Skip to content
Back to search

lnwjud

lnwjud — local AI-agent runtime & MCP gateway

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/engasnm111/lnwjud with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/engasnm111/lnwjud'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/engasnm111--lnwjud/badge.svg)](/listings/engasnm111--lnwjud)

HTML

<a href="/listings/engasnm111--lnwjud"><img src="/api/listings/engasnm111--lnwjud/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Windows 10 / 11

1. Open [GitHub Releases](https://github.com/engasnm111/lnwjud/releases/latest). 2. Download `lnwjud-Setup-<version>.exe` for the normal installer, or `lnwjud-Portable-<version>.exe` if you prefer a portable executable. 3. Launch lnwjud, add the project/workspace you want to use, then configure the MCP connection method you need.

Community Windows artifacts may be unsigned when production code-signing credentials are not configured. Release verification still checks the declared signing mode, SHA-256 manifests, runtime provenance, and packaged-app smoke evidence; verify the release assets if Windows shows an unknown-publisher warning.

Windows-only features such as WSL, Registry, Windows Sandbox, Windows OCR and Outlook/COM remain available only where the Windows provider is supported.

macOS 13+

Download the artifact that matches the Mac architecture (`arm64` for Apple silicon or `x64` for Intel). Do not swap architectures just because both filenames contain the word “Mac”. Computers remain unusually literal about this.

See [Install lnwjud on macOS](docs/INSTALL_MACOS.md) for DMG/ZIP installation, permissions, MCP launcher paths, Gatekeeper/signing expectations, and troubleshooting.

Linux

Choose the release artifact that matches the Linux architecture and package type. Ubuntu 24.04 LTS x64 is the primary Linux release target; arm64 remains architecture-specific and evidence-gated.

See [Install lnwjud on Linux](docs/INSTALL_LINUX.md) for AppImage/DEB installation, Wayland/X11 behavior, secure storage, MCP, and platform limits.

Local data vs workspace metadata

Installed lnwjud keeps per-user runtime data outside your source repository: `%APPDATA%\lnwjud` on Windows, `~/Library/Application Support/lnwjud` on macOS, and `$XDG_DATA_HOME/lnwjud` (or `~/.local/share/lnwjud`) on Linux unless `LNWJUD_DATA_PATH` is explicitly set. A workspace may contain `.lnwjud/project-profile.json` for project-scoped policy such as Ponytail or Engineering Harness mode/profile; `.lnwjud/` is local metadata and is ignored by this repository.

Engineering Harness (opt-in)

Engineering Harness is **Off by default**. Enable it in **Settings → Engineering Harness** when you want lnwjud to turn a substantive coding request into a durable, risk-based workflow instead of treating every request the same way.

- **Presets:** Standard, **Senior** (recommended), Strict, or Custom. - **Scope:** coding projects/tasks by default, with an optional per-workspace On/Off + preset override. - **Policy precedence:** explicit workspace/project opt-out wins; project policy can strengthen a preset but cannot silently weaken an explicit user opt-out. - **Durability:** `engineering_start_task` reuses the existing durable Goal authority. Requirement changes increment the Goal intent revision and stale only affected Engineering gates instead of resetting proven work. - **Evidence:** required checks remain Pending/Running/Failed/Stale until observed evidence satisfies them. Host-observed mechanical checks are not replaced by a model assertion. - **Enforcement:** first-party development mutations such as guarded file edits, Git, shell/process/project commands, verification, Codex/Agent Swarm and worktree operations require the current `engineeringTask` binding when Harness is active. Existing permission, Active Project, recovery, Full Bypass and rolling `goalLease` rules still apply independently. - **Advisory boundary:** external `mcp_call`, general Office/web/native-UI routes are not mechanically Engineering-guarded in v5.7.0; their existing security/permission controls remain authoritative. - **No hidden writes:** project assessment and the Settings project-profile preview do not write repository files, commit, push, deploy, or create a Scheduled Task by themselves.

For the Thai setup and workflow guide, see [docs/USAGE_TH.md](docs/USAGE_TH.md#8a-engineering-harness--senior-coding-workflow).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 279 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <p align="center">
  2. <img src="assets/logo/logo-256x256.png" width="160" alt="lnwjud logo" />
  3. </p>
  4. <h1 align="center">lnwjud</h1>
  5. <p align="center">
  6. <strong>Cross-platform local AI-agent runtime and MCP gateway</strong><br />
  7. <em>299 total tool definitions for local files, Git, processes, Windows automation, WSL, browser control, durable goal continuation, Engineering Harness, native Goal automation, context capsules, indexing, observability, Office semantic automation, ECC integration, and extensibility; 287 are advertised by default and all 299 when Codex delegation plus Agent Swarm is enabled.</em>
  8. </p>
  9. <p align="center">
  10. <em>อ่านที่เหลือใน Readme ได้เลยครับ ติดปัญหาทักมาได้ใน <a href="https://url.in.th/rEZiG"><strong>Line</strong></a> ได้ตลอดครับ / กำลังพัฒนาให้เรื่อยๆครับ ท่านที่ถามหาช่องสนับสนุนค่ากาแฟ แปะลิงก์ไว้ให้แล้วครับ ขอบคุณครับ — <a href="https://easydonate.app/abcz"><strong>Donate</strong></a></em>
  11. </p>
  12. <p align="center">
  13. <a href="https://github.com/engasnm111/lnwjud/releases/latest"><img alt="GitHub Release" src="https://img.shields.io/github/v/release/engasnm111/lnwjud" /></a>
  14. <a href="LICENSE"><img alt="License" src="https://img.shields.io/badge/license-MIT-blue.svg" /></a>
  15. <img alt="Platform" src="https://img.shields.io/badge/platform-Windows%20%7C%20macOS%20%7C%20Linux-0078D4" />
  16. <img alt="Node" src="https://img.shields.io/badge/Node.js-24.x-339933" />
  17. <img alt="MCP" src="https://img.shields.io/badge/MCP-299%20tools-6f42c1" />
  18. </p>
  19. <h2 align="center">Download lnwjud</h2>
  20. <p align="center">Download Windows and Linux v5.9.3 directly; macOS remains on v5.8.7 pending containment verification.</p>
  21. <table align="center">
  22. <tr>
  23. <td align="center" width="33%">
  24. <a href="https://github.com/engasnm111/lnwjud/releases/latest/download/lnwjud-Setup-5.9.3.exe">
  25. <img src="assets/download/download-windows.svg" width="300" alt="Download lnwjud for Windows" />
  26. </a><br />
  27. <sub><a href="https://github.com/engasnm111/lnwjud/releases/latest/download/lnwjud-Portable-5.9.3.exe">Portable x64</a></sub>
  28. </td>
  29. <td align="center" width="33%">
  30. <a href="https://github.com/engasnm111/lnwjud/releases/download/v5.8.7/lnwjud-5.8.7-arm64.dmg">
  31. <img src="assets/download/download-macos.svg" width="300" alt="Download lnwjud for macOS" />
  32. </a><br />
  33. <sub><a href="https://github.com/engasnm111/lnwjud/releases/download/v5.8.7/lnwjud-5.8.7-x64.dmg">Intel x64 DMG</a> · <a href="docs/INSTALL_MACOS.md">Install guide</a></sub>
  34. </td>
  35. <td align="center" width="33%">
  36. <a href="https://github.com/engasnm111/lnwjud/releases/latest/download/lnwjud-5.9.3-x64.deb">
  37. <img src="assets/download/download-linux.svg" width="300" alt="Download lnwjud for Linux" />
  38. </a><br />
  39. <sub><a href="https://github.com/engasnm111/lnwjud/releases/latest/download/lnwjud-5.9.3-x64.AppImage">x64 AppImage</a> · <a href="docs/INSTALL_LINUX.md">Other architectures</a></sub>
  40. </td>
  41. </tr>
  42. </table>
  43. <p align="center"><a href="https://github.com/engasnm111/lnwjud/releases/latest"><strong>View all release files →</strong></a></p>
  44. ---
  45. ## Current published version: v5.9.3
  46. ## Current source version: v5.9.3
  47. The development source includes the [local Goal Event API](docs/development/GOAL_EVENT_API.md) for explicitly approved workspace companions.
  48. ### Ponytail developer skills (v5.9.0 source)
  49. The six bundled Ponytail document skills are pinned to [upstream v5.3.2](https://github.com/DietrichGebert/ponytail/releases/tag/v5.3.2), the latest stable release verified on 2026-10-21. They provide Lite/Full/Ultra coding guidance, review, audit, debt, impact and help; **there is no separate upstream hook/plugin installation**. Ponytail is OFF by default unless enabled explicitly through Global, Workspace or Current Goal settings. Coding actions remain subject to exact bundled-skill activation and normal workspace/Goal safety checks. See [Ponytail integration and package acceptance](docs/PONYTAIL.md) for pinned SHA, commands, provenance, validation and limitations.
  50. ## Install
  51. ### Windows 10 / 11
  52. 1. Open [GitHub Releases](https://github.com/engasnm111/lnwjud/releases/latest).
  53. 2. Download `lnwjud-Setup-<version>.exe` for the normal installer, or `lnwjud-Portable-<version>.exe` if you prefer a portable executable.
  54. 3. Launch lnwjud, add the project/workspace you want to use, then configure the MCP connection method you need.
  55. Community Windows artifacts may be unsigned when production code-signing credentials are not configured. Release verification still checks the declared signing mode, SHA-256 manifests, runtime provenance, and packaged-app smoke evidence; verify the release assets if Windows shows an unknown-publisher warning.
  56. Windows-only features such as WSL, Registry, Windows Sandbox, Windows OCR and Outlook/COM remain available only where the Windows provider is supported.
  57. ### macOS 13+
  58. Download the artifact that matches the Mac architecture (`arm64` for Apple silicon or `x64` for Intel). Do not swap architectures just because both filenames contain the word “Mac”. Computers remain unusually literal about this.
  59. See [Install lnwjud on macOS](docs/INSTALL_MACOS.md) for DMG/ZIP installation, permissions, MCP launcher paths, Gatekeeper/signing expectations, and troubleshooting.
  60. ### Linux
  61. Choose the release artifact that matches the Linux architecture and package type. Ubuntu 24.04 LTS x64 is the primary Linux release target; arm64 remains architecture-specific and evidence-gated.
  62. See [Install lnwjud on Linux](docs/INSTALL_LINUX.md) for AppImage/DEB installation, Wayland/X11 behavior, secure storage, MCP, and platform limits.
  63. ### Local data vs workspace metadata
  64. Installed lnwjud keeps per-user runtime data outside your source repository: `%APPDATA%\lnwjud` on Windows, `~/Library/Application Support/lnwjud` on macOS, and `$XDG_DATA_HOME/lnwjud` (or `~/.local/share/lnwjud`) on Linux unless `LNWJUD_DATA_PATH` is explicitly set. A workspace may contain `.lnwjud/project-profile.json` for project-scoped policy such as Ponytail or Engineering Harness mode/profile; `.lnwjud/` is local metadata and is ignored by this repository.
  65. ### Engineering Harness (opt-in)
  66. Engineering Harness is **Off by default**. Enable it in **Settings → Engineering Harness** when you want lnwjud to turn a substantive coding request into a durable, risk-based workflow instead of treating every request the same way.
  67. - **Presets:** Standard, **Senior** (recommended), Strict, or Custom.
  68. - **Scope:** coding projects/tasks by default, with an optional per-workspace On/Off + preset override.
  69. - **Policy precedence:** explicit workspace/project opt-out wins; project policy can strengthen a preset but cannot silently weaken an explicit user opt-out.
  70. - **Durability:** `engineering_start_task` reuses the existing durable Goal authority. Requirement changes increment the Goal intent revision and stale only affected Engineering gates instead of resetting proven work.
  71. - **Evidence:** required checks remain Pending/Running/Failed/Stale until observed evidence satisfies them. Host-observed mechanical checks are not replaced by a model assertion.
  72. - **Enforcement:** first-party development mutations such as guarded file edits, Git, shell/process/project commands, verification, Codex/Agent Swarm and worktree operations require the current `engineeringTask` binding when Harness is active. Existing permission, Active Project, recovery, Full Bypass and rolling `goalLease` rules still apply independently.
  73. - **Advisory boundary:** external `mcp_call`, general Office/web/native-UI routes are not mechanically Engineering-guarded in v5.7.0; their existing security/permission controls remain authoritative.
  74. - **No hidden writes:** project assessment and the Settings project-profile preview do not write repository files, commit, push, deploy, or create a Scheduled Task by themselves.
  75. For the Thai setup and workflow guide, see [docs/USAGE_TH.md](docs/USAGE_TH.md#8a-engineering-harness--senior-coding-workflow).
  76. ## What can lnwjud do?
  77. lnwjud exposes **299 tool definitions** through one local runtime and MCP gateway. The default advertised set is 287; all 299 are available when Codex delegation plus Agent Swarm is enabled.
  78. | Area | Examples |
  79. | --- | --- |
  80. | Workspace & files | read/search/edit files, paging, full scans, project indexing, recovery trash |
  81. | Git | status, diff, history, blame, guarded Git mutations |
  82. | Processes | shell, managed processes, durable background tasks, Goal-owned native automation, logs, cancellation |
  83. | MCP | local HTTP/stdio MCP, External MCP discovery/describe/call, live tool availability |
  84. | Development | test, lint, typecheck, build, affected-test context, Codex integration |
  85. | Browser | managed Chrome/CDP, DOM inspection, Set-of-Marks, screenshots |
  86. | Recovery | backups, checkpoints, restore, crash/session recovery, durable-goal state |
  87. | Observability | Work Log, Live Logs, Doctor, incident reports, trace/audit metadata |
  88. | Native capabilities | UI/input/media/Office/scheduler providers when the current OS supports them |
  89. | Windows-specific | WSL, Registry, Windows Sandbox, Windows Event Log/OCR, Outlook/COM |
  90. For the complete generated catalog, see [MCP Tool Catalog](docs/mcp/MCP_TOOL_CATALOG.md). For the broader capability explanation, see [lnwjud capabilities](docs/LNWJUD_CAPABILITIES.md).
  91. ## Platform compatibility
  92. lnwjud composes providers for the detected host instead of instantiating a Windows provider everywhere and hoping for the best.
  93. | Feature | Windows | macOS | Linux |
  94. | --- | --- | --- | --- |
  95. | Core MCP / files / Git / processes | ✅ | ✅ | ✅ |
  96. | External MCP | ✅ | ✅ | ✅ |
  97. | OpenAI Secure MCP Tunnel client | target-native | target-native | target-native |
  98. | Remote MCP with ngrok | ✅ | ✅ | ✅ |
  99. | Managed browser / CDP | dependency-gated | dependency-gated | dependency-gated |
  100. | Native PDF text provider | dependency-gated | dependency-gated | dependency-gated |
  101. | Automatic Poppler install | Windows x64 | hidden | hidden |
  102. | WSL / Registry / Windows Sandbox | ✅ | unsupported | unsupported |
  103. | Outlook COM | ✅ | unsupported | unsupported |
  104. The authoritative matrix is [Native platform support contract](docs/architecture/PLATFORM_SUPPORT.md).
  105. ## MCP connection choices
  106. - **Local MCP:** use the packaged stdio launcher or Desktop loopback MCP endpoint directly. The Local transport starts the local listener without ngrok, a public URL, or Remote MCP OAuth.
  107. - **Remote MCP via ngrok + OAuth:** remains the default/backward-compatible Remote MCP transport. lnwjud owns the protected loopback OAuth gateway and ngrok child runtime.
  108. - **Remote MCP via Cloudflare:** opt-in for a Cloudflare Tunnel/reverse proxy that you manage. lnwjud provides a stable local OAuth-gateway target and verifies the configured public HTTPS origin; it does not claim to create or manage the Cloudflare tunnel.
  109. - **Remote MCP via Custom URL:** opt-in for another externally managed HTTPS reverse proxy. No ngrok token/install is required; the public origin must route to the stable local protected gateway.
  110. - **OpenAI Secure MCP Tunnel:** separate outbound-only OpenAI tunnel path using the verified target-native bundled `tunnel-client`. One lnwjud tunnel endpoint is intended to serve multiple simultaneous ChatGPT chats/workspaces; do not create one tunnel/profile per chat. v4.62.0 explicitly gives the tunnel transport 32 active MCP-request slots so normal multi-chat tool fan-out does not hit tunnel-client's lower default ceiling. If several physical lnwjud hosts (for example Mac + Windows) must be independently selectable, give each host a distinct Tunnel ID/ChatGPT connection: HTTP replicas sharing one Tunnel ID are work-sharing replicas, so a request goes to whichever replica polls it first rather than to a chat-selected host.
  111. - **External MCP servers:** lnwjud can discover supported Cursor/Claude Desktop/custom MCP definitions and keep child MCP servers separate from the first-party catalog.
  112. See the [Thai usage guide](docs/USAGE_TH.md) and [full expanded README](FULL_README.md) for the long-form setup and architecture notes.
  113. ## Durable goals + scheduled continuation / Goal แบบทำงานต่อเนื่อง
  114. lnwjud can keep long-running work alive across chat turns with a **durable goal** plus the bundled `lnwjud-scheduled-continuation` skill. The intended model is simple: one stable goal, one recurring Native ChatGPT Scheduled Task, periodic checkpoints, and an explicit finish only when the work is genuinely complete.
  115. lnwjud สามารถทำงานยาวข้ามหลายรอบแชทได้ด้วย **durable goal** ร่วมกับสกิล `lnwjud-scheduled-continuation` แนวทางที่ควรใช้คือ: 1 งาน = 1 goal ที่ใช้ `goalKey` เดิม, มี Native ChatGPT Scheduled Task แบบ recurring เพียง 1 ตัว, บันทึก checkpoint ระหว่างทาง และปิด goal เมื่อทุกอย่างเสร็จจริงเท่านั้น
  116. The scheduled continuation should be a **Native ChatGPT Scheduled Task running in cloud mode every 1 hour**. It is a watchdog that wakes the workflow back up; the durable goal remains the source of truth for plan state, progress, blockers, evidence, and tracked background tasks. Do not create a new goal or timer on every wake.
  117. ตัว Scheduled Task ควรเป็น **Native ChatGPT Scheduled Task ที่รันบน cloud ทุก 1 ชั่วโมง** มีหน้าที่ปลุกงานกลับมาทำต่อเท่านั้น ส่วนสถานะจริงของงานให้ยึด durable goal เป็นหลัก ห้ามสร้าง goal ใหม่หรือตัวตั้งเวลาใหม่ทุกครั้งที่ถูกปลุก
  118. ### Recommended prompt — English
  119. ```text
  120. @lnwjud
  121. Workspace:
  122. C:\path\to\my-project
  123. Continue this task until it is genuinely complete. Do not stop only because the current chat turn ends.
  124. - Use the lnwjud-scheduled-continuation skill.
  125. - Create or resume the same durable goal using one stable goalKey. Treat that Durable Goal as the authoritative task state and never create duplicate goals for the same job. When plan or step progress changes, use update_goal_plan so the Watcher-visible plan stays current.
  126. - Create exactly one recurring Native ChatGPT Scheduled Task, run it in cloud mode every 1 hour, and reuse that same scheduled continuation for this goal.
  127. - Checkpoint immediately after every meaningful milestone, and refresh active progress at least every 10 minutes when sustained work has no natural milestone. Persist current phase, step status, next action, blockers, evidence, tracked background tasks, and reconstruction-grade resumeContext: changed files, exact commands/results, decisions, failed attempts, pending validation, resume prerequisites, state facts, and artifacts. A checkpoint records progress; it is not a reason to stop useful work.
  128. - When the scheduled task wakes the workflow, claim the continuation for the same goal and resume from the latest checkpoint instead of starting over.
  129. - If CI, build, test, deployment, or another process is still running, keep tracking the same task until its terminal result is known. If a failure is fixable, inspect the exact failure, diagnose it, repair it, and run the relevant validation in the same turn instead of stopping at a status report.
  130. - Do not finish the goal while any planned step, acceptance criterion, required Engineering gate/review finding, blocker, or blocking task remains unresolved. Reconcile stale duplicate/superseded/abandoned goals instead of leaving finished work Active in Watcher.
  131. - When the work is truly complete, cancel the scheduled continuation, make the exact Native ChatGPT Scheduled Task non-runnable, then call finish_goal with final evidence and read get_goal to confirm a terminal state before reporting completion.
  132. ```
  133. ### Prompt แนะนำ — ภาษาไทย
  134. ```text
  135. @lnwjud
  136. Workspace:
  137. C:\path\to\my-project
  138. ทำงานนี้ต่อเนื่องจนเสร็จจริง ห้ามหยุดกลางทางเพียงเพราะแชทจบรอบ
  139. - ใช้สกิล lnwjud-scheduled-continuation
  140. - สร้างหรือ resume durable goal เดิมด้วย goalKey ที่คงที่ และให้ Durable Goal เป็น state หลักของงาน ห้ามสร้าง goal ซ้ำสำหรับงานเดียวกัน เมื่อ plan หรือสถานะ step เปลี่ยน ให้ใช้ update_goal_plan เพื่อให้ plan/progress ที่ Watcher แสดงเป็นปัจจุบัน
  141. - สร้าง Native ChatGPT Scheduled Task แบบ recurring เพียง 1 ตัว ให้รันบน cloud ทุก 1 ชั่วโมง และใช้ scheduled continuation ตัวเดิมกับ goal นี้ไปตลอด
  142. - หลัง milestone สำคัญทุกครั้งให้ checkpoint ทันที และถ้าทำงานต่อเนื่องโดยไม่มี milestone ตามธรรมชาติให้ refresh อย่างน้อยทุก 10 นาที โดยบันทึก current phase, step status, next action, blockers, evidence, tracked background task และ resumeContext ที่สร้างงานต่อได้จริง เช่นไฟล์ที่เปลี่ยน, คำสั่งและผลลัพธ์, การตัดสินใจ, failed attempts, pending validation, prerequisites, state facts และ artifacts การ checkpoint คือการบันทึก progress ไม่ใช่เหตุผลให้หยุดทำงาน
  143. - เมื่อ scheduled task ปลุกขึ้นมา ให้ claim continuation ของ goal เดิม แล้วทำงานต่อจาก checkpoint ล่าสุด ห้ามเริ่มงานใหม่ตั้งแต่ต้น
  144. - หากมี CI, build, test, deploy หรือ process ที่ยังรันอยู่ ให้ติดตาม task เดิมจนได้ terminal result ถ้าความล้มเหลวนั้นแก้ได้ ให้เปิดผลล้มเหลวจริง วิเคราะห์ root cause แก้ และรัน validation ที่เกี่ยวข้องต่อใน turn เดิม ห้ามหยุดแค่รายงานสถานะ
  145. - ห้าม finish goal หากยังมี step, acceptance criterion, Engineering gate/review finding ที่จำเป็น, blocker หรือ blocking task ที่ยังไม่เสร็จ และให้ reconcile goal ซ้ำ/ถูกแทนที่/ถูก abandon ที่งานจบแล้วแทนการปล่อยค้าง Active ใน Watcher
  146. - เมื่อทุกอย่างเสร็จจริง ให้ cancel scheduled continuation, ทำให้ Native ChatGPT Scheduled Task ตัวเดิมไม่สามารถรันต่อได้ แล้วค่อย finish_goal พร้อม final evidence จากนั้นเรียก get_goal ยืนยันว่าเป็น terminal ก่อนรายงานว่าเสร็จ
  147. ```
  148. ### Goal lifecycle / วงจรของ Goal
  149. 1. **Start / resume — `run_goal`**
  150. - English: Use one stable `goalKey`; resume the existing goal instead of creating a duplicate.
  151. - ไทย: ใช้ `goalKey` เดิมสำหรับงานเดียวกัน ถ้ามี goal อยู่แล้วให้ resume ห้ามสร้างซ้ำ
  152. 2. **Checkpoint — `checkpoint_goal`**
  153. - English: Save meaningful progress: current phase, completed/pending steps, next action, blockers, evidence, and tracked background tasks. A checkpoint records progress; it is **not** an instruction to stop working.
  154. - ไทย: บันทึกความคืบหน้าที่สำคัญ เช่น phase, step ที่เสร็จ/ค้าง, งานถัดไป, blocker, evidence และ task ที่กำลังรันอยู่ การ checkpoint คือการเซฟสถานะ ไม่ใช่การสั่งให้หยุดงาน
  155. 3. **Prepare + wake — `prepare_scheduled_continuation` / `claim_scheduled_continuation`**
  156. - English: Keep exactly one hourly Native ChatGPT recurring task for the goal. Every wake resumes the same durable goal from its latest checkpoint.
  157. - ไทย: ให้มี scheduled task แบบรายชั่วโมงเพียง 1 ตัวต่อ goal และทุกครั้งที่ถูกปลุกให้กลับมาทำ goal เดิมต่อจาก checkpoint ล่าสุด
  158. 4. **Stop watchdog — `cancel_scheduled_continuation`**
  159. - English: Once the goal is genuinely terminal, make the exact recurring Native ChatGPT task non-runnable so a completed job is not awakened again.
  160. - ไทย: เมื่องานจบจริง ให้ปิด scheduled continuation และทำให้ task ตัวเดิมรันต่อไม่ได้ เพื่อไม่ให้ปลุกงานที่เสร็จแล้วขึ้นมาอีก
  161. 5. **Finish — `finish_goal`**
  162. - English: Finish only after all planned steps are complete, blockers are cleared, blocking tasks are terminal, acceptance criteria are satisfied, and scheduled continuation cleanup is complete. Record final evidence instead of merely declaring success in chat.
  163. - ไทย: ปิด goal หลังจากทุก step เสร็จ, blocker ถูกเคลียร์, blocking task จบแล้ว, acceptance criteria ผ่านครบ และ cleanup ตัวตั้งเวลาเรียบร้อย พร้อมบันทึกหลักฐานสุดท้าย
  164. ### v5 Goal state / สถานะ Goal ใน v5
  165. - **Plan + Watcher projection:** `get_goal_plan` projects the authoritative plan; `update_goal_plan` changes that same durable plan and keeps the plan/progress shown by Watcher aligned with real step state instead of creating a second planner.
  166. - **Freshness + reconstruction:** call `checkpoint_goal` immediately after meaningful step/task/blocker/commit/push/CI/package milestones, and at least every 10 minutes during sustained work without a natural milestone. Meaningful checkpoints carry reconstruction-grade `resumeContext`; a short summary alone is not enough for reliable resume.
  167. - **Acceptance:** `update_goal_acceptance` records explicit completion evidence. `finish_goal(status=completed)` is rejected while any criterion is still pending or blocked; Engineering Harness goals must also satisfy their required gates and blocking review findings.
  168. - **Newest intent wins:** `revise_goal_intent` increments `userIntentRevision`; stale checkpoints or delivery receipts from older accepted user intent are fenced/retired rather than replayed.
  169. - **Context Capsule:** `create_context_capsule` stores a bounded immutable objective/decision/result summary for compact/resume or handoff. It stores task state, not private chain-of-thought, and does not drive ChatGPT through browser/DOM automation.
  170. - **Pressure + iteration:** `context_pressure` reports a local estimate when exact provider usage is unavailable, while `advance_goal_iteration` is explicitly bounded by `maxIterations` and can stop when no new evidence appears.
  171. - **Completion hygiene:** after watchdog cleanup and `finish_goal`, read `get_goal` and confirm a terminal status before reporting completion. Reconcile stale duplicate, superseded, or abandoned Goal cards when authoritative evidence shows they no longer represent live work; completed work must not remain Active in Watcher.
  172. ภาษาไทยแบบสั้น: v5 แยก **plan / acceptance / user intent / context capsule / bounded iteration** ออกจากกันชัดเจน โดย Durable Goal ยังเป็น source of truth เพียงชุดเดียว ถ้าผู้ใช้เปลี่ยนคำสั่งใหม่ งานเก่าต้องแพ้ revision ใหม่ และ Context Capsule ใช้เก็บสรุปสถานะเพื่อกลับมาทำต่อ ไม่ใช่เก็บ chain-of-thought หรือใช้ browser ไปสร้างแชทใหม่เอง
  173. ### Short prompt — English
  174. ```text
  175. Use lnwjud-scheduled-continuation. Create or resume one durable goal for this job, keep exactly one Native ChatGPT Scheduled Task running in cloud mode every 1 hour, and resume from the latest checkpoint until the goal is genuinely complete. Checkpoint every meaningful milestone, never duplicate the goal or timer, and when all steps are complete with no blockers or blocking tasks left, cancel the scheduled continuation first and then finish_goal with final evidence.
  176. ```
  177. ### Prompt แบบสั้น — ภาษาไทย
  178. ```text
  179. ใช้สกิล lnwjud-scheduled-continuation สร้างหรือ resume durable goal เดิมสำหรับงานนี้ และสร้าง Native ChatGPT Scheduled Task บน cloud แบบ recurring ทุก 1 ชั่วโมงเพียง 1 ตัว เพื่อกลับมาทำงานต่อจาก checkpoint ล่าสุดจน goal เสร็จจริง ระหว่างทางให้ checkpoint ทุก milestone สำคัญ ห้ามสร้าง goal หรือตัวตั้งเวลาซ้ำ และเมื่อทุก step เสร็จ ไม่มี blocker หรือ blocking task ค้าง ให้ปิด scheduled continuation ก่อน แล้ว finish_goal พร้อมหลักฐานสุดท้าย
  180. ```
  181. This pattern is especially useful for long CI/release jobs, multi-stage refactors, deployments, packaging, migrations, or any task where “continue later” should be backed by durable state rather than wishful thinking.
  182. รูปแบบนี้เหมาะกับงาน CI/Release ที่ใช้เวลานาน, refactor หลายขั้น, deploy, packaging, migration หรืองานใดก็ตามที่ต้องทำต่อหลายรอบ เพราะคำว่า “เดี๋ยวมาทำต่อ” ถ้าไม่มี state เก็บไว้ก็เป็นระบบ persistence ที่น่าเชื่อถือพอ ๆ กับกระดาษโน้ตที่ติดหน้าพัดลม
  183. ## Documentation
  184. - [Full expanded README / historical detail](FULL_README.md)
  185. - [คู่มือใช้งานภาษาไทย](docs/USAGE_TH.md)
  186. - [macOS installation](docs/INSTALL_MACOS.md)
  187. - [Linux installation](docs/INSTALL_LINUX.md)
  188. - [Platform support matrix](docs/architecture/PLATFORM_SUPPORT.md)
  189. - [Complete capabilities](docs/LNWJUD_CAPABILITIES.md)
  190. - [MCP Tool Catalog](docs/mcp/MCP_TOOL_CATALOG.md)
  191. - [Tool contract](docs/architecture/TOOL_CONTRACT.md)
  192. - [Release process](docs/development/RELEASE_PROCESS.md)
  193. - [Security](SECURITY.md)
  194. - [Contributing](CONTRIBUTING.md)
  195. ## Security boundary
  196. lnwjud is intentionally powerful because it operates on the local machine. Tool availability does **not** bypass Active Project scope, permission policy, mutation approval, recovery, host OS permissions, or platform capability gates. Unknown/unsupported platforms and missing native providers should fail closed rather than silently substituting a different OS implementation.
  197. ## Community
  198. ติดปัญหา อยากแชร์วิธีใช้ หรือเจอบัค สามารถเข้ากลุ่มพูดคุยได้ที่ [Line](https://url.in.th/rEZiG).
  199. ## License
  200. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.