lazycodex-ai 5.1.61 → 5.1.63

package/packages/omo-codex/plugin/skills/remove-ai-slops/SKILL.md

@@ -96,12 +96,12 @@ The agent looks for these ten categories. The first three are stylistic, the nex
 10. **Oversized modules** — any source file exceeding **250 pure LOC** (non-blank, non-comment lines). This is an architectural defect, not a style preference. Measure: `awk '!/^[[:space:]]*$/ && !/^[[:space:]]*(#|\/\/)/' <file> | wc -l`.
 
    **When found, do NOT just flag it. Execute a full modular refactoring:**
-   1. Run `check-no-excuse-rules.py` recursively on scope to list all violations.
+   1. List every oversized file in scope: run the `awk` measure above on each source file. For `.py` files you may instead run the `programming` skill's Python checker (`uv run <programming skill dir>/scripts/python/check-no-excuse-rules.py <paths>`, rule `oversized-module`); it scans only `.py` files, so it never covers another language.
    2. For each oversized file, identify distinct responsibilities (single-responsibility principle).
    3. Plan the split: name each new file after the concept it owns (never `utils.py`, `helpers.py`, `common.py`, `part_1.py`).
    4. Present the split plan to the user before executing.
    5. Extract into clean modules with explicit `__init__.py` re-exports (re-exports ONLY, no logic in `__init__.py`).
-   6. Verify: run `check-no-excuse-rules.py` again — every file must be ≤250 pure LOC. Run tests, typecheck, lint.
+   6. Verify: re-measure exactly as in step 1 — every file must be ≤250 pure LOC. Run tests, typecheck, lint.
 
    **Forbidden escapes**:
    - Counting blanks/comments toward budget.
@@ -110,7 +110,7 @@ The agent looks for these ten categories. The first three are stylistic, the nex
    - "It's generated" — only valid if the file lives in a build output directory.
    - "230 LOC, close enough" — a 230-LOC file about to grow is already over. Split now.
 
-   KEEP: genuinely self-contained single-responsibility scripts (e.g., a standalone CLI checker). Opt out with `# noqa: SIZE_OK` in first 5 lines and a comment explaining why.
+   KEEP: genuinely self-contained single-responsibility scripts (e.g., a standalone CLI checker). Opt out with the language's SIZE_OK marker in the first 10 lines (`# noqa: SIZE_OK` in Python, the form the Python checker reads; `// allow: SIZE_OK` in `//`-comment languages) and a comment explaining why.
 
 ---
 
@@ -130,7 +130,7 @@ A pass is complete only when all applicable gates are green. Skip gates that are
 
 ## Process
 
-### Phase 0: Plan with TodoWrite
+### Phase 0: Plan with the todo tool
 
 Create todos for all phases below. Mark `in_progress` one at a time.
 
@@ -270,8 +270,8 @@ If any gate fails or any checklist item flips:
 
 1. Identify the specific change that caused the failure.
 2. Explain why it broke things.
-3. `git checkout` the affected file (or use `git diff` + targeted `Edit` to revert just the problematic hunk).
-4. If genuine slop remains after revert, edit the file directly yourself — in parallel per file via multiple Edit calls — applying only the changes you can prove are safe.
+3. `git checkout` the affected file (or use `git diff` + targeted `edit` to revert just the problematic hunk).
+4. If genuine slop remains after revert, edit the file directly yourself — in parallel per file via multiple `edit` calls — applying only the changes you can prove are safe.
 5. Re-run the failing gate and re-walk the checklist for the affected file.
 6. Repeat until all gates green AND checklist clean.
 

package/packages/omo-codex/plugin/skills/review-work/SKILL.md

@@ -163,7 +163,7 @@ For GOAL, CONSTRAINTS, BACKGROUND - review the full conversation history. The us
 
 ## Phase 1: Manual QA (you run it)
 
-You are the QA lane. Do not delegate hands-on QA to a sub-agent: the orchestrator owns the real-surface proof, exactly as the ulw-loop final gate records `manualQa` under the main session.
+You are the QA lane. Do not delegate hands-on QA to a sub-agent: the orchestrator owns the real-surface proof, exactly as the ulw-loop final gate records `manualQa` under the main session. One exception: inside a `ulw-execute` run, whose root never runs QA itself, dispatch these scenarios to one QA worker and build the matrix from the artifacts it captures.
 
 1. **Reuse first.** If this session already captured real-surface evidence for the FINAL tree (an ultrawork or ulw-loop evidence directory, a `visual-qa` verdict on this same build), consume it as QA rows instead of re-running. A fix committed after a capture stales that capture: re-run the rows it covered.
 2. **Pick the channel that faithfully exercises the surface** and capture the artifact:
@@ -282,7 +282,7 @@ Store the lane verdicts independently:
 | Manual QA (Phase 1) | PASS/FAIL | rows, artifact paths |
 | Gate review | pending/APPROVE/REJECT/INCONCLUSIVE | - |
 
-If the reviewer stays silent after the reliability followup, record the lane INCONCLUSIVE and respawn one smaller reviewer scoped to the same inputs. If that retry also ends without a verdict, close the still-running agent if safe, keep the lane INCONCLUSIVE, and emit the final result naming the incomplete lane. Do not spin in repeated wait/followup cycles, and do not use a queued followup as a cancellation.
+If the reviewer ends without a verdict (it completed without one, answered ack-only to one follow-up, or reported `BLOCKED:`), record the lane INCONCLUSIVE and respawn one smaller reviewer scoped to the same inputs. A reviewer that is still running is alive, not silent. If that retry also ends without a verdict, close the still-running agent if safe, keep the lane INCONCLUSIVE, and emit the final result naming the incomplete lane. Do not spin in repeated wait/followup cycles, and do not use a queued followup as a cancellation.
 
 After the lane reaches a terminal state and before delivering the verdict, tear down the review worktree: run `git worktree unlock <path>` followed by `git worktree remove <path>`. The reviewer runs inside that worktree, so removing it earlier destroys its working directory; a crashed review leaves the locked tree as a recoverable marker for manual cleanup.
 

package/packages/omo-codex/plugin/skills/ultimate-browsing/SKILL.md

@@ -15,14 +15,14 @@ Web access for the hosts the user's browser cannot open (WAF / 403 / Cloudflare
 User request
   |
   +- a page the user's browser can open (read, click, screenshot, QA, login)  NOT this skill (browser skill, attached engine)
-  +- simple search query ------------------------------ NOT this skill (use web-search)
+  +- simple search query ------------------------------ NOT this skill (use web search)
   |
   +- URL blocked / 403 / Cloudflare / WAF ------------- TIER 1  insane-search
   +- YouTube/Vimeo/TikTok subtitles or metadata ------- TIER 1  insane-search (yt-dlp)
   +- archive snapshot of a dead or changed page ------- TIER 1  insane-search (surrogates, provenance-tagged)
   |
   +- Chinese platform (xhs/douyin/weibo/bilibili/v2ex/wechat)  TIER 1.5 agent-reach
-  +- podcast transcript / stock forum ----------------- TIER 1.5 agent-reach
+  +- podcast transcript ------------------------------- TIER 1.5 agent-reach
   +- Twitter feed / LinkedIn profile / GitHub via CLI - TIER 1.5 agent-reach
   |
   +- Tier 1/1.5 returned empty or partial ------------- TIER 2  2a owned engine (stealth)
@@ -71,8 +71,8 @@ The full engine harness (rules R1-R7, the Phase 0 official-API index, the no-sit
 | search | Exa AI | [references/agent-reach/search.md](references/agent-reach/search.md) |
 
 ```bash
-mcporter call 'douyin.parse_douyin_video_info(url: "<URL>")'   # douyin, zero-config
-curl -s "https://r.jina.ai/https://weibo.com/<uid>/<pid>"      # weibo via Jina
+mcporter call 'douyin.parse_douyin_video_info(share_link: "<URL>")'   # douyin, zero-config
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/https://weibo.com/<uid>/<pid>"   # weibo via Jina (key required)
 yt-dlp --dump-json "<bilibili-url>"                            # Bilibili (overseas: add --cookies-from-browser)
 curl -s "https://www.v2ex.com/api/topics/hot.json"            # V2EX public API
 ```
@@ -115,17 +115,19 @@ When the blocked flow needs the user's account, drive the browser they are alrea
 
 ### Cookie login (cross-platform)
 
-`scripts/extract_cookies.py` reads cookies from a local Chromium-family or Firefox-family browser and optionally injects them into the running CDP session. It resolves browser profile paths and decrypts cookie values per-OS (macOS Keychain, Linux libsecret, Windows DPAPI):
+A login the user holds goes through Tier 2b, never through their cookies: the `browser` skill forbids copying a session out of the user's real browser profile (`references/owned-engine/network.md`, Cookies).
+
+`scripts/extract_cookies.py` reads cookies from the default profile store of a local Chromium-family or Firefox-family browser and optionally injects them over CDP. It resolves browser profile paths and decrypts cookie values per-OS (macOS Keychain, Linux libsecret, Windows DPAPI). Because it always reads that default store, run it only where that browser profile is not the user's live profile (for example a dedicated automation account whose browser the task owns); on the user's own machine it would copy their session, so use Tier 2b instead.
 
 ```bash
 # Extract cookies to a file:
 mkdir -p ~/.local/state/omo-cookies
 python3 -B scripts/extract_cookies.py --browser chrome --domain youtube.com --output ~/.local/state/omo-cookies/youtube.cookies.json
-# Extract and inject into the running CDP session:
+# Extract and inject over CDP (needs a browser started with --remote-debugging-port=9242; connectPipe opens no port):
 python3 -B scripts/extract_cookies.py --browser chrome --domain youtube.com --inject --cdp 9242
 ```
 
-Cookie export files are written with owner-only `0600` permissions. Do not place live auth cookies in shared temp directories or commit them to a repo. Cookie injection sends values to CDP over stdin rather than argv. Cookies apply on next navigation — reload after injecting. Google services use fingerprint-bound tokens that may not transfer across browser profiles. Limits in [references/chrome-stealth.md](references/chrome-stealth.md).
+For a Tier 2a owned page, load the exported file and call `omowright.injectCookies(page, cookies)` instead (see [references/chrome-stealth.md](references/chrome-stealth.md)). Cookie export files are written with owner-only `0600` permissions. Do not place live auth cookies in shared temp directories or commit them to a repo. Cookie injection sends values to CDP over stdin rather than argv. Cookies apply on next navigation — reload after injecting. Google services use fingerprint-bound tokens that may not transfer across browser profiles. Limits in [references/chrome-stealth.md](references/chrome-stealth.md).
 
 ## Reference docs
 
@@ -139,7 +141,8 @@ Cookie export files are written with owner-only `0600` permissions. Do not place
 
 ```bash
 # agent-reach auth: set the channel-specific env vars from each tool's docs only if you have access
-# insane-search needs no env vars — it auto-installs deps on first run
+# insane-search: JINA_API_KEY only for the Jina Reader route (the engine skips that surrogate without it)
+# insane-search Python deps: the install one-liner in references/insane-search/README.md
 ```
 
 ## Anti-patterns

package/packages/omo-codex/plugin/skills/ultimate-browsing/engine/AGENTS.md

@@ -61,7 +61,7 @@ is a regression, not an upgrade:
 - **Module split of the fetch chain** — `curl_probe` / `referers` / `url_transforms` /
   `waf_detector` / `validators` / `executor` / `summary` as separate modules rather than
   one monolith.
-- **The Python test suite** under `engine/tests/` with its HTML/JSON fixtures.
+- **The Python test suite** under `engine/tests/` with its HTML/JSON fixtures (source checkout only: the skill copy filter drops `engine/tests/` from every shipped edition).
 - **De-personalization** — no personal absolute paths, no personal auth token literals,
   no personal browser choice; enforced by `depersonalization-gate.test.ts`.
 - **Skill-level layering** — the engine is Tier 1 under a router that also owns Tier 1.5
@@ -115,7 +115,7 @@ Any future upstream sync preserves BOTH sides. Concretely:
 
 ## OVERVIEW
 
-A 17-module Python package embedded in the `ultimate-browsing` skill: a site-agnostic fetch chain that escalates from a cheap curl probe to a real browser, with declarative WAF and surrogate registries. Not "optional scripts" — it has its own CLI entry (`python3 -B -m engine URL`; `-B` keeps bytecode caches out of a signed app bundle, #11373), two YAML config schemas, a 4-file test suite, and a standalone CI guard. Package exports (`__init__.py`): `fetch`, `FetchResult`, `Attempt`, `Verdict`, `ValidationResult`, `validate`, `CHALLENGE_MARKERS`, `detect`, `TRANSFORMS`, `apply_transform`.
+A 13-file Python package (`__init__.py`, `__main__.py` and 11 modules) embedded in the `ultimate-browsing` skill: a site-agnostic fetch chain that escalates from a cheap curl probe to a real browser, with declarative WAF and surrogate registries. Not "optional scripts" — it has its own CLI entry (`python3 -B -m engine URL`; `-B` keeps bytecode caches out of a signed app bundle, #11373), two YAML config schemas, a 6-file test suite (source checkout only), and a standalone CI guard. Package exports (`__init__.py`): `fetch`, `FetchResult`, `Attempt`, `Verdict`, `ValidationResult`, `validate`, `CHALLENGE_MARKERS`, `detect`, `TRANSFORMS`, `apply_transform`.
 
 ## THE NO-SITE-NAME RULE (enforced in CI)
 
@@ -170,11 +170,11 @@ python3 -B -m engine URL [--selector S] [--device auto|desktop|mobile]
 
 ## TESTS
 
-`tests/` — `test_surrogate.py` (staleness, proxy gating, short-circuit), `test_surrogate_validators.py`, `test_fetch_chain.py`, `test_playwright_templates.py`, plus HTML/JSON fixtures under `tests/fixtures/`.
+`tests/` (source checkout only; not shipped with the skill) — `test_surrogate.py` (staleness, proxy gating, short-circuit), `test_surrogate_validators.py`, `test_fetch_chain.py`, `test_playwright_templates.py`, `test_playwright_stealth.py`, `test_executor_timeout.py`, plus HTML/JSON fixtures under `tests/fixtures/`.
 
 ## NOTES
 
 - `summary.py` emits an **R7 API-first hint** after >=3 challenge verdicts against a known WAF profile: look for `/api/`, `/graphql`, or `.json` endpoints, which usually carry weaker WAF protection than the HTML surface.
 - `templates/` holds the Playwright JS templates (`playwright_real_chrome.js`, `playwright_mobile_chrome.js`) the executor drives.
 - `url_transforms.py` transforms stay domain-agnostic (`mobile_subdomain`, `am_prefix`, `drop_www`).
-- Parent: [`packages/shared-skills/AGENTS.md`](../../../AGENTS.md).
+- Parent (source checkout only; not shipped with the skill): `packages/shared-skills/AGENTS.md`.

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/agent-reach/README.md

@@ -25,13 +25,13 @@
 mcporter call 'exa.web_search_exa(query: "query", numResults: 5)'
 
 # 通用网页阅读
-curl -s "https://r.jina.ai/URL"
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/URL"
 
 # GitHub 搜索
 gh search repos "query" --sort stars --limit 10
 
 # Twitter 搜索
-twitter search "query" --limit 10
+twitter search "query" -n 10
 
 # YouTube/B站字幕
 yt-dlp --write-sub --skip-download -o "/tmp/%(id)s" "URL"

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/agent-reach/career.md

@@ -25,5 +25,5 @@ mcporter call 'linkedin-scraper.search_jobs(keyword: "software engineer", limit:
 如果 MCP 不可用，可以用 Jina Reader：
 
 ```bash
-curl -s "https://r.jina.ai/https://linkedin.com/in/username"
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/https://linkedin.com/in/username"
 ```

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/agent-reach/social.md

@@ -105,7 +105,7 @@ twitter likes
 
 ```bash
 # 使用 Jina Reader 读取
-curl -s "https://r.jina.ai/https://weibo.com/USER_ID/POST_ID"
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/https://weibo.com/USER_ID/POST_ID"
 ```
 
 > 微博主要通过网页抓取，推荐使用通用网页读取方式。

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/agent-reach/web.md

@@ -6,13 +6,13 @@
 
 ```bash
 # 读取任意网页内容
-curl -s "https://r.jina.ai/URL"
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/URL"
 
 # 示例
-curl -s "https://r.jina.ai/https://example.com/article"
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/https://example.com/article"
 ```
 
-**适用场景**: 大多数网页可以直接用 Jina Reader 读取。
+**适用场景**: 大多数网页可以直接用 Jina Reader 读取。匿名调用返回 401，必须带 `JINA_API_KEY`（见 [../insane-search/jina.md](../insane-search/jina.md)）。
 
 ## Web Reader (MCP)
 
@@ -69,7 +69,7 @@ for e in feedparser.parse('FEED_URL').entries[:5]:
 
 | 场景 | 推荐工具 |
 |-----|---------|
-| 通用网页 | Jina Reader (`curl r.jina.ai`) |
+| 通用网页 | Jina Reader (`curl r.jina.ai`，需 `JINA_API_KEY`) |
 | 需要图片/格式控制 | web-reader MCP |
 | 微信公众号 | Exa (搜索+阅读) / Camoufox (可选阅读) |
 | RSS 订阅 | feedparser |

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/chrome-stealth.md

@@ -29,7 +29,8 @@ page that only a signed-in user can reach belongs to the attached engine, not to
 
 ## Cookie login limits
 
-`scripts/extract_cookies.py` still exports cookies from a local browser; inject them with
+`scripts/extract_cookies.py` still exports cookies from a local browser's default profile store (run it only where
+that profile is not the user's live one; see `../SKILL.md`, Cookie login); inject them with
 `injectCookies(page, cookies)` into an **owned** profile. It sanitizes the set (drops expired
 entries, keeps host-prefixed cookies secure and root-scoped). Limits that do not change:
 

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/insane-search/README.md

@@ -17,7 +17,7 @@
 2. 즉시 다음을 실행:
    ```bash
    python3 -B -m engine "<URL>" [--selector "<CSS>"] [--device auto|desktop|mobile] [--trace] \
-                              [--no-retry] [--no-extract]
+                              [--timeout 25] [--max-attempts 12] [--no-playwright] [--allow-proxy] [--json]
    ```
 3. 종료코드 0(ok) 또는 1(fail) 받은 뒤 판단. trace를 먼저 읽고 재시도 결정.
 4. 실패 시에만 `--trace --json`으로 재호출해서 원인 진단 후 `--device` 또는 `user_hint` 조정.
@@ -46,7 +46,7 @@
 - Claude는 그 사이 foreground에서 MCP Playwright 정찰 루트를 진행
 - engine이 먼저 성공해도 좋고, MCP 정찰로 얻은 API가 먼저 성공해도 좋음. 빠른 쪽 결과 채택
 
-**MCP 정찰 루트**:
+**MCP 정찰 루트** (Playwright MCP가 로드된 세션 전용. 없으면 the `browser` skill's `references/owned-engine/network.md` 로 같은 XHR/fetch 목록을 모은다):
 1. `mcp__playwright__browser_navigate` → 대상 페이지 로드 (브라우저 렌더링)
 2. `mcp__playwright__browser_network_requests` → XHR/fetch 호출 목록 수집, `/api/`·`/graphql`·`\.json` 필터로 내부 엔드포인트 식별
 3. 식별된 JSON API URL을 `python3 -B -m engine <API_URL>`로 재호출 (백그라운드 engine과는 별개 호출). 대부분 API 레이어는 페이지 HTML보다 WAF 보호가 얕아 curl_cffi로 바로 수집됨
@@ -124,7 +124,7 @@
 ### 단일 진입점
 
 ```python
-from insane_search.engine import fetch
+from engine import fetch      # 스킬 디렉터리에서 실행 (패키지는 engine/)
 
 result = fetch(
     "https://example.com/path",
@@ -136,15 +136,13 @@ result = fetch(
 
 if result.ok:
     print(result.verdict)     # strong_ok | weak_ok
-    html = result.content     # raw body — 단, content-rescue가 발동한 경우 구조 텍스트
-    # v0.10.0 content-rescue: PDF 응답은 pypdf 추출 텍스트, visible text가 얇은
-    # SPA 셸은 JSON-LD articleBody / 렌더된 innerText로 대체될 수 있다.
-    # result.extraction_source로 판별: "raw"(원문 그대로) | pdf | json_ld | *+inner_text.
-    # 일반 HTML 성공은 항상 raw. 끄기: enable_extraction=False / --no-extract.
-    # 429/502/503/504는 probe에서 백오프 재시도(Retry-After 반영, 총 10초 캡);
-    # 끄기: enable_retry=False / --no-retry.
+    html = result.content     # raw body (내장 추출/변환 없음)
+    # 필드: ok, content, final_url, verdict, profile_used, trace, summary,
+    #       provenance, snapshot_timestamp, trust (engine/result_schema.py FetchResult).
+    # 업스트림 신버전의 content-rescue(PDF/JSON-LD 추출)와 Retry-After 백오프는
+    # 이 스냅샷에 없다 — engine/AGENTS.md의 WANT 목록. grid 시도 사이에는 짧은 jitter만 둔다.
 else:
-    # Phase 3 수동 개입 (Playwright MCP) 필요 — result.trace로 원인 진단
+    # result.trace로 원인 진단. 브라우저가 필요하면 아래 "needs_js_exec only 폴백 규칙"을 따른다
     pass
 ```
 
@@ -191,16 +189,17 @@ report     — FetchResult(ok, verdict, profile_used, trace, summary)
 | 태그 | 실행기 | 언제 |
 |------|--------|------|
 | `needs_real_tls_stack` + `needs_js_exec` | `playwright_real_chrome.js` (로컬 Node) | Akamai Bot Manager 등 — Chromium 번들 TLS는 탐지됨 |
-| `needs_js_exec` only | Playwright MCP (`mcp__playwright__*`) | Cloudflare 기본 방어 등 |
+| `needs_js_exec` only | 에이전트가 직접 띄우는 브라우저 (엔진은 stub만 반환, 아래 규칙) | Cloudflare 기본 방어 등 |
 | `needs_mobile_context` (+ real_tls) | `playwright_mobile_chrome.js` | 모바일 디바이스 에뮬레이션 필요 |
 
 자세한 선택 기준: [playwright.md](playwright.md).
 
-### Playwright MCP 호출 규칙
+### `needs_js_exec only` 폴백 규칙
 
-`fetch_chain`의 `needs_js_exec only` 케이스는 **Claude 세션에서 MCP 도구를 직접 호출**해야 한다. subprocess 경로 없음. 즉:
+`fetch_chain`의 `needs_js_exec only` 케이스는 subprocess 경로가 없어 **에이전트가 직접 브라우저를 다뤄야** 한다. 즉:
 1. `result.summary`에 "Playwright MCP must be invoked from the Claude session"이 포함되면
-2. `mcp__playwright__browser_navigate` → `browser_wait_for` → `browser_snapshot` 흐름으로 Claude가 직접 처리
+2. 엔진 문구가 MCP를 가리켜도 기본 경로는 Tier 2a owned engine이다: js eval에서 omowright `connectPipe`, 스텔스는 `connectCloakProfile` (`../../SKILL.md` Tier 2, the `browser` skill's `references/owned-engine/`)
+3. `mcp__playwright__*` 도구는 그 MCP가 이미 세션에 연결된 경우에만 쓴다. 없으면 새로 설치하지 않는다 ([playwright.md](playwright.md))
 
 ## Phase 2 — 수동 개입 (옵션)
 
@@ -233,7 +232,7 @@ Tier 1 추출 폴백 전용이며 에이전트가 직접 브라우저를 다루
 
 ```bash
 # 범용 웹 (Jina Reader — 일반 HTML만, WAF 사이트엔 무효)
-curl -s "https://r.jina.ai/{URL}"
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/{URL}"
 
 # yt-dlp — 1,858 사이트 미디어 메타데이터
 yt-dlp --dump-json "URL"
@@ -290,7 +289,7 @@ yt-dlp --write-sub --write-auto-sub --sub-lang "en,ko" --skip-download -o "/tmp/
 | 파일 | 언제 읽는가 | 무엇을 다루는가 |
 |------|-------------|-----------------|
 | [`tls-impersonate.md`](tls-impersonate.md) | curl_cffi 격자가 전부 `challenge`/`blocked`로 끝날 때, 새 impersonate 타겟을 `waf_profiles.yaml`에 추가할 때 | curl_cffi로 Safari/Chrome/Firefox TLS(JA3/JA4) 지문 복제하는 방법, WAF(Akamai/Cloudflare/F5 등)별 최적 타겟 조합, 임퍼소네이션 타겟 버전 목록, `tls_impersonate_avoid`의 실증 근거 |
-| [`playwright.md`](playwright.md) | engine이 Playwright fallback으로 넘어가는데 MCP/Local Chrome 중 어디로 갈지 확인 필요할 때 | Approach 1 (`mcp__playwright__*` — Cloudflare급 챌린지), Approach 2 (Local Node + `channel:'chrome'` + stealth — Akamai Bot Manager급), 템플릿 파라미터 규격 |
+| [`playwright.md`](playwright.md) | engine이 Playwright fallback으로 넘어가는데 MCP/Local Chrome 중 어디로 갈지 확인 필요할 때 | Approach 1 (이미 연결된 경우의 `mcp__playwright__*`, 없으면 omowright owned engine — Cloudflare급 챌린지), Approach 2 (Local Node + `channel:'chrome'` + stealth — Akamai Bot Manager급), 템플릿 파라미터 규격 |
 | [`fallback.md`](fallback.md) | `verdict`가 애매하거나 Phase 전환 타이밍 결정 필요할 때 | engine의 Phase 0→1→2→3 에스컬레이션 원칙, 응답 성공/실패 판정 기준 세부, 각 Phase 종료 조건 |
 | [`metadata.md`](metadata.md) | 본문 전체를 못 가져왔지만 제목·요약·가격·저자 같은 핵심만이라도 필요할 때 | OGP 메타 태그, JSON-LD (Schema.org), Twitter Card 파싱, 구조화 데이터 추출 패턴 |
 
@@ -298,7 +297,7 @@ yt-dlp --write-sub --write-auto-sub --sub-lang "en,ko" --skip-download -o "/tmp/
 
 | 파일 | 언제 읽는가 | 무엇을 다루는가 |
 |------|-------------|-----------------|
-| [`jina.md`](jina.md) | WAF 없는 일반 웹(블로그·뉴스·Wiki)의 깨끗한 마크다운 추출 필요할 때 | `r.jina.ai/URL` 한 줄로 Puppeteer 기반 JS SPA 렌더링, 마크다운 변환, 무료 500 RPM, API 키 불필요 |
+| [`jina.md`](jina.md) | WAF 없는 일반 웹(블로그·뉴스·Wiki)의 깨끗한 마크다운 추출 필요할 때 | `r.jina.ai/URL` + `JINA_API_KEY` Bearer 헤더(익명 호출은 401)로 Puppeteer 기반 JS SPA 렌더링, 마크다운 변환 |
 | [`cache-archive.md`](cache-archive.md) | 원본 사이트가 차단됐지만 과거 스냅샷으로라도 접근 필요할 때 | Wayback Machine CDX API, archive.today, AMP Cache (Google Cache는 2024-07 종료됨) |
 | [`rss.md`](rss.md) | 뉴스·블로그·커뮤니티의 시계열 업데이트를 구조화해 받고 싶을 때 | RSS/Atom 자동 발견, 피드 파싱, 인증 불필요 — 가장 깔끔한 시계열 데이터 소스 |
 

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/insane-search/fallback.md

@@ -23,9 +23,12 @@
 
 ## Phase 1: 경량 프로브 (병렬)
 
+> **R1 ([README.md](README.md))**: 차단된 URL에는 WebFetch나 즉흥 curl을 쓰지 않는다. `python3 -B -m engine "<URL>"`이
+> 아래 Phase 1-3(curl_cffi 프로브, Referer/변환/디바이스 격자, 서로게이트, Playwright 폴백)을 실행한다.
+> 이 문서는 `--trace` 출력을 읽기 위한 단계 설명이다.
+
 **먼저 시도** (동시):
-- WebFetch (Claude 내장)
-- Jina Reader (기본 / JSON / SPA 모드)
+- Jina Reader (기본 / JSON / SPA 모드, `JINA_API_KEY` 있을 때만)
 - curl Chrome Desktop UA
 
 **아직 성공 없으면 추가 시도**:
@@ -34,7 +37,6 @@
 - URL 변형 시도: `.json`, `/rss`, `/feed`
 
 **사이드카** (1차와 동시, low-trust):
-- Google AMP 캐시
 - archive.today
 - Wayback Machine
 → **원본이 하나라도 성공하면 사이드카는 참고만.** 전부 실패 시에만 사이드카 채택 (provenance 태깅 필수)
@@ -90,7 +92,7 @@ for target in TARGETS:
         session = requests.Session(impersonate=target)
         session.headers.update(HEADERS)
         resp = session.get("{URL}", timeout=20)
-        if resp.status_code == 200 and len(resp.text) > 300:
+        if resp.status_code == 200 and len(resp.text) >= 3072 and not any(m in resp.text for m in ("Access Denied", "Just a moment...", "DataDome", "sec-if-cpt-container")):
             # 성공 — JSON-LD도 같이 추출
             break
     except:
@@ -103,7 +105,7 @@ for target in TARGETS:
 
 ---
 
-## Phase 3: Playwright MCP (브라우저)
+## Phase 3: 브라우저 (owned engine, 또는 이미 연결된 Playwright MCP)
 
 **조건**: Phase 2도 실패 또는 JS 챌린지/CAPTCHA 감지
 
@@ -114,7 +116,9 @@ browser_evaluate → () => document.body.innerText  (Light Mode — 먼저)
 필요 시 browser_snapshot → 접근성 트리 전체
 ```
 
-**API 발견**: `browser_network_requests`로 숨은 JSON API를 찾으면 이후 curl_cffi로 재사용 가능.
+위 흐름은 Playwright MCP가 이미 세션에 연결된 경우의 도구 이름이다. 없으면 같은 단계를 Tier 2a owned engine(js eval의 omowright `connectPipe` / `connectCloakProfile`)으로 실행한다 — [README.md](README.md) "`needs_js_exec only` 폴백 규칙".
+
+**API 발견**: `browser_network_requests`(MCP) 또는 owned engine의 `createNetworkSnoop`(the `browser` skill's `references/owned-engine/network.md`)로 숨은 JSON API를 찾으면 이후 curl_cffi로 재사용 가능.
 
 상세: [playwright.md](playwright.md)
 

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/insane-search/jina.md

@@ -21,7 +21,7 @@ curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/{URL}"
 ### JSON 구조화 출력
 
 ```bash
-curl -H "Accept: application/json" "https://r.jina.ai/{URL}"
+curl -H "Authorization: Bearer ${JINA_API_KEY}" -H "Accept: application/json" "https://r.jina.ai/{URL}"
 ```
 
 반환: `data.{title, description, url, content, metadata, external, usage}`
@@ -31,7 +31,7 @@ curl -H "Accept: application/json" "https://r.jina.ai/{URL}"
 ### CSS 선택자 타겟팅
 
 ```bash
-curl -H "X-Target-Selector: .article-body" "https://r.jina.ai/{URL}"
+curl -H "Authorization: Bearer ${JINA_API_KEY}" -H "X-Target-Selector: .article-body" "https://r.jina.ai/{URL}"
 ```
 
 네비게이션/풋터 제거, 본문만 추출. 커뮤니티 게시판에서 특히 효과적.
@@ -39,7 +39,7 @@ curl -H "X-Target-Selector: .article-body" "https://r.jina.ai/{URL}"
 ### SPA 스트리밍 모드
 
 ```bash
-curl -H "Accept: text/event-stream" "https://r.jina.ai/{URL}"
+curl -H "Authorization: Bearer ${JINA_API_KEY}" -H "Accept: text/event-stream" "https://r.jina.ai/{URL}"
 ```
 
 JS 로딩 완료까지 대기. 동적 콘텐츠가 완전히 렌더링된 최종 버전 반환.
@@ -47,7 +47,7 @@ JS 로딩 완료까지 대기. 동적 콘텐츠가 완전히 렌더링된 최종
 ### 스크린샷
 
 ```bash
-curl -H "X-Respond-With: screenshot" "https://r.jina.ai/{URL}"
+curl -H "Authorization: Bearer ${JINA_API_KEY}" -H "X-Respond-With: screenshot" "https://r.jina.ai/{URL}"
 ```
 
 GCS 서명 URL 반환 (4시간 유효). 비주얼 검증 용도.
@@ -55,7 +55,7 @@ GCS 서명 URL 반환 (4시간 유효). 비주얼 검증 용도.
 ### PDF 처리
 
 ```bash
-curl -s "https://r.jina.ai/https://example.com/file.pdf"
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/https://example.com/file.pdf"
 ```
 
 PDF → 마크다운 자동 변환. 페이지 수 메타데이터 포함.
@@ -63,33 +63,33 @@ PDF → 마크다운 자동 변환. 페이지 수 메타데이터 포함.
 ### 쿠키 전달 (인증 사이트)
 
 ```bash
-curl -H "X-Set-Cookie: session=abc123" "https://r.jina.ai/{URL}"
+curl -H "Authorization: Bearer ${JINA_API_KEY}" -H "X-Set-Cookie: session=abc123" "https://r.jina.ai/{URL}"
 ```
 
 ### 링크 보존
 
 ```bash
-curl -H "X-With-Links: true" "https://r.jina.ai/{URL}"
+curl -H "Authorization: Bearer ${JINA_API_KEY}" -H "X-With-Links: true" "https://r.jina.ai/{URL}"
 ```
 
 ### 캐시 제어
 
 ```bash
 # 캐시 우회 (실시간 필요 시)
-curl -H "X-No-Cache: true" "https://r.jina.ai/{URL}"
+curl -H "Authorization: Bearer ${JINA_API_KEY}" -H "X-No-Cache: true" "https://r.jina.ai/{URL}"
 
 # 캐시 TTL 지정 (초)
-curl -H "X-Cache-Tolerance: 600" "https://r.jina.ai/{URL}"
+curl -H "Authorization: Bearer ${JINA_API_KEY}" -H "X-Cache-Tolerance: 600" "https://r.jina.ai/{URL}"
 ```
 
 ### 순수 텍스트 / 원본 HTML
 
 ```bash
 # body.innerText만
-curl -H "X-Respond-With: text" "https://r.jina.ai/{URL}"
+curl -H "Authorization: Bearer ${JINA_API_KEY}" -H "X-Respond-With: text" "https://r.jina.ai/{URL}"
 
 # 원본 HTML
-curl -H "X-Respond-With: html" "https://r.jina.ai/{URL}"
+curl -H "Authorization: Bearer ${JINA_API_KEY}" -H "X-Respond-With: html" "https://r.jina.ai/{URL}"
 ```
 
 ## 검증된 성공 사이트
@@ -131,6 +131,6 @@ curl -H "X-Respond-With: html" "https://r.jina.ai/{URL}"
 Jina JSON 모드의 `external.alternate`에서 사이트의 RSS URL이 자동 노출됨:
 
 ```bash
-curl -H "Accept: application/json" "https://r.jina.ai/{URL}" | \
+curl -H "Authorization: Bearer ${JINA_API_KEY}" -H "Accept: application/json" "https://r.jina.ai/{URL}" | \
 python3 -c "import sys,json; print(json.load(sys.stdin)['data'].get('external',{}))"
 ```

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/insane-search/naver.md

@@ -26,10 +26,10 @@ Jina Reader로 완전 접근 가능.
 
 ```bash
 # 기사 목록
-curl -s "https://r.jina.ai/https://news.naver.com/"
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/https://news.naver.com/"
 
 # 개별 기사
-curl -s "https://r.jina.ai/https://n.news.naver.com/article/{press_id}/{article_id}"
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/https://n.news.naver.com/article/{press_id}/{article_id}"
 ```
 
 ## 네이버 증권
@@ -37,7 +37,7 @@ curl -s "https://r.jina.ai/https://n.news.naver.com/article/{press_id}/{article_
 Jina Reader로 실시간 주가, 주요 뉴스 접근.
 
 ```bash
-curl -s "https://r.jina.ai/https://finance.naver.com/item/main.naver?code={종목코드}"
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/https://finance.naver.com/item/main.naver?code={종목코드}"
 ```
 
 ## 네이버 금융 시세 (비공식, 무인증)

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/insane-search/playwright.md

@@ -65,7 +65,7 @@ bun install
 ### 호출 (engine 내부)
 
 ```python
-from insane_search.engine.executor import run_playwright_fallback
+from engine.executor import run_playwright_fallback   # 스킬 디렉터리에서 실행 (패키지는 engine/)
 
 attempt, html = run_playwright_fallback(
     "https://example.com/path",

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/insane-search/rss.md

@@ -13,7 +13,7 @@ python3 -c "import feedparser" 2>/dev/null || pip install feedparser -q
 Jina Reader JSON 모드로 사이트의 RSS URL을 자동 탐지:
 
 ```bash
-curl -sH "Accept: application/json" "https://r.jina.ai/{URL}" | \
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" -H "Accept: application/json" "https://r.jina.ai/{URL}" | \
   python3 -c "import sys,json; print(json.load(sys.stdin)['data'].get('external',{}).get('alternate',[]))"
 ```
 

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/insane-search/tls-impersonate.md

@@ -59,11 +59,11 @@ def cffi_fetch(url, locale="ko-KR"):
 
 generic alias는 항상 최신 버전으로 해석된다. **2026년에 chrome99 같은 옛 버전은 WAF가 의심하므로 generic alias 사용 권장.**
 
-| Alias | 해석 (2026.04) | 용도 |
+| Alias | 해석 (v0.15.0) | 용도 |
 |-------|---------------|------|
-| `safari` | safari260 | **한국 사이트 최적** (쿠팡, 에펨코리아) |
+| `safari` | safari2601 | **한국 사이트 최적** (쿠팡, 에펨코리아) |
 | `chrome` | chrome146 | 범용 (Cloudflare, Akamai) |
-| `firefox` | firefox135 | chrome/safari 실패 시 대안 |
+| `firefox` | firefox147 | chrome/safari 실패 시 대안 |
 | `chrome_android` | chrome131_android | 모바일 API 엔드포인트 |
 | `safari_ios` | safari260_ios | iOS 모바일 |
 
@@ -71,15 +71,20 @@ generic alias는 항상 최신 버전으로 해석된다. **2026년에 chrome99
 <summary>핀 버전 전체 (클릭)</summary>
 
 ```
+edge99, edge101,
 chrome99, chrome100, chrome101, chrome104, chrome107, chrome110,
 chrome116, chrome119, chrome120, chrome123, chrome124, chrome131,
 chrome133a, chrome136, chrome142, chrome145, chrome146,
-chrome131_android, edge99, edge101,
-safari15_3, safari15_5, safari17_0, safari17_2_ios,
-safari18_0, safari18_0_ios, safari260, safari260_ios,
-firefox133, firefox135
+chrome99_android, chrome131_android,
+safari153, safari155, safari170, safari172_ios,
+safari180, safari180_ios, safari184, safari184_ios,
+safari260, safari2601, safari260_ios,
+firefox133, firefox135, firefox144, firefox147,
+tor145
 ```
 
+구 표기(`safari15_3`, `safari15_5`, `safari17_0`, `safari17_2_ios`, `safari18_0`, `safari18_0_ios`, `safari18_4`, `safari18_4_ios`)는 deprecated alias로 아직 받는다.
+
 </details>
 
 ## WAF별 최적 전략

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

@@ -119,6 +119,8 @@ Before the first task command, create one `RUN_TMP=$(mktemp -d)` per task, track
 At task end, after owned processes exit, remove only owned directories, including runtime caches. Never wipe shared caches; retain worktrees still needed by open PRs and any parent directory containing them.
 
 ## 0. Survey the skills, gather context, then size the work
+This section records into the notepad, so run section 2's `NOTE=`
+command first; section 2 then initialises that same file.
 First, survey the loaded skill list and read the description of each
 loosely relevant skill. Decide explicitly which skills this task will
 use and prefer using every genuinely applicable one — name them in the