@litfamily/litopencode 1.0.0

package/README-Ko-KR.md

@@ -0,0 +1,252 @@
+<p align="center"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litopencode@1.0.0/docs/assets/cover.webp" width="100%" alt="LitOpenCode v5 armory cover" /></p>
+
+# LitOpenCode
+
+[English](README.md) · [한국어](README-Ko-KR.md)
+
+**Keep the work lit.**
+
+<p align="center"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litopencode@1.0.0/docs/assets/readme/litopencode-wordmark.svg" width="480" alt="LITOPENCODE 디스플레이 타입" /></p>
+<p align="center"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litopencode@1.0.0/docs/assets/readme/litopencode-clay-icon.png" width="160" alt="LitOpenCode 클레이 마크" /></p>
+
+> **불씨를 건네받았다.**<br>
+> **이제, 당신의 작업에 옮길 차례다.**
+
+고치고 싶은 버그 하나. 만들고 싶은 화면 하나. 끝내고 싶은 프로젝트 하나.
+
+시작은 짧은 한 줄이면 됩니다. 어려운 건 그다음입니다. 대화가 길어지고 세션이
+바뀌면, 어디까지 했는지부터 다시 짚어야 합니다. 어떤 결정을 내렸는지,
+무엇을 확인했는지, 다음에는 무엇을 해야 하는지.
+
+**LIT은 그 불씨를 남깁니다.** 목표와 계획, 확인한 결과, 다음에 할 일을 프로젝트에
+기록합니다. 다음 세션에서 그 기록을 읽고 작업을 이어갈 수 있도록.
+
+**대화가 끝난 자리에서, 다음 작업이 시작되도록.**
+
+LitOpenCode는 쓰던 **OpenCode**에 워크플로 agent, 슬래시 명령, 로컬 근거 기록을
+추가합니다. 다른 LitFamily 제품을 설치하지 않아도 독립적으로 사용할 수 있습니다.
+“꺼지지 않는 불”은 프로그램이 끝없이 돌아간다는 뜻이 아닙니다.
+**세션이 끝나도, 이어갈 작업을 남긴다는 뜻입니다.**
+
+```text
+계획하기 → 만들기 → 확인하기 → 다음 작업에 건네기
+```
+
+[설치](#30초-설치) · [처음 사용하기](#처음-사용하기) · [주요 경로](#주요-경로) · [안전](#안전과-업데이트) · [문서](#문서)
+
+## 작은 lit 작업부터 시작하기
+
+프롬프트에 `lit`을 붙이거나 `/lit`을 입력해 LitOpenCode 워크플로를 선택하세요. 모델과 권한 질문은 OpenCode가 담당하고 plugin은 프로젝트 기록을 남깁니다.
+
+| 프롬프트 또는 경로 | 효과 |
+| --- | --- |
+| `lit` 또는 `/lit` | 확인 기준이 있는 작은 작업을 시작합니다. |
+| `handoff` 또는 `/lit-handoff` | 현재 결과와 다음 할 일을 다음 세션으로 건넵니다. |
+| `lit-plan` | 구현 전에 계획을 준비합니다. |
+| `/start-work <승인된 계획>` | 승인한 계획을 실행합니다. |
+| `/review-work` | 변경과 근거를 검토합니다. |
+| `/litresearch` | 출처를 남기는 제공된 조사 경로를 사용합니다. |
+
+경로를 선택했다는 사실만으로 모델 실행이나 화면 확인을 증명할 수 없습니다.
+
+패키지의 참조 원본은 `vendor/handoff/`와 `vendor/scientific-visualization/`의
+canonical 경로를 사용합니다. 번호가 붙은 license·provenance 파일명은 출처 기록으로
+그대로 보존합니다.
+
+## 실제 경로와 편집 이미지
+
+`lit` 또는 `/lit`으로 범위가 정해진 작업을 시작하고, `handoff` 또는 `/lit-handoff`로 확인한 결과와 다음 단계를 건넵니다. `lit-plan`은 계획을 준비하고, `/start-work <승인된 계획>`은 승인한 계획을 실행하며, `/review-work`는 변경과 근거를 검토하고, `/litresearch`는 제공된 출처 기반 조사 경로를 사용합니다. 기대하는 효과는 다음 세션이 이어갈 수 있는 프로젝트별 목표·근거·다음 단계 기록입니다. 호스트 제약도 분명합니다. 모델 실행과 권한 질문은 OpenCode가 담당하고 plugin은 경로와 기록을 제공하므로, 경로를 선택했다는 사실만으로 실행이나 화면 확인을 증명할 수 없습니다.
+
+<p align="center"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litopencode@1.0.0/docs/assets/litopencode-ignition-1600.webp" width="48%" alt="LitOpenCode 점화 장치" /><img src="https://cdn.jsdelivr.net/npm/@litfamily/litopencode@1.0.0/docs/assets/litopencode-continuity-1600.webp" width="48%" alt="LitOpenCode 연속 장치" /></p>
+
+<p align="center"><a href="docs/assets/readme/ignition-film.mp4"><img src="docs/assets/readme/poster.png" width="720" alt="Ignition 모션 포스터" /></a></p>
+
+포스터를 선택하면 선택형 영상을 엽니다. README에서 자동 재생하지 않습니다.
+
+소스 트리의 `docs/assets/cover.svg`는 편집 가능한 저대역폭 대체 표지이며, 위 WebP는 제품 강조 표지입니다.
+
+## 30초 설치
+
+Node.js/npm과 OpenCode가 준비된 환경에서 실행하세요.
+
+scoped 패키지를 Node.js/npm과 OpenCode가 준비된 환경에서 설치하세요.
+
+```sh
+LIT_PACKAGE='@litfamily/litopencode@latest'
+npm exec --package "$LIT_PACKAGE" -- litopencode install
+```
+
+OpenCode를 재시작하고 **Tab**을 눌러 **lit-loop**를 선택합니다. 모델 접근과 인증은
+OpenCode의 provider 설정을 사용합니다. 설치 과정에서 모델, 권한, 출력 스타일을
+선택할 수 있으며 기본 권한은 safe/ask-first입니다.
+
+```sh
+npm exec --package @litfamily/litopencode@latest -- litopencode install --dry-run  # 변경 사항 미리 보기
+npm exec --package @litfamily/litopencode@latest -- litopencode install --yes     # 기본값 사용, 저장된 선택 유지
+npm exec --package @litfamily/litopencode@latest -- litopencode doctor            # 패키지와 설정 상태 확인
+```
+
+설치 도구는 OpenCode 설정 루트에 플러그인과 native 명령·스킬 파일을 등록합니다.
+route 파일은 `~/.config/opencode/litopencode.json`이며 `XDG_CONFIG_HOME`을 지정하면
+설정 루트가 달라집니다. 기존 custom route는 사용자 소유로 유지됩니다.
+custom root, 모델 선택, 터미널 정책, 무인 설치는 [상세 안내](docs/reference-Ko-KR.md#설치)를 참고하세요.
+
+이 checkout의 패키지는 `@litfamily/litopencode@1.0.0`입니다. registry의 `@latest`는 다를 수 있으므로
+정확한 버전이 필요하면 `npm view @litfamily/litopencode version`으로 확인하세요.
+
+## 처음 사용하기
+
+작은 작업 하나부터 시작하세요. 빈 작업 폴더를 OpenCode에서 열고, `lit-loop`를
+선택한 뒤 채팅에 다음을 입력합니다.
+
+```text
+lit 외부 의존성 없이 index.html 하나로 할 일 목록을 만들고, 추가와 완료 표시를 확인한 뒤 다음 할 일을 남겨줘.
+```
+
+첫 결과는 `index.html`입니다. 직접 열어 항목 추가와 완료 표시를 확인하세요.
+모델의 완료 보고와 실제 동작이 다르면 그 차이를 알려주세요.
+작업을 다시 시작할 때는 `/lit-recap`으로 기록을 읽고 이어갈 일을 확인합니다.
+
+`/lit`도 같은 워크플로를 시작합니다. 계획 검토가 필요한 작업은 `lit-plan`에서 계획을
+작성하고 승인한 뒤 `/start-work`로 실행하며 `/review-work`로 마무리합니다.
+승인된 계획은 `lit-implement`가 실행합니다. planner는 명시적인 사용자 승인을 기다립니다.
+파일 편집이나 shell 실행 권한은 없습니다.
+
+진행 상황과 근거는 `.litopencode/litgoal/`에 저장합니다. OpenCode에는 native goal
+primitive가 없으므로 이 프로젝트별 로컬 기록으로 작업을 재개합니다. 정적 스킬은
+문서에 명시된 경로로 선택했을 때 작업 지침을 제공합니다.
+
+## Ignition mark
+
+<p align="center"><img src="docs/assets/readme/ascii-readme.svg" width="480" alt="LIT ASCII B 마크" /></p>
+
+<details>
+<summary>ASCII 로고 복사</summary>
+
+```text
+                             ▄▄▄▄
+                   ▗███▌   ▗██████▖
+ ▗▄▄▄▄▄          ▗▟████▌   ▝██████▘
+ ▐█████        ▗▟██████▌    ▝▀▜█▀▘
+ ▐█████      ▗▟███████▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄
+ ▐█████    ▗▟█████████████████████████ ▐█▀
+ ▐█████    ████████████████████████████▀
+ ▐█████    ██▛▘   ▄ ▄▄▄▄▖▄▄▄▄▄▄▄▄▄▄▄▄▄▖
+ ▐█████    ▀    ▄██ ████▌█████████████▌
+ ▐█████       ▄████ ████▌█████████████▌
+ ▐█████     ▄█████▛                                 litopencode
+ ▐█████  ▗▟█████▀▘       ▄▄▄▄▄     ▗▖
+ ▐█████ ▐█████▀          █████     ▐▛▀
+ ▐█████ ▐███▀            █████
+ ▐█████ ▐█▀              █████
+ ▐█████ ▝                █████
+ ▐█████▄▄▄▄▄▄▄▖          █████
+ ▐███████████▛           █████
+ ▐██████████▀            █████
+
+```
+
+</details>
+
+<p align="center">
+<a href="#30초-설치"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litopencode@1.0.0/docs/assets/readme/badge-version.svg" alt="1.0.0" /></a>
+<a href="LICENSE"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litopencode@1.0.0/docs/assets/readme/badge-license.svg" alt="MIT 라이선스" /></a>
+</p>
+
+<p align="center">
+<a href="docs/reference-Ko-KR.md"><img src="docs/assets/readme/lucide-book-open.svg" width="16" alt="" /> 문서</a> &nbsp; <a href="#30초-설치">설치</a> &nbsp; <a href="#ignition-motion"><img src="docs/assets/readme/lucide-play.svg" width="16" alt="" /> Ignition</a> &nbsp; <a href="LICENSE"><img src="docs/assets/readme/lucide-shield-check.svg" width="16" alt="" /> MIT</a>
+</p>
+
+소스 트리에는 편집 가능한 저대역폭 벡터 대체 표지 `docs/assets/cover.svg`가 남아 있습니다.
+
+## OpenCode 안에서 어떻게 동작하나요?
+
+OpenCode는 설정 파일에서 플러그인을 불러옵니다. agent와 채팅·명령 경로는
+워크플로와 설치된 스킬을 선택합니다. 도구와 작업 수명주기 hook이 프로젝트에
+기록을 남기며, 돌아왔을 때 그 기록을 읽고 작업을 이어갈 수 있습니다.
+
+```mermaid
+flowchart TD
+    Config["OpenCode 설정: opencode.json / opencode.jsonc"] --> Plugin["LitOpenCode 플러그인"]
+    Plugin --> Routes["agent와 채팅 / 명령 경로"]
+    Plugin --> Tools["lit / litwork / start-work 도구"]
+    Plugin --> Hooks["메시지·도구·세션 hook"]
+    Routes --> Skills["설치된 스킬과 canonical 원본"]
+    Tools --> Records["프로젝트 기록: .litopencode/litgoal/"]
+    Hooks -->|작업 수명주기 이벤트| Records
+    Records -->|명시적인 recap 요청| Routes
+    classDef host fill:#080D14,stroke:#F2EFDF,color:#F2EFDF
+    classDef lit fill:#080D14,stroke:#FF6337,color:#F2EFDF
+    classDef local fill:#080D14,stroke:#D7F75B,color:#F2EFDF
+    class Config host
+    class Plugin,Routes,Tools,Hooks lit
+    class Skills,Records local
+```
+
+## LITFAMILY
+
+![LitClaude, LitHermes, LitCodex, LitOpenCode, LitGrok을 표현한 다섯 중장갑 머신](docs/assets/readme/litfamily-machines.png)
+
+LitClaude · LitHermes · LitCodex · LitOpenCode · LitGrok.
+다섯 중장갑 머신으로 다섯 제품을 표현한 일러스트입니다. 각 제품은 자신이 지원하는 도구에서 독립적으로 동작합니다.
+
+## 주요 경로
+
+| 경로 | 용도 |
+| --- | --- |
+| `/lit` 또는 `/litwork` | 범위가 분명한 작업 구현과 검증 |
+| `/lit-plan` → `/start-work` → `/review-work` | 계획, 승인, 실행, 검토 |
+| `/litresearch` 또는 `/lit-research` | 출처 근거를 남기는 연구, 순차 대체 경로 지원 |
+| `/lit-handoff` | 작업 재개 맥락 저장. 정확히 `handoff`만 입력해도 연결 |
+| `/lit-recap` | 로컬 상태의 짧은 요약 |
+| `/lit-code`, `/debugging`, `/refactor` | 코딩, 디버깅, 리팩터링 지침 |
+| `/lit-korean` | 의미를 유지하며 한국어 문장 다듬기 |
+| `/lit-scientific-visualization` | 패키지에 포함된 과학 시각화 워크플로 |
+
+Autoresearch, Autoconference, Wikify, UI/UX는 [전체 경로 안내](docs/reference-Ko-KR.md#주요-명령)에,
+두 가지 rule 처리 경로는 [규칙 엔진 상세 안내](docs/reference.md#safety-and-updates)에서 확인하세요.
+이전 스킬 이름은 한 릴리스 동안 별칭으로 연결됩니다. [마이그레이션 안내](docs/migration.md#skill-id-renames)를 확인하세요.
+
+## 안전과 업데이트
+
+- `lit-plan`의 `edit`, `bash`, `task`는 계속 거부됩니다. `balanced`와 `yolo`는 명시적으로
+  선택해야 하며 planner 보호나 하위 agent의 재귀 위임 금지를 해제하지 않습니다.
+- 공개 자료를 검색할 때는 목적지, redirect, byte 한도를 검사합니다. 가져온 본문은 데이터로 취급합니다.
+- 대화형 시작과 install/doctor 성공 후 foreground 업데이트 검사가 실행될 수 있습니다.
+  `--no-auto-update` 또는 `LITOPENCODE_NO_AUTO_UPDATE=1`로 자동 업데이트를 끌 수 있습니다.
+- 스킬 학습 결과는 명시적인 apply 명령이 있어야 반영됩니다. 학습의 review·변경·rollback·curator는
+  POSIX를 지원하며 Windows에서는 해당 경계를 차단합니다. 설치, doctor, 수동 조회에는
+  이 제한이 적용되지 않습니다. [학습 루프 상세 안내](docs/reference.md#skill-learning-loop).
+
+## 제거
+
+`litopencode uninstall` 명령은 없습니다. OpenCode의 `opencode.jsonc` 또는 custom root의
+`opencode.json`에서 `plugin` 배열의 `@litfamily/litopencode`·`@litfamily/litopencode@<version>` 항목을 제거하세요.
+전역 설치를 했다면 npm binary도 제거합니다.
+
+```sh
+npm uninstall -g @litfamily/litopencode
+```
+
+설치된 명령·스킬 파일은 소유 관계를 확인한 뒤 설치 도구가 관리하는 복사본만 제거하세요.
+사용자가 만든 파일과 수정 내용은 보존합니다. route가 필요하면 `litopencode.json`을,
+작업을 재개할 계획이라면 프로젝트의 `.litopencode/` 기록을 남기세요. 제거 후 OpenCode를
+재시작합니다. [제거 상세 안내](docs/reference-Ko-KR.md#제거).
+
+## 문서
+
+- [워크플로 상세 안내](docs/reference-Ko-KR.md): 모델, 권한, host 연결, 명령, 검증 방법
+- [English reference](docs/reference.md): 전체 스킬 목록, 학습 루프, 규칙 엔진 포함
+- [마이그레이션 안내](docs/migration.md)
+- [터미널 마크와 활성화 확인 문구](docs/lit-mark.md)
+- [Changelog](CHANGELOG.md)
+- [출시 담당자 체크리스트](docs/release-checklist.md) (저장소 전용)
+
+- [기여 안내](CONTRIBUTING.md) · [지원](SUPPORT.md) · [보안 제보](SECURITY.md)
+- [행동 규범](CODE_OF_CONDUCT.md) · [개인정보와 네트워크 동작](docs/privacy.md)
+
+## Ignition motion
+
+[![Ignition 모션 그래픽 포스터](docs/assets/readme/poster.png)](docs/assets/readme/ignition-film.mp4)
+
+[10초 영상 보기](docs/assets/readme/ignition-film.mp4) · [애니메이션 GIF](docs/assets/readme/ignition-readme.gif) · [Lucide 아이콘 라이선스](docs/assets/readme/Lucide-LICENSE.txt) · [ASCII 글꼴 라이선스](docs/assets/readme/JetBrainsMono-OFL.txt)

package/README.md

@@ -0,0 +1,252 @@
+<p align="center"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litopencode@1.0.0/docs/assets/cover.webp" width="100%" alt="LitOpenCode v5 armory cover" /></p>
+
+# LitOpenCode
+
+[English](README.md) · [한국어](README-Ko-KR.md)
+
+**Keep the work lit.**
+
+<p align="center"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litopencode@1.0.0/docs/assets/readme/litopencode-wordmark.svg" width="480" alt="LITOPENCODE display type" /></p>
+<p align="center"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litopencode@1.0.0/docs/assets/readme/litopencode-clay-icon.png" width="160" alt="LitOpenCode clay mark" /></p>
+
+> **The spark is yours.**<br>
+> **Bring it to your work.**
+
+A bug to fix. A screen to build. A project to finish.
+
+Starting takes a line. Continuing takes more. When a conversation grows long or a
+session ends, you have to recover where you stopped: what you decided, what you
+checked, and what comes next.
+
+**LIT keeps that spark in the project.** It records the goal, the plan, verified
+results, and the next steps so another session can read them and continue.
+
+**Where one conversation ends, the next piece of work begins.**
+
+LitOpenCode adds workflow agents, slash commands, and a local evidence ledger to
+**OpenCode**. Keep the tool you already use; no other LitFamily product is required.
+A lasting flame does not mean a program runs forever. **It means leaving work ready
+to continue when the session ends.**
+
+```text
+Plan → Build → Verify → Leave the next step
+```
+
+[Install](#install-in-30-seconds) · [First use](#first-use) · [Core routes](#core-routes) · [Safety](#safety-and-updates) · [Docs](#documentation)
+
+## Start with one lit task
+
+Append `lit` to a prompt, or use `/lit`, to select the LitOpenCode workflow. OpenCode owns the model and permission prompts; the plugin keeps project records.
+
+| Prompt or route | Effect |
+| --- | --- |
+| `lit` or `/lit` | Start a bounded task and record what was checked. |
+| `handoff` or `/lit-handoff` | Carry the current result and next step into another session. |
+| `lit-plan` | Prepare a plan before implementation. |
+| `/start-work <approved-plan>` | Execute an approved plan. |
+| `/review-work` | Review the change and evidence. |
+| `/litresearch` | Use the shipped source-backed research route. |
+
+Selecting a route does not claim that the model ran or that a visual check passed.
+
+The packaged reference corpora use the canonical paths `vendor/handoff/` and
+`vendor/scientific-visualization/`. Their numbered license and provenance filenames
+remain source-attribution records.
+
+## Practical routes and visual cues
+
+Use `lit` or `/lit` to start a bounded task; `handoff` or `/lit-handoff` carries the checked result and next step; `lit-plan` prepares a plan; `/start-work <approved-plan>` executes an approved plan; `/review-work` checks the change and its evidence; and `/litresearch` uses the shipped source-backed research route. The expected effect is a project-local goal, evidence, and next-step record that another session can resume. The host limit is explicit: OpenCode owns model execution and permission prompts, while the plugin supplies routes and records; selecting a route does not prove execution or a visual check.
+
+<p align="center"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litopencode@1.0.0/docs/assets/litopencode-ignition-1600.webp" width="48%" alt="LitOpenCode ignition apparatus" /><img src="https://cdn.jsdelivr.net/npm/@litfamily/litopencode@1.0.0/docs/assets/litopencode-continuity-1600.webp" width="48%" alt="LitOpenCode continuity apparatus" /></p>
+
+<p align="center"><a href="docs/assets/readme/ignition-film.mp4"><img src="docs/assets/readme/poster.png" width="720" alt="Ignition motion poster" /></a></p>
+
+The poster opens the optional film; this README keeps motion opt-in.
+
+The retained `docs/assets/cover.svg` is the editable, low-bandwidth fallback; the WebP above is the product emphasis export.
+
+
+
+## Install in 30 seconds
+
+Install the scoped package with Node.js/npm and OpenCode available:
+
+```sh
+LIT_PACKAGE='@litfamily/litopencode@latest'
+npm exec --package "$LIT_PACKAGE" -- litopencode install
+```
+
+Restart OpenCode, press **Tab**, and select **lit-loop**. Model access and credentials
+come from your OpenCode provider setup. The installer offers model, permission, and
+output-style choices; the default permission mode is safe/ask-first.
+
+```sh
+npm exec --package @litfamily/litopencode@latest -- litopencode install --dry-run  # preview changes
+npm exec --package @litfamily/litopencode@latest -- litopencode install --yes     # use defaults; preserve saved choices
+npm exec --package @litfamily/litopencode@latest -- litopencode doctor            # inspect package and configuration health
+```
+
+Installation registers the plugin and native command/skill files under your OpenCode
+config root. Routes live in `~/.config/opencode/litopencode.json`; `XDG_CONFIG_HOME`
+changes that root. Existing custom routes remain user-owned. See the
+[installation and model reference](docs/reference.md#install) for custom roots,
+provider choices, terminal policy, and unattended setup.
+
+This checkout is `@litfamily/litopencode@1.0.0`. Registry `@latest` can differ; inspect it with
+`npm view @litfamily/litopencode version` when an exact version matters.
+
+## First use
+
+Start with one small task. Open an empty project folder in OpenCode, select
+`lit-loop`, and send:
+
+```text
+lit Build a to-do list in one index.html with no dependencies; check adding and completing items, then leave results and next steps.
+```
+
+Your first result is `index.html`. Open it and try adding and completing an item.
+If the behavior differs from the completion report, tell the agent what happened.
+When you return, use `/lit-recap` to read the record and find the next step.
+
+Use `/lit` for the same workflow. For work that needs a reviewed plan, select
+`lit-plan`, approve the plan, then run `/start-work`; finish with `/review-work`.
+`lit-implement` executes the approved plan. The planner waits for explicit user
+confirmation and cannot edit files or run shell commands.
+
+Progress and evidence live in `.litopencode/litgoal/`. OpenCode does not expose a
+native goal primitive; this repository-local ledger supports resuming work. Static
+skills provide guidance when their documented routes select them.
+
+## Ignition mark
+
+<p align="center"><img src="docs/assets/readme/ascii-readme.svg" width="480" alt="LIT ASCII B mark" /></p>
+
+<details>
+<summary>Copy ASCII logo</summary>
+
+```text
+                             ▄▄▄▄
+                   ▗███▌   ▗██████▖
+ ▗▄▄▄▄▄          ▗▟████▌   ▝██████▘
+ ▐█████        ▗▟██████▌    ▝▀▜█▀▘
+ ▐█████      ▗▟███████▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄
+ ▐█████    ▗▟█████████████████████████ ▐█▀
+ ▐█████    ████████████████████████████▀
+ ▐█████    ██▛▘   ▄ ▄▄▄▄▖▄▄▄▄▄▄▄▄▄▄▄▄▄▖
+ ▐█████    ▀    ▄██ ████▌█████████████▌
+ ▐█████       ▄████ ████▌█████████████▌
+ ▐█████     ▄█████▛                                 litopencode
+ ▐█████  ▗▟█████▀▘       ▄▄▄▄▄     ▗▖
+ ▐█████ ▐█████▀          █████     ▐▛▀
+ ▐█████ ▐███▀            █████
+ ▐█████ ▐█▀              █████
+ ▐█████ ▝                █████
+ ▐█████▄▄▄▄▄▄▄▖          █████
+ ▐███████████▛           █████
+ ▐██████████▀            █████
+
+```
+
+</details>
+
+<p align="center">
+<a href="#install-in-30-seconds"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litopencode@1.0.0/docs/assets/readme/badge-version.svg" alt="1.0.0" /></a>
+<a href="LICENSE"><img src="https://cdn.jsdelivr.net/npm/@litfamily/litopencode@1.0.0/docs/assets/readme/badge-license.svg" alt="MIT license" /></a>
+</p>
+
+<p align="center">
+<a href="docs/reference.md"><img src="docs/assets/readme/lucide-book-open.svg" width="16" alt="" /> Docs</a> &nbsp; <a href="#install-in-30-seconds">Install</a> &nbsp; <a href="#ignition-motion"><img src="docs/assets/readme/lucide-play.svg" width="16" alt="" /> Ignition</a> &nbsp; <a href="LICENSE"><img src="docs/assets/readme/lucide-shield-check.svg" width="16" alt="" /> MIT</a>
+</p>
+
+## How LitOpenCode fits into OpenCode
+
+OpenCode loads the plugin from its config. Agents and chat/command routes select
+workflows and installed skills. Tools and lifecycle hooks keep the project records
+that you can read when you return.
+
+```mermaid
+flowchart TD
+    Config["OpenCode config: opencode.json / opencode.jsonc"] --> Plugin["LitOpenCode plugin"]
+    Plugin --> Routes["Agents and chat / command routes"]
+    Plugin --> Tools["lit / litwork / start-work tools"]
+    Plugin --> Hooks["Message, tool and session hooks"]
+    Routes --> Skills["Installed skills and canonical references"]
+    Tools --> Records["Project records: .litopencode/litgoal/"]
+    Hooks -->|Work lifecycle events| Records
+    Records -->|Explicit recap| Routes
+    classDef host fill:#080D14,stroke:#F2EFDF,color:#F2EFDF
+    classDef lit fill:#080D14,stroke:#FF6337,color:#F2EFDF
+    classDef local fill:#080D14,stroke:#D7F75B,color:#F2EFDF
+    class Config host
+    class Plugin,Routes,Tools,Hooks lit
+    class Skills,Records local
+```
+
+## LITFAMILY
+
+![Five armored machines representing LitClaude, LitHermes, LitCodex, LitOpenCode and LitGrok](docs/assets/readme/litfamily-machines.png)
+
+LitClaude · LitHermes · LitCodex · LitOpenCode · LitGrok.
+Five armored machines for five independent products, each working in its own host.
+
+## Core routes
+
+| Route | Use it to |
+| --- | --- |
+| `/lit` or `/litwork` | Implement and verify a bounded task. |
+| `/lit-plan` → `/start-work` → `/review-work` | Plan, approve, execute, and review work. |
+| `/litresearch` or `/lit-research` | Research with source evidence and a sequential fallback. |
+| `/lit-handoff` | Leave resumable context; exact bare `handoff` also works. |
+| `/lit-recap` | Read a concise recap from local state. |
+| `/lit-code`, `/debugging`, `/refactor` | Apply coding, debugging, or refactoring guidance. |
+| `/lit-korean` | Improve Korean prose without changing its meaning. |
+| `/lit-scientific-visualization` | Use the packaged scientific-visualization workflow. |
+
+The [full route and skill reference](docs/reference.md#core-commands) covers
+Autoresearch, Autoconference, Wikify, UI/UX, and the two-lane repository rules engine.
+[Migration notes](docs/migration.md#skill-id-renames) explain the one-release skill aliases.
+
+## Safety and updates
+
+- `lit-plan` keeps `edit`, `bash`, and `task` denied. `balanced` and `yolo` are explicit
+  permission choices; neither removes the planner guard or permits recursive delegation.
+- Public retrieval checks destinations, redirects, and byte limits. Retrieved text is data.
+- Interactive startup and successful install/doctor commands can run a foreground update
+  check. Use `--no-auto-update` or `LITOPENCODE_NO_AUTO_UPDATE=1` to disable automatic updates.
+- Skill learning requires an explicit apply command. Its review, mutation, rollback, and
+  curator boundaries support POSIX; on Windows those boundaries fail closed. Install,
+  doctor, and passive surfaces remain available. [Learning-loop details](docs/reference.md#skill-learning-loop).
+
+## Uninstall
+
+There is no `litopencode uninstall` command. Remove the `@litfamily/litopencode` or
+`@litfamily/litopencode@<version>` entry from the `plugin` array in OpenCode's `opencode.jsonc`
+(or a custom root's `opencode.json`). Also remove legacy `litopencode` package entries if present. If installed globally,
+remove the npm binary:
+
+```sh
+npm uninstall -g @litfamily/litopencode
+```
+
+Review installed command/skill files before removing installer-owned copies; preserve
+user-created files and edits. Keep `litopencode.json` if you still need its routes, and
+keep project `.litopencode/` ledgers if you plan to resume. Restart OpenCode after removal.
+See the [removal reference](docs/reference.md#remove).
+
+## Documentation
+
+- [Workflow reference](docs/reference.md): models, permissions, host hooks, all skills, learning loop, and reproducible verification.
+- [한국어 상세 안내](docs/reference-Ko-KR.md)
+- [Migration notes](docs/migration.md)
+- [Terminal mark and activation probes](docs/lit-mark.md)
+- [Changelog](CHANGELOG.md)
+- [Maintainer release checklist](docs/release-checklist.md) (repository only)
+
+- [Contributing](CONTRIBUTING.md) · [Support](SUPPORT.md) · [Security](SECURITY.md)
+- [Code of conduct](CODE_OF_CONDUCT.md) · [Privacy and network behavior](docs/privacy.md)
+
+## Ignition motion
+
+[![Ignition motion graphic poster](docs/assets/readme/poster.png)](docs/assets/readme/ignition-film.mp4)
+
+[Watch the 10-second film](docs/assets/readme/ignition-film.mp4) · [Animated GIF](docs/assets/readme/ignition-readme.gif) · [Lucide icon license](docs/assets/readme/Lucide-LICENSE.txt) · [ASCII font license](docs/assets/readme/JetBrainsMono-OFL.txt)

package/SECURITY.md

@@ -0,0 +1,36 @@
+# Security policy
+
+Please report suspected vulnerabilities privately before sharing exploit details.
+Examples include writes outside an approved root, unsafe deletion of user files,
+symlink or ownership bypasses, public-fetch access to private networks, credential
+exposure, or untrusted text acquiring execution authority.
+
+## Reporting
+
+If this repository's GitHub Security tab offers **Report a vulnerability**, use that
+private reporting flow. Its availability depends on repository settings; this file
+does not establish that it is enabled. No dedicated security email is published in
+this repository. If private reporting is unavailable, open a minimal issue asking
+maintainers for a private reporting channel. Do not include the vulnerability,
+exploit, credentials, private files, or identifying victim details in that issue.
+
+In the private report, include the affected package version or commit, operating
+system, Node.js and OpenCode versions, entry point, expected boundary, observed
+impact, and minimal reproduction using disposable paths and synthetic data. State
+whether the issue requires a modified installed file, unusual permissions, or a
+specific host configuration. Preserve original evidence locally and share only
+the relevant redacted portion.
+
+## Triage and fixes
+
+Maintainers assess impact, reproduce the issue, and coordinate a fix and disclosure
+with the reporter. There is no promised response deadline or published long-term
+support matrix. Include the exact affected version rather than assuming that all
+historical releases receive fixes. A fix on a local branch is not a released fix.
+
+Do not test against systems you do not own or have permission to assess. Use a
+temporary OpenCode root and synthetic files. A report never authorizes disabling
+ownership checks, broadening planner permissions, or accessing third-party data.
+
+See [Privacy](docs/privacy.md) for stored state and network behavior, and
+[Support](SUPPORT.md) for ordinary installation and configuration problems.

package/SUPPORT.md

@@ -0,0 +1,37 @@
+# Getting help
+
+Start with the [README](README.md), [workflow reference](docs/reference.md), or
+[Korean reference](docs/reference-Ko-KR.md). [Migration notes](docs/migration.md)
+cover package and skill changes. For a reproducible bug, use this repository's bug
+report template. For a proposed improvement, use its feature-request template.
+
+Include the package version or commit, Node.js/npm and OpenCode versions, operating
+system, exact command or route, expected result, and actual result. Mention whether
+you used a global install, npm execution, or a local tarball, and whether the config
+root is the default, XDG-based, or explicitly supplied. Replace identifying path
+segments with placeholders consistently.
+
+When the executable is already installed, a bounded diagnostic is:
+
+```sh
+litopencode doctor --json --no-auto-update
+```
+
+Inspect the output before sharing it. Attach the relevant redacted portion, not
+your entire OpenCode configuration, provider credentials, session export, project
+ledger, or home directory. Reproduce against a disposable config root when
+possible, and say whether the failure occurs there too. See [Privacy](docs/privacy.md).
+
+Model availability, provider billing and credentials, and host-specific UI behavior
+also depend on OpenCode and your configured provider. Separate a local CLI or hook
+result from an authenticated host-session result. Optional scientific Python
+dependencies must be installed separately when the scientific workflow needs them;
+a dependency diagnostic is not proof that a figure workflow completed.
+
+Do not work around an ownership or permission refusal by deleting unfamiliar files
+or granting the planner write access. Report the boundary and the smallest sanitized
+reproduction. For vulnerabilities use [Security](SECURITY.md), and for conduct
+concerns use the [Code of Conduct](CODE_OF_CONDUCT.md).
+
+Support is community-based. There is no guaranteed response time or paid support
+commitment in this repository.

package/bin/litopencode

@@ -0,0 +1,3 @@
+#!/bin/sh
+script_dir=$(CDPATH= cd "$(dirname "$0")" && pwd)
+exec node "$script_dir/litopencode.cjs" "$@"

package/bin/litopencode.cjs

@@ -0,0 +1,10 @@
+#!/usr/bin/env node
+"use strict";
+
+import("../dist/cli.js")
+  .then(({ main }) => main())
+  .catch((error) => {
+    const message = error instanceof Error ? error.stack || error.message : String(error);
+    console.error(message);
+    process.exitCode = 1;
+  });

package/dist/activation-managed-prompts.d.ts

@@ -0,0 +1,2 @@
+export declare const litHandoffPromptInjection: string;
+export declare const scientificVisualizationPromptInjection: string;

package/dist/activation-managed-prompts.js

@@ -0,0 +1,51 @@
+import { nativeManagedSkillReferences } from "./cli/managed-skill-assets.js";
+import { scientificVisualizationBanner } from "./scientific-visualization-banner.js";
+import { readManagedSkillAsset, readStaticSkillBody } from "./activation-prompt-utils.js";
+const litHandoffBanner = "▲ LIT · lit-handoff";
+export const litHandoffPromptInjection = `${litHandoffBanner}
+<lit-handoff-mode>
+First model-emitted line of your reply MUST be exactly:
+
+${litHandoffBanner}
+
+Emit that line exactly once; the harness renders the logo separately.
+
+Load the native lit-handoff skill from OpenCode first. Resolve SKILL_ROOT to its
+canonical/ directory, next to that installed SKILL.md, never relative to the project
+or command file. Apply
+the complete adapter, original contract, and template below without abbreviation. Verify
+live workspace state because an existing handoff can be stale.
+
+# OpenCode adapter
+
+${nativeManagedSkillReferences("lit-handoff", readStaticSkillBody("lit-handoff"))}
+
+# Exact original contract
+
+${readManagedSkillAsset("lit-handoff", "../../vendor/handoff/SKILL.md")}
+
+# Resolved exact template
+
+${readManagedSkillAsset("lit-handoff", "../../vendor/handoff/templates/HANDOFF.md")}
+</lit-handoff-mode>`;
+export const scientificVisualizationPromptInjection = `${scientificVisualizationBanner}
+<lit-scientific-visualization-mode>
+First model-emitted line of your reply MUST be exactly:
+
+${scientificVisualizationBanner}
+
+Emit that line exactly once; the harness renders the logo separately.
+
+Load the native lit-scientific-visualization skill from OpenCode first. Resolve
+SKILL_ROOT to its canonical/ directory, next to that installed SKILL.md, never relative
+to the project or command file. Read related assets, scripts, and references from that root. Do not install
+Python packages silently; report executable capability as READY or DEGRADED.
+
+# OpenCode adapter
+
+${nativeManagedSkillReferences("lit-scientific-visualization", readStaticSkillBody("lit-scientific-visualization"))}
+
+# Exact original contract
+
+${readManagedSkillAsset("lit-scientific-visualization", "../../vendor/scientific-visualization/SKILL.md")}
+</lit-scientific-visualization-mode>`;

package/dist/activation-primary-prompts.d.ts

@@ -0,0 +1,2 @@
+export declare const litLoopPromptInjection: string;
+export declare const litPlanPromptInjection: string;