness provides one), each status is in `outcome.json`, and `outcome verify` passed.
 - Every excursion opened during the run was closed by an EXIT rule, folded back into the claim or axis that triggered it, and recorded in both `excursion-log.md` and the ulw-loop ledger.
-- The delivery message carries the closing briefing: how many sources the answer rests on (total + unique domains) and how many minutes the run took.
+- The delivery message carries the closing briefing printed by `outcome briefing`: sources (total + unique domains), elapsed minutes, every promised deliverable with its status, and any residual defects.
 - The session journal reconstructs what was searched, found, and expanded, wave by wave, and it was written in real time rather than reconstructed at the end.
 
 ## Epistemic instrumentation
@@ -132,6 +134,8 @@ mkdir -p .omo/ulw-research/$(date +%Y%m%d-%H%M%S)
 
 This is `$SESSION_DIR`. The orchestrator owns the journal: you write every file in it; workers never do. Maintain:
 
+- `brief.md` — the analysis block, the axis list, the expected truths, and the `## Deliverable` record from the interview below (lane, state, formats, each field with `answered_by`).
+- `sources-ledger.md` — one line per source the moment it is read: `[S<n>] <url> — <what it is>`. The closing briefing counts sources and domains from this file.
 - `wave-<N>-<kind>-<axis>.md` — your digest of each worker return: key findings, sources with URLs, and the worker's EXPAND markers verbatim.
 - `expansion-log.md` — per wave: workers spawned, markers gained, leads opened and closed.
 - `excursion-log.md` — one ENTER row and one EXIT row per excursion: `excursion_id`, parent claim or axis, ENTER trigger, depth, workers spent, the EXIT rule that closed it, what it changed in the top-level answer (`none` is a valid, required answer), and the ulw-loop steer/evidence id it was mirrored into.
@@ -148,20 +152,22 @@ Append each digest the moment its worker returns, not in a batch at the end —
 
 ulw-loop is ON by default for this mode: when the `ulw-loop` skill is available, register the research axes as loop goals so the run has durable state and survives a compaction. The session directory's timestamp is the run's start clock — the closing briefing is computed from it, so create it once and never rename it. From that point every finding, source, quote, number, and lead is written into `$SESSION_DIR` **the instant it lands** — never held in the conversation for an end-of-run dump. After any context loss, re-read the brief and the journal before doing anything else, then resume from the open wave.
 
-### Format-proposal gate — ALWAYS ask, before the first wave
+### Deliverable lane, format, and the empty-info interview
 
-Never guess the shape of the deliverable. After the decomposition and before spawning wave 1, propose the final materials and WAIT for the user's answer:
+Never block collection on the shape of the deliverable, and never guess it either. Read [references/deliverable-phase.md](references/deliverable-phase.md) sections 1-6 before writing the brief, then:
 
-- **Default pair: PDF + DOCX.** Offer both as the baseline for any report/document request.
-- Name the alternatives that actually fit THIS domain — slides for a briefing, standalone HTML for a living page, Markdown for a working note, several at once when the audience differs.
-- Propose the TEMPLATE too, chosen from the domain and the user's own context: section skeleton, citation style, length target, language, and any house style they have used before. A prior document the user points at is the strongest template signal — read it and mirror its structure and tagging.
-- Ask once, compactly: proposed format + proposed template + what each option costs. Then stop and wait. Guessing here wastes the entire assembly pass.
+1. **Derive first.** Name the lane (`template-strict`, `template-vibe`, `no-format`, `edit-existing`) and the promised formats from the request and its destination (the reference's section 3). When the request refers to an existing deliverable, decide its state with `node "$SKILL_DIR/scripts/report-tools.mjs" outcome state --deliverable <path> --session-dir "$SESSION_DIR"`: `partial` resumes the skeleton on disk, `complete` means edit-existing and never a regenerated report. `$SKILL_DIR` is this skill's own directory, the folder containing this SKILL.md.
+2. **Read the requester's format memory** with the memory tool when the harness exposes one: the pointer `system/human/report-style.md`, then `reference/human-report-style.md`; take the choice recorded for the most similar context (same destination kind and audience) as the first option.
+3. **Ask only what is still missing**: at most the reference's three questions (destination and format, audience and length, template lineage) in one call to the harness question tool (`ask_user_question` or `request_user_input`), non-blocking where the harness supports it, each with its default first, a free-text "describe the format" path, and "don't care, you decide". Collection starts without waiting; a late answer is folded in until the assembly worker starts, and after that it becomes a re-render request.
+4. **Record it.** Write `## Deliverable` into `brief.md` (lane, state, formats, destination, audience, template, format description, each with `answered_by: user|default|request`) and open the manifest in the same step: `node "$SKILL_DIR/scripts/report-tools.mjs" outcome init --promised <formats> --lane <lane> --session-dir "$SESSION_DIR"`.
 
-Record the answer in the journal; Phase 5 opens by turning it into `design-spec.md`.
+Phase 5 opens by turning the recorded fields into `design-spec.md`.
 
 ## Phase 1 — Saturation wave
 
-Launch the entire first wave in one turn — every axis at once, as team members if you formed a team, else as background workers. Sequential launches and "start with one and see" defeat the mode.
+**When the user asked for MASS research, the wave is sized by the topic's angles, not by the roster ceiling.** "mass ulw research", "mulw research", "ulw mass research" — in any language — order over-collection that a team of 8 cannot produce. Where the harness has a dependency-graph surface (the `mass-ulw` skill and its `references/planning.md`), run collection through it instead: a 60+ node opening wave covering every angle the topic has, routed across the whole difficulty ladder in one graph — mechanical sweeps and per-item harvest batches on the cheapest tier, judgment-shaped angles a step up, cross-territory angles a step above that, and the deepest tier reserved for genuinely hairy contradictions. Each wave's EXPAND leads define the next wave's nodes, and the synthesis reduces through several parallel architect-tier nodes into ONE architect-tier reducer (the strongest reasoning tier substitutes wherever no architect tier exists). Absent that surface, hold the same shape with background workers in batched waves. Everything else in this skill still binds: the deliverable interview, the journal, the claim graph, the convergence rules, and the delivery gates.
+
+Otherwise launch the entire first wave in one turn — every axis at once, as team members if you formed a team, else as background workers. Sequential launches and "start with one and see" defeat the mode.
 
 Scaling floor — more angles always justify more workers:
 
@@ -173,13 +179,15 @@ Scaling floor — more angles always justify more workers:
 | Multi-faceted | 4 | 6 | 2 | 2 | 14 |
 | Full due diligence | 4 | 6 | 3 | 2 | 15 |
 
+The browsing column is BINDING, not advisory: when the brief says `Browsing: yes`, the roster names a browsing-worker angle, armed with the `ultimate-browsing` skill, before the first wave launches, and that worker is spawned in the same turn as the rest of the wave. A run that reaches wave 2 with zero browsing workers on a `Browsing: yes` brief has silently downgraded every source to what plain fetch happened to return.
+
 **Disambiguate before you expand.** When the topic names something that could resolve several ways — a product, a person, a codename, a version — the first wave settles WHICH entity before any worker researches its history, benchmarks, or controversies: canonical name, first-party URL or account, whether it exists in the claimed category, and a confidence line. An unresolved entity never becomes a premise in a later wave's spawn message; that is exactly how a run starts inventing facts about something that does not exist.
 
 Role protocols — embed the relevant one in each spawn message; every worker gets a unique angle:
 
 - **Codebase (explore), 2-4 workers.** Grep with 3+ keyword variations; structural/AST search; LSP definitions and references; file-name globs; `git log --all -S '<keyword>'` and `--grep` for history including deleted code. Cross-validate hits across tools. Report absolute file paths, patterns with `file:line`, and how findings connect.
 - **Web (librarian), 3-6 workers.** At least 10 distinct websearch queries per worker, each with a different operator or angle (see Search craft); fetch the full page for every result that matters — snippets lie. Context7 with 3+ queries per known library. grep.app and `gh search code|repos|issues` for real-world usage. Official docs via sitemap discovery (`<base>/sitemap.xml`), then targeted pages.
-- **Browsing, 0-3 workers.** Pages plain fetch cannot read (WAF, 403, Cloudflare, dynamic rendering, login): the worker loads the `ultimate-browsing` skill and escalates through its tiers — Tier-1 insane-search engine first (including its Phase-2.5 archive surrogates), then Tier-2 Chrome stealth — rather than abandoning the source. Capture screenshots when visual context matters. **Provenance is part of the claim**: when a source came back with `provenance` of `snapshot` (an archive copy), cite it with its `snapshot_timestamp` and never state it as the current live page; content from a `proxy` route is `untrusted` and needs a second independent route before any claim rests on it. When one blocked territory hides many leads, fan out more browsing subagents in parallel for breadth instead of serializing one worker through them.
+- **Browsing, 1-3 workers on a `Browsing: yes` brief (0 otherwise), every one loaded with the `ultimate-browsing` skill.** The skill owns the routing — the harness's own browser first, then its extraction engine with archive surrogates, platform-native readers, and Chrome stealth as each source demands; the worker owns the deliverable. This worker RENDERS pages, it does not re-fetch them: its standing deliverable is a full-page screenshot of every top source plus the rendered text plain fetch could not reach; a worker that returns only fetched text has not done its job. JS-rendered, login-gated, WAF-blocked, and screenshot-bearing sources all belong here rather than in the web lane. **Provenance is part of the claim**: when a source came back with `provenance` of `snapshot` (an archive copy), cite it with its `snapshot_timestamp` and never state it as the current live page; content from a `proxy` route is `untrusted` and needs a second independent route before any claim rests on it. When one blocked territory hides many leads, fan out more browsing subagents in parallel for breadth instead of serializing one worker through them.
 - **Repo deep-dive (librarian), 0-2 workers.** Shallow-clone the most relevant repos to `${TMPDIR:-/tmp}`, pin the HEAD SHA, read core modules, follow call chains, return SHA-pinned permalinks.
 
 Example spawn (codebase axis; librarian, browsing, and repo-dive follow the same contract with their own protocol):
@@ -249,7 +257,7 @@ Interest alone is not a trigger. Anything without one stays a queued lead in `ex
 Settle with executed code, not judgment, whenever sources disagree, a behavior is undocumented, a claim is performance- or compatibility-shaped, or the honest answer is "it should work". Spawn one verification worker per claim:
 
 ```
-task(category="deep", run_in_background=true, prompt="TASK: verify by execution: <claim>.
+task(category="deep-low", run_in_background=true, prompt="TASK: verify by execution: <claim>.
 SOURCE: <where it came from>; CONTRADICTION: <opposing source, if any>.
 Write a minimal self-contained script that tests the claim; run it (uv run --with <deps> python / bun / direct compile); capture full stdout+stderr; pin versions.
 Reply with: the exact code, the full output, environment (OS, runtime, dependency versions), and a verdict — CONFIRMED / REFUTED / PARTIAL — grounded in the output.")
@@ -299,7 +307,7 @@ Workers: <total> · Waves: <count> · Excursions: <count> · Sources: <count> (<
 
 `SYNTHESIS.md` is the citation source of truth for final materials: every claim carries inline `[Source N]` citations, and every high-risk non-code claim you assert must be a verified-claims row from Phase 3b. Assert nothing the gate left in the unresolved/refuted annex.
 
-**Write the skeleton early and fill it as claims lock.** The moment the format gate is answered, create the deliverable file with its approved section headings and a `STATUS: draft — <n> sections open` line at the top. An interrupted run must leave a partial report on disk, never an empty directory and a lost conversation.
+**Write the skeleton early and fill it as claims lock.** The moment the brief records the deliverable, create the deliverable file with its section headings and a `STATUS: draft — <n> sections open` line as line 2 (an HTML comment in HTML); that line is the partial-state marker `outcome state` reads, removed only when the deliverable is complete. An interrupted run must leave a partial report on disk, never an empty directory and a lost conversation.
 
 **Keep sourced numbers, assumptions, and derived results visibly apart.** Every quantitative claim carries its lineage: `MEASURED` (a number a source states, cited), `ASSUMED` (a coefficient, distribution, or scope you chose — say why), `DERIVED` (computed from those, showing the formula), plus a sensitivity line whenever the assumption moves the answer. Presenting a derived estimate with the confidence of a measured one is the most damaging thing this mode can ship.
 
@@ -307,7 +315,7 @@ Workers: <total> · Waves: <count> · Excursions: <count> · Sources: <count> (<
 
 ## Phase 5 — Final materials
 
-The format answered at the Phase 0 gate is binding. Absent an explicit user override, render **both PDF and DOCX**:
+The promised formats recorded in `brief.md` and `outcome.json` are binding; `pdf` + `docx` is the default pair only when a document was asked for with no format word and no destination:
 
 | Target | How |
 |---|---|
@@ -316,7 +324,7 @@ The format answered at the Phase 0 gate is binding. Absent an explicit user over
 | Slides / deck | `uv run --with python-pptx python` — one claim per slide, a chart or diagram per claim. |
 | Standalone HTML / Markdown | The authored source itself. |
 
-**Write `design-spec.md` the moment the format gate is answered — before any asset worker spawns.** It is the one design contract every asset and assembly worker receives: template family (a document the user pointed at is the strongest signal — mirror its structure and register; absent one, default to the clean analyst-report register — restrained accent palette, generous margins, styled section headings, no emoji, no clipart), accent palette, body/heading fonts (a real CJK webfont — Pretendard, Noto Sans KR — when the report language needs one), and the figure standard below. One font family and one palette govern prose, charts, Mermaid, and generated images alike; a diagram rendering in a random default font inside a styled report is a defect, not a style choice.
+**Write `design-spec.md` the moment the deliverable is recorded — before any asset worker spawns.** When a document was pointed at, extract it instead of retyping its stylesheet: `node "$SKILL_DIR/scripts/report-tools.mjs" format-extract <reference> --out "$SESSION_DIR/design-spec.md"` (`--from-url` for a URL), then fill every `TODO: ask` from the interview answers, never by guessing. It is the one design contract every asset and assembly worker receives: template family (absent a reference, the clean analyst-report register — one accent over neutral tones, generous margins, styled section headings, no emoji, no clipart), palette tokens, body/heading fonts (a real gothic CJK webfont — Pretendard, Noto Sans KR — when the report language needs one, with `word-break: keep-all` for Korean), responsive breakpoints and HTML/CSS charts for web deliverables, the figure standard below, and the lineage mode on its own line: `Lineage: inline` (analyst default: every unit-bearing number tagged MEASURED / ASSUMED / DERIVED or cited in the same element) or `Lineage: section` (web and blog register: every section cited, lineage in the figure captions). The reference's section 6 lists the full defaults. One font family and one palette govern prose, charts, Mermaid, and generated images alike; a diagram rendering in a random default font inside a styled report is a defect, not a style choice.
 
 **The figure standard — binding for every image, chart, and diagram.** Each figure sits in a fixed-size container styled from the spec (border, background, caption); the image scales to fit entirely inside it with its original aspect ratio preserved — object-fit: contain semantics — never stretched, never cropped, never spilling out. Every chart carries a title, axis labels, units, and value labels in the report's language; a bare number the reader cannot name is a defect.
 
@@ -329,25 +337,30 @@ Asset workers (background, parallel, each fed `design-spec.md`) — visuals are
 
 **Verify the asset manifest before rendering.** List every asset the document references, assert each file exists and is non-empty on disk, and re-render whatever is missing. A document that renders with three broken diagrams is a document you will publish twice.
 
-Assembly worker — `task(category="deep", load_skills=["frontend", "visual-qa", "open-design", "data-scientist", "imagegen", "ulw-loop"], run_in_background=true, ...)`: before writing, read every available design and visualization skill and apply it — the report is a designed artifact, not a text dump; the worker's prompt carries `design-spec.md`. Use the template the user approved; absent a stronger house style the default skeleton is executive summary → key findings by theme → detailed analysis (quotes under 20 words with attribution, charts, Mermaid graphs, generated visuals, SHA-pinned permalinks, verification results) → comparative analysis when options compete → numbered sources with access dates → methodology appendix (workers, waves, searches, verifications, debate rounds) → correction log naming what verification overturned. Write it long and specific: every claim cites `[Source N]`, and the sources section lists every source the run actually used rather than a curated few.
+Assembly worker — `task(category="deep-low", load_skills=["frontend", "visual-qa", "open-design", "data-scientist", "imagegen", "ulw-loop"], run_in_background=true, ...)`: before writing, read every available design and visualization skill and apply it — the report is a designed artifact, not a text dump; the worker's prompt carries `design-spec.md`. Use the template the user approved; absent a stronger house style the default skeleton is executive summary → key findings by theme → detailed analysis (quotes under 20 words with attribution, charts, Mermaid graphs, generated visuals, SHA-pinned permalinks, verification results) → comparative analysis when options compete → numbered sources with access dates → methodology appendix (workers, waves, searches, verifications, debate rounds) → correction log naming what verification overturned. Write it long and specific: every claim cites `[Source N]`, and the sources section lists every source the run actually used rather than a curated few.
 
-### The delivery gate — visual QA must PASS
+### The delivery gates — every gate for the QA tier must PASS, in order
 
-Nothing reaches the user until the gate passes:
+Nothing reaches the user until the gates pass. Record each result with `node "$SKILL_DIR/scripts/report-tools.mjs" outcome gate <static|layout|visual|proofread> <pass|fail|not_run> --session-dir "$SESSION_DIR"`; a gate this harness does not provide is recorded `not_run`. A chat or post answer (light tier) runs the static gates and one render; every paginated or web deliverable runs them all (the reference's sections 3 and 7).
 
-**Visual QA (always).** Render the produced artifact back to images — PDF pages to PNG, the HTML in a real browser — and look at them: missing or broken figures, images stretched or spilling their containers, diagram or chart text rendered off the spec's font or palette, clipped tables, overflowing CJK text, blank pages, unlabeled chart values, wrong page breaks. Fix and re-render until the pages are clean. Reading the source markup is not visual QA; inspect the pixels.
+1. **Static gates (always, before anyone looks at pixels).** `node "$SKILL_DIR/scripts/report-tools.mjs" check "$SESSION_DIR/report.html" --design-spec "$SESSION_DIR/design-spec.md" > "$SESSION_DIR/defects.json"`: keep-all, palette tokens, emoji, em dashes, heading length, unsourced numbers, figure containers, chart text, gothic-only fonts, citations, the closing and sources sections, broken assets. Codes and fixes: [references/report-gates.md](references/report-gates.md).
+2. **Layout gates.** Print the probe with `node "$SKILL_DIR/scripts/report-tools.mjs" layout-probe --json`, evaluate its `source` in the rendered page through the `browser` skill's owned headless engine, save the result as `$SESSION_DIR/boxes.json`, and re-run `check` with `--layout "$SESSION_DIR/boxes.json"` (overflow, clipped text, distorted images, overlapping siblings).
+3. **Visual QA.** Render the produced artifact back to images — PDF pages to PNG, the HTML through the browser skill at desktop and phone widths — and look at them: missing or broken figures, images stretched or spilling their containers, diagram or chart text rendered off the spec's font or palette, clipped tables, overflowing CJK text, blank pages, unlabeled chart values, wrong page breaks. Reading the source markup is not visual QA; inspect the pixels.
 
-Then deliver: the artifact plus a compact chat-readable summary of what it says — the answer in a few sentences, the numbers that matter, and what to look at first. The document is the deliverable; the summary is what gets it read.
+**Repair is bounded.** After every gate run that found defects, ask `node "$SKILL_DIR/scripts/report-tools.mjs" repair decide --state "$SESSION_DIR/repair-state.json" --defects "$SESSION_DIR/defects.json" --artifact-bytes <bytes> --renders <pages> --session-dir "$SESSION_DIR"` and obey it: `repair` means fix and re-run; `deliver` means stop and ship with the residual defects the manifest now lists; `block` means a content-integrity defect remains (or there is no usable artifact), so do not deliver: tell the user what blocks it and record the row as `failed` with the reason. Never repair past a stop decision (3 attempts, a 2-attempt plateau, an oscillation, or 15 minutes; the reference's section 8).
+
+Then resolve every manifest row (`outcome set <format> delivered --path <file>` or `blocked_capability` / `skipped` / `failed` with `--reason`) and deliver: the artifact plus a compact chat-readable summary of what it says — the answer in a few sentences, the numbers that matter, and what to look at first. The document is the deliverable; the summary is what gets it read.
 
 ### The closing briefing — every run ends with it
 
 The last thing the user reads states, in one compact block, what the answer is made of:
 
-- **Sources.** How many sources the answer rests on and how many distinct domains they come from, counted from the journal's source ledger, not estimated. Name how many were primary sources and how many claims went to the unresolved/refuted annex.
-- **Effort.** Workers, waves, excursions, and verifications — the same counters as the `SYNTHESIS.md` header.
-- **Elapsed time, always.** Minutes from the run's start to delivery, derived from the session directory's own timestamp so it cannot be guessed: `python3 -c "import datetime,os,sys; s=datetime.datetime.strptime(os.path.basename(sys.argv[1]),'%Y%m%d-%H%M%S'); print(round((datetime.datetime.now()-s).total_seconds()/60))" "$SESSION_DIR"`.
+- **The printed block.** `node "$SKILL_DIR/scripts/report-tools.mjs" outcome verify --session-dir "$SESSION_DIR" && node "$SKILL_DIR/scripts/report-tools.mjs" outcome finish --session-dir "$SESSION_DIR" && node "$SKILL_DIR/scripts/report-tools.mjs" outcome briefing --session-dir "$SESSION_DIR"`: sources and distinct domains counted from `sources-ledger.md`, elapsed minutes from the session directory's own timestamp, every promised deliverable with its status, the gate results, the residual defects, and the repair summary. A failing `verify` means the run is not done.
+- **Effort.** Workers, waves, excursions, and verifications — the same counters as the `SYNTHESIS.md` header — plus how many sources were primary and how many claims went to the unresolved/refuted annex.
+
+Never ship the artifact without this block, and never fill it from memory — paste the printed block and read the rest off the journal.
 
-Never ship the artifact without this block, and never fill it from memory — every number in it is read off the journal.
+**Record the format choice.** After delivery, when the harness exposes a memory tool and the run qualifies (the user declared a preference, or made the same unsolicited choice on 2+ runs), append one episode line to `reference/human-report-style.md` in the grammar of the reference's section 5, and update the `system/human/report-style.md` pointer when a generalization changed.
  If you stood up a team, disband it and confirm every worker is terminal before the final answer.
 
 ## Search craft
@@ -378,9 +391,11 @@ High-yield combinations: official docs (`site:<docs domain>`), GitHub implementa
 | Obeying a surrounding "stop exploring" rule mid-research | Authority section — those rules do not bind this mode |
 | Asking a worker to write journal or session files | Workers are read-only; you journal every return |
 | Two workers given the same angle | One unique angle per worker, always |
+| A `Browsing: yes` run whose roster carries no browsing worker, or a browsing worker spawned without `ultimate-browsing` | The browsing column is binding — name the angle in the brief and spawn it, armed with the skill, in the first wave before any lead is chased |
 | Contested claim settled by judgment | Phase 3 — run code, capture output, verdict |
 | Deliverable claims without citations | Every claim cites a source or a verification artifact |
-| Guessing the deliverable format instead of asking | The format gate is unconditional: propose PDF+DOCX plus the domain-fitting alternatives and the template, then wait before wave 1 |
+| Guessing the deliverable format | Derive it from the request and destination; ask the empty-info interview only for what is still missing, and record `answered_by` for every field |
+| Blocking the collection wave on the format question | Ask non-blocking and start collecting; unanswered fields run on the shown defaults |
 | A roster smaller than the harness ceiling | Fill every member slot; split the broadest axis until the team is full |
 | One tier across the whole roster | Mixed tiers by design — cheap breadth, premium attack |
 | Silently re-routing a "quick"/"fast" instruction | Routing words are literal; journal requested -> spawned -> fallback per slot |
@@ -389,10 +404,14 @@ High-yield combinations: official docs (`site:<docs domain>`), GitHub implementa
 | Batching findings into an end-of-run journal dump | Journal each return as it lands; the journal is what survives a compaction |
 | Ending the run because every worker finished | Reserve the final fifth of the run for synthesis and materials |
 | A derived estimate presented as a measured number | MEASURED / ASSUMED / DERIVED lineage on every quantitative claim, plus a sensitivity line |
-| Delivering before the delivery gates pass | Visual QA on rendered pages always, plus the harness's proofread gate — a typo the user finds means a gate did not run |
+| Delivering before the delivery gates pass | Static and layout gates, visual QA on rendered pages, plus the harness's proofread gate — a typo the user finds means a gate did not run |
+| Skipping the static gates | `report-tools check` runs before any pixel review; its defects are cheaper than a visual pass |
+| Delivering with a pending manifest row | `outcome verify` must pass; every promised format ends `delivered`, `blocked_capability`, `skipped`, or `failed` with a reason |
+| Repairing past the tracker's stop decision | `repair decide` owns the budget; `deliver` ships with the residual list, `block` stops delivery |
+| Guessing a design-spec value the extractor marked `TODO: ask` | Fill it from the interview answers or the reference's defaults, never by guessing |
 | Referencing an asset that is not on disk | Verify the asset manifest before rendering; re-render whatever is missing |
 | A figure stretched, cropped, or styled off the report's design language | `design-spec.md` binds every asset: fixed containers, contain-fit with aspect preserved, spec fonts and palette in charts and Mermaid |
 | Chasing an interesting find with no ENTER trigger | Excursions need a named trigger; everything else stays a queued lead |
 | An excursion that never came back, or drifted into a new mission | EXIT rules are unconditional; depth 3 means promote it to an axis or record it as a gap |
 | An excursion whose result was never folded back | Every EXIT writes what it changed in the top-level answer, `none` included, and mirrors into the loop ledger |
-| Delivering without the closing briefing | Source count, unique domains, and elapsed minutes are read off the journal and stated every time |
+| Delivering without the closing briefing | Paste the block `outcome briefing` prints; never compute or recall its numbers by hand |

package/packages/omo-codex/plugin/skills/ulw-research/references/deliverable-phase.md

@@ -0,0 +1,187 @@
+# ulw-research - deliverable phase contract
+
+Read this before the brief is written and again before Phase 6. It replaces the old blocking format question with a contract that never stalls collection: the deliverable is derived from the request and its destination, the requester is asked only what is genuinely missing, and every promise made about the output is tracked in a manifest until it is delivered, skipped, or blocked with a reason.
+
+Every helper named here is one command of the dispatcher:
+
+```bash
+node "$SKILL_DIR/scripts/report-tools.mjs" <command> ...
+```
+
+`$SKILL_DIR` is the directory of the skill's `SKILL.md`. The helpers are plain `.mjs` files with no dependencies and run under `node` or `bun` on macOS, Linux, and Windows. They never launch a browser. Exit codes: `0` pass, `1` semantic failure (blockers found, a failed verify, a blocked repair), `2` usage or IO error. JSON goes to stdout and a one-line summary to stderr. Always pass `--session-dir "$SESSION_DIR"` explicitly; `SESSION_DIR` in the environment is only a fallback.
+
+## 1. Lanes
+
+The brief names exactly one lane. The lane decides how much the requester is asked, what the design spec starts from, and how strict the gates are.
+
+| Lane | Definition | How to say it to the requester |
+| --- | --- | --- |
+| `template-strict` | The requester pointed at a document (a prior report, a page, a house template). Its structure, tokens, citation style, and figure standard are copied mechanically and not reinterpreted. | "I will match the document you pointed at: same structure, colors, fonts, and citation style." |
+| `template-vibe` | The requester named a register or feeling ("like a consulting deck", "a clean blog post") without a document to copy. The design spec is written from the defaults in section 6 and the register. | "I will write it in that style using the default report design; point me at an example if you want an exact match." |
+| `no-format` | Nothing about the shape was said and the destination implies it (a chat answer, a thread post, a quick note). No interview about format. | "I will answer in the shape this destination expects." |
+| `edit-existing` | A complete deliverable for this question already exists (section 2). The run edits it in place. It never regenerates it. | "I will update the existing report rather than write a new one." |
+
+## 2. Deliverable state
+
+Before the brief is written, decide the state of any deliverable the request refers to:
+
+```bash
+node "$SKILL_DIR/scripts/report-tools.mjs" outcome state --deliverable <path> --session-dir "$SESSION_DIR"
+```
+
+| State | Meaning | What it opens |
+| --- | --- | --- |
+| `none` | No file, or an empty one. | A fresh run in the lane the request implies. |
+| `partial` | The file carries a `STATUS: draft` line in its first 5 lines, or its manifest still has a `pending` row. | Resume the on-disk skeleton: keep the sections that exist, fill the missing ones, and never start over. |
+| `complete` | The manifest says every promised row is resolved and the file is present and non-empty. | `edit-existing` only. A complete report is never regenerated from scratch. |
+
+## 3. Destination-derived defaults
+
+The request and its destination usually answer the format question already. Derive the defaults first; the interview (section 4) only covers what this table leaves open.
+
+| Request or destination signal | Default format set | Lane | QA tier |
+| --- | --- | --- | --- |
+| A question answered in chat, with no document asked for | `post` (the answer itself, Markdown) | `no-format` | light |
+| A thread, channel, or messenger post | `post` | `no-format` | light |
+| A web page URL as the destination, or "blog", "page" | `html` | `template-vibe` | full |
+| The words "PDF", "DOCX", "slides", or "LaTeX" in the request | exactly the named formats (`pdf`, `docx`, `slides`, `latex`) | `template-vibe` | full |
+| "Report", "document", "write-up" with no format word and no destination | `pdf` + `docx` | `template-vibe` | full |
+| A pointed-at document (a file, a URL, a prior report) | the reference's own format | `template-strict` | full |
+| A prior report of the same kind in this workspace, not pointed at | that report's format, offered as the Q1 default | `template-vibe` | full |
+| A complete existing deliverable for this question (section 2) | its existing format | `edit-existing` | the original's tier |
+
+QA tiers: **light** runs the static gates and one render check of the answer. **Full** runs the static gates, the layout gates, visual QA of every page, and the proofread gate (section 7).
+
+## 4. The empty-info interview
+
+The interview has exactly three questions, asked together through the harness question tool without waiting for the answer. A question is **skipped** when the request, the destination, a pointed-at document, or a declared memory episode already answers it; when all three are answered, nothing is asked.
+
+- **Q1 - destination and format.** Options in this order: the memory hit (the choice recorded for the most similar prior context, section 5) when there is one; the derived default from section 3; "describe the format in your own words" (free text, which becomes the brief for the design spec); "don't care, you decide" (resolves to the derived default).
+- **Q2 - audience and length.** Who reads it, and a length band: `short` (a page or a post), `standard` (a report of about 5 to 12 pages), or `deep` (a full dossier). The derived default is first.
+- **Q3 - template lineage.** The pointed-at document, the last report of the same kind, or the clean analyst register (section 6). The derived default is first.
+
+Non-blocking rule: ask, do not wait, and start collection. Write `brief.md` at once with every field and who answered it; the unanswered fields carry their defaults. A late answer is folded in until the assembly lane starts; after that it becomes a re-render request, handled like any other repair.
+
+Recorded fields, under `## Deliverable` in `brief.md`:
+
+```text
+lane: template-vibe
+state: none
+formats: pdf, docx (answered_by: request)
+destination: internal review document (answered_by: default)
+audience: engineering leads, standard (answered_by: user)
+template: clean analyst register (answered_by: default)
+format description: none
+```
+
+`answered_by` is one of `user`, `default`, `request`. Run `outcome init` (section 9) in the same step, with the formats as the promised list.
+
+## 5. Report-format memory episodes
+
+When the memory tool is present, the requester's report-format choices are kept as an append-only episode log, so a repeat requester is not asked the same question twice. When no memory tool is present, skip this section silently.
+
+- Pointer: `system/human/report-style.md`, projected every session. One line naming the log, plus the generalizations currently in force.
+- Episode log: `reference/human-report-style.md`, one line per episode, newest last:
+
+```text
+- [YYYY-MM-DD] <destination kind> · <audience> - <format and template chosen, one line> <!-- src: <session-id>; pattern: observed|declared; confidence: low|medium|high -->
+```
+
+Qualification (write after delivery, only when one of these holds): `declared` - the requester stated the preference outright ("always PDF only"); `observed` - the requester made the same unsolicited choice on 2 or more runs (read the log first). Record format and template choices only, never report content, subjects, names, or findings. Append; never rewrite an existing line.
+
+Read-time generalization (before the interview): a similar context is one with the same destination kind and audience. Consistent similar episodes supply Q1's first option; a `declared` similar episode skips the question it answers. One session never flips a default: a single `observed` episode that disagrees with the rest changes nothing.
+
+Pruning: keep the log near 15 lines. When it grows past that, prune the oldest episodes that agree with the majority for their context first. Never prune a `declared` episode or a minority episode (the only one recording a different choice for its context). Update the pointer in the same memory commit when a generalization changes.
+
+## 6. design-spec.md
+
+Write `$SESSION_DIR/design-spec.md` the moment the deliverable fields are known, before any asset lane starts. Every asset and assembly lane receives it.
+
+1. When a document was pointed at, extract it first. Do not retype its stylesheet:
+   ```bash
+   node "$SKILL_DIR/scripts/report-tools.mjs" format-extract <reference.html|reference.md> --out "$SESSION_DIR/design-spec.md"
+   node "$SKILL_DIR/scripts/report-tools.mjs" format-extract <https://...> --from-url --out "$SESSION_DIR/design-spec.md"
+   ```
+   The extractor copies the CSS custom properties (light and dark), font stacks by role, the most-used colors, px breakpoints, the section skeleton, the heading numbering, the citation marker style, the lineage mode, and the figure containers, under the fixed sections `Extracted from`, `Tokens`, `Typography`, `Layout`, `Structure`, `Figures`, `Citations`, `Open questions`. A field it cannot determine reads `TODO: ask`. A PDF reference is unsupported: ask for its HTML or Markdown source.
+2. Fill every `TODO: ask` from the interview answers, then from the clean analyst register below. Never guess a value.
+3. Apply the binding figure standard and the defaults:
+   - Every figure sits in a fixed-size container with a caption; the image scales inside it with contain-fit, its aspect ratio preserved, never stretched, cropped, or spilling out. Every chart carries a title, axis labels, units, and value labels as real text, with deterministic ticks (round values computed from the data range, never left to a renderer's auto-scaling).
+   - One accent color over neutral background, text, and rule tones. Every color in prose, charts, and diagrams is a spec token.
+   - For web deliverables, HTML/CSS bars and inline SVG are preferred over image charts, and the page has responsive breakpoints so it reads on a phone, a tablet, and a desktop.
+   - Gothic (sans) type only, as a real embedded webfont for the report language; Korean text uses `word-break: keep-all; overflow-wrap: anywhere`.
+   - A closing section on how the report was made (method, sources, members and waves, the gates it passed, what verification overturned) and a numbered sources section with access dates.
+4. Declare the lineage mode on its own line in the spec:
+   - `Lineage: inline` (the analyst default): every unit-bearing number carries `MEASURED`, `ASSUMED`, or `DERIVED` inline or in a `data-lineage` attribute, or a `[S<n>]` citation in the same element. The gate reports an untagged number as a major defect.
+   - `Lineage: section` (web and blog register): sources are bracketed source-label links at sentence end (the report language's word for "source"), lineage distinctions live in the figure captions, and every section is cited. The gate reports an untagged number as an advisory minor defect; the section-citation gate carries the weight.
+
+## 7. Delivery gates, in order
+
+Nothing reaches the requester until the gates for its QA tier pass, in this order. Each gate writes its status into the manifest with `outcome gate <gate> <pass|fail|not_run> --session-dir "$SESSION_DIR"`.
+
+1. **Static gates.** `check` on the rendered HTML:
+   ```bash
+   node "$SKILL_DIR/scripts/report-tools.mjs" check "$SESSION_DIR/report.html" --design-spec "$SESSION_DIR/design-spec.md" > "$SESSION_DIR/defects.json"
+   ```
+   It checks keep-all, palette tokens, emoji, em dashes in prose (en dashes outside numeric ranges are advisory), heading length and generic headings, unsourced numbers (section 6), figure containers and captions, chart SVG text, Korean serif fonts, sections without citations, the closing section, the sources section, broken local assets, and any `--require-section <regex>` the brief requires. Every code, severity, and fix is in [report-gates.md](report-gates.md).
+2. **Layout gates.** Print the probe, evaluate it in the rendered page through the browser skill's owned headless engine, save the returned object as `$SESSION_DIR/boxes.json`, and re-run `check` with `--layout "$SESSION_DIR/boxes.json"`. It adds overflow past the container, clipped text, scroll containers, distorted images, and overlapping siblings.
+   ```bash
+   node "$SKILL_DIR/scripts/report-tools.mjs" layout-probe --json   # .source is one async expression
+   ```
+3. **Visual QA.** Render the artifact to images (PDF pages to PNG, the HTML in the browser skill's engine at desktop and phone widths) and look at the pixels for what a machine cannot see: composition, hierarchy, page breaks, figure legibility.
+4. **Proofread.** A dedicated writing lane proofreads the final text only (grammar, spelling, punctuation, terminology, native register); it never composes or rewrites content.
+
+The light tier runs gate 1 and one render (recorded as `visual`) and records `layout` and `proofread` as `not_run`. The full tier runs all four.
+
+## 8. Bounded repair loop
+
+After every gate run that produced defects, ask the tracker what to do next:
+
+```bash
+node "$SKILL_DIR/scripts/report-tools.mjs" repair decide --state "$SESSION_DIR/repair-state.json" --defects "$SESSION_DIR/defects.json" --artifact-bytes <report bytes> --renders <rendered page count> --session-dir "$SESSION_DIR"
+```
+
+- `action: repair`: fix the listed defects, re-render, re-run the gate, and ask again.
+- `action: deliver`: stop repairing and deliver. `reason` is `clean` or the stop condition that fired; the residual defects are written into the manifest and listed in the closing briefing.
+- `action: block` (exit `1`): do not deliver. Either a content-integrity defect remains (`missing_closing_section`, `missing_citation_section`, `broken_asset_reference`, `missing_required_section`, `missing_promised_deliverable`), or a stop fired without proof of a usable artifact (`--artifact-bytes` and `--renders`). Tell the requester what blocks delivery and record the affected rows as `failed` with the reason.
+
+Defaults: 3 repair attempts, a plateau of 2 consecutive attempts that do not improve the (blocker, major, minor) counts compared in that order, and 15 minutes of wall clock from the first decision. A defect set that repeats an earlier attempt exactly stops the loop as an oscillation. When several conditions hold at once the reported reason follows `clean`, `blocking`, `oscillation`, `plateau`, `max_attempts`, `wall_clock`.
+
+## 9. Outcome manifest and closing briefing
+
+`$SESSION_DIR/outcome.json` tracks every promise made about the output, so a promised format is never silently dropped.
+
+```bash
+node "$SKILL_DIR/scripts/report-tools.mjs" outcome init --promised pdf,docx --lane template-vibe --session-dir "$SESSION_DIR"
+node "$SKILL_DIR/scripts/report-tools.mjs" outcome set pdf delivered --path "$SESSION_DIR/report.pdf" --pages 12 --session-dir "$SESSION_DIR"
+node "$SKILL_DIR/scripts/report-tools.mjs" outcome set docx blocked_capability --reason "no document converter in this session" --session-dir "$SESSION_DIR"
+node "$SKILL_DIR/scripts/report-tools.mjs" outcome render "$SESSION_DIR/renders/page-01.png" --page 1 --session-dir "$SESSION_DIR"
+node "$SKILL_DIR/scripts/report-tools.mjs" outcome verify --session-dir "$SESSION_DIR"
+node "$SKILL_DIR/scripts/report-tools.mjs" outcome finish --session-dir "$SESSION_DIR"
+node "$SKILL_DIR/scripts/report-tools.mjs" outcome briefing --session-dir "$SESSION_DIR"
+```
+
+- `init` runs when the brief is written (section 4): one `pending` row per promised format (`pdf`, `docx`, `html`, `md`, `latex`, `slides`, `post`).
+- `set` resolves a row: `delivered` (absolute path; bytes are read from disk; pages when paginated), `blocked_capability` (this session cannot produce it), `skipped` (the requester or the lane dropped it), or `failed`. Every status except `delivered` needs `--reason`.
+- `verify` runs before delivery and exits `1` while a row is `pending`, a status lacks its reason, or a delivered file is missing or empty.
+- `finish` stamps the finish time, the elapsed minutes from the session directory's start stamp, and the source and domain counts from `sources-ledger.md`.
+- `briefing` prints the closing block from the manifest and the ledger: sources and distinct domains, elapsed minutes, every deliverable with its status, the gate results, the residual defects, and the repair summary. That text is the closing briefing, pasted as printed, never filled in from memory.
+
+## 10. Command reference
+
+Invoke every command as `node "$SKILL_DIR/scripts/report-tools.mjs" <command>`. Exit codes for all of them: `0` pass, `1` semantic failure, `2` usage or IO error.
+
+| Command | Flags | Exit `1` when |
+| --- | --- | --- |
+| `check <report.html>` | `--design-spec <spec>` (required), `--layout <boxes.json>`, `--require-section <regex>` (repeatable), `--max-defects N` | any blocker defect |
+| `layout-probe` | `--cap N` (default 400), `--root <selector>` (default `main, article`), `--json` | never |
+| `repair decide` | `--state <file>` and `--defects <json>` (required), `--artifact-bytes N`, `--renders N`, `--session-dir <dir>`, `--max-attempts N`, `--plateau-limit N`, `--wall-clock-ms N`, `--now <ISO>` | the decision is `block` |
+| `outcome init` | `--promised <list>` (required), `--lane <lane>`, `--session-dir <dir>`, `--now <ISO>` | never |
+| `outcome set <format> <status>` | `--path <file>`, `--pages N`, `--reason <text>`, `--session-dir <dir>`, `--now <ISO>` | never |
+| `outcome gate <gate> <status>` | `--session-dir <dir>` | never |
+| `outcome render <png>` | `--page N` (required), `--session-dir <dir>` | never |
+| `outcome state` | `--deliverable <path>` (required), `--session-dir <dir>` | never |
+| `outcome verify` | `--session-dir <dir>` | a promise is unresolved or a delivered file is missing or empty |
+| `outcome finish` | `--ledger <file>`, `--session-dir <dir>`, `--now <ISO>` | never |
+| `outcome briefing` | `--json`, `--ledger <file>`, `--session-dir <dir>`, `--now <ISO>` | never |
+| `format-extract <reference>` | `--out <design-spec.md>` (required), `--from-url` | never (an unsupported reference exits `2`) |
+| `--help` | `--json` | never |

package/packages/omo-codex/plugin/skills/ulw-research/references/report-gates.md

@@ -0,0 +1,66 @@
+# Report-Gates Defect Glossary
+
+This reference catalogs every defect code the report gates (`static`, `layout`, `visual`, `proofread`) can raise, their severity and impact, and how to repair them.
+
+## Defect Codes by Category
+
+### Static Gate (Content & Structure)
+
+| Code | Severity | Integrity | What It Detects | How to Fix |
+|------|----------|-----------|-----------------|-----------|
+| `korean_no_keep_all` | major | false | Text containing Hangul uses default word breaking, causing character-level wrapping and orphaned characters on mobile or narrow containers. | Add "word-break: keep-all; overflow-wrap: anywhere" to the body or the slide text container. |
+| `palette_off_token` | minor | false | Color values are hardcoded literals (hex, rgb) instead of design-system tokens or are missing from the design spec palette. | Replace the literal color with a design-spec token (var(--...)) or add the color to the spec palette. |
+| `emoji_in_prose` | major | false | Emoji characters appear in body text, headings, or figure captions. Emoji render at inconsistent sizes and lack semantic meaning. | Remove the emoji; use an inline SVG icon or plain text. |
+| `em_dash_in_prose` | major | false | Em dashes (—) are used in body text for sentence breaks or parenthetical asides. Readability and accessibility suffer without a rewrite. | Rewrite the sentence with a comma, colon, or period instead of an em dash. |
+| `en_dash_in_prose` | minor | false | En dashes (–) are used incorrectly outside of numeric ranges. Only numeric ranges (e.g., "pages 5–10") should use en dashes. | Use a hyphen for compounds; keep the en dash only between numbers. |
+| `heading_too_long` | minor | false | A heading exceeds one visual line: 26 Korean characters (52 display width units) or 12 English words. | Shorten the heading to one line (26 Korean characters or 12 English words). |
+| `heading_generic` | minor | false | A heading uses generic labels (e.g., "Introduction", "Background") without conveying the section's specific claim or finding. | Make the heading carry the section's claim instead of a generic label. |
+| `unsourced_number` | major | false | A numeric value (percentage, count, duration, ratio) appears without a source attribution, measurement tag, or derivation chain. | Tag the number MEASURED / ASSUMED / DERIVED or cite its source in the same paragraph. |
+| `chart_without_figure` | major | false | An image or chart lacks a figure wrapper with a caption. Uncaptioned charts isolate visuals from narrative flow. | Wrap the image or chart in a figure container with a caption. |
+| `chart_svg_no_text` | major | false | An SVG chart or diagram lacks a title, axis labels, units, or value labels. Visuals cannot stand alone without text guidance. | Give the chart a title, axis labels, units, and value labels as SVG text. |
+| `chart_svg_missing_labels` | minor | false | An SVG chart has some labels (e.g., title) but is missing others (e.g., axis ticks or unit). | Add the missing title, axis ticks, or unit label to the chart. |
+| `korean_serif_font` | major | false | A serif or brush Korean font family is applied to Korean text. The design spec mandates gothic (sans) Korean typefaces. | Use a gothic (sans) Korean family; serif and brush families are banned by the design spec. |
+| `section_without_citation` | major | false | A major section or subsection contains no in-text citations or reference marks. Source attribution is missing. | Cite at least one source inside this section or merge it into a cited one. |
+| `missing_closing_section` | blocker | true | The report lacks a closing section explaining the methodology, sources, and gate outcomes. Delivery is incomplete without narrative closure. | Add the closing section that explains how the report was made (method, sources, gates). |
+| `missing_citation_section` | blocker | true | The report has no sources, references, or citation definitions (e.g., [S1], [S2]). Attribution is impossible. | Add a sources or references section, or [S<n>] definition lines. |
+| `broken_asset_reference` | blocker | true | An asset file (image, diagram, spreadsheet) is missing or unreadable. The deliverable cannot be rendered or is incomplete. | Re-render or restore the missing asset file before delivery. |
+| `missing_required_section` | blocker | true | A section explicitly required by the brief (e.g., via `--require-section`) is absent. | Add the section the brief requires (matched by --require-section). |
+| `missing_promised_deliverable` | blocker | true | A deliverable (e.g., a slide deck, a chart, a data file) is promised in the brief but not delivered, not marked blocked_capability, and not skipped with a reason. | Produce the promised deliverable or record it as blocked_capability or skipped with a reason. |
+
+### Layout Gate (Rendering & Presentation)
+
+| Code | Severity | Integrity | What It Detects | How to Fix |
+|------|----------|-----------|-----------------|-----------|
+| `layout_overflow` | major | false | An element exceeds its container width or height, causing horizontal scroll or content spillage in PDF, DOCX, or slide renders. | Constrain the element to its container (max-width: 100%, overflow-wrap: anywhere, or a narrower measure). |
+| `layout_text_clipped` | major | false | Text is clipped or hidden by `overflow: hidden` or a fixed container height. Content is lost or unreadable. | Remove the overflow: hidden clip or give the text room to wrap. |
+| `layout_scroll_container` | minor | false | A table or list is wrapped in a scrollable container for HTML deliverables. Scrolling content prints clipped in PDF or DOCX. | Scrolling content prints clipped; make the content fit or wrap the table in a scroll wrapper only for HTML deliverables. |
+| `layout_image_distorted` | major | false | An image is distorted, stretched, or squeezed (aspect ratio is not preserved). The visual information is misrepresented. | Preserve the image aspect ratio (object-fit: contain inside a fixed container). |
+| `layout_sibling_overlap` | major | false | Two adjacent block elements overlap (via negative margins, absolute positioning, or grid collision). Layout is broken. | Separate the overlapping elements (margins, grid, or a slide split). |
+
+## Exit Codes
+
+Gates emit a manifest-level outcome with one of three statuses:
+
+| Status | Meaning |
+|--------|---------|
+| `pass` | All checks passed; no defects raised. |
+| `fail` | One or more defects raised (blocker, major, or minor severity). Repair is required before delivery. |
+| `not_run` | The gate was not invoked (e.g., no probe file provided for layout, no visual inspection conducted). |
+
+### Layout Gate Probe File Requirement
+
+The `layout` gate only runs when a probe file (a rendering artifact: PDF, PNG, or HTML snapshot) is provided alongside the manifest. If no probe file is available, the manifest records `layout: not_run` and the gate does not emit defects.
+
+## Lineage and Citation Markers
+
+Defect codes and their hints are delivered via the outcome manifest under `residualDefects` (if repair did not exhaust). Each defect entry includes:
+
+- **code**: A string key from the table above (e.g., `"em_dash_in_prose"`)
+- **message**: A human-readable narrative or location hint describing where the defect was found (e.g., "Line 42: em dash found in paragraph 2")
+
+Citations within reports follow one of two lineage modes:
+
+- **inline**: Source marks appear as `[Sn]` or `[Rn]` hyperlinks inline with the cited text.
+- **section**: Sources are listed in a dedicated section with numbered entries ([S1], [S2], etc.).
+
+Both modes are valid; choose based on the report's narrative flow.