opensocrates 1.4.0 → 1.5.1

package/README.md

@@ -4,108 +4,167 @@
 
 # OpenSocrates
 
-**A method for the judgment your Codex agent is making.**
+**Reasoning help for results you can understand, judge, and use.**
 
-OpenSocrates brings 48 authored reasoning methods to Codex. Examine assumptions,
-compare options, and weigh evidence within the task you are already doing.
+OpenSocrates brings 48 authored reasoning methods into the task you are already
+doing: synthesize evidence, understand stakeholder perspectives, compare choices,
+and write useful messages. The original English/Korean procedures remain intact.
+The v1.5 reader guides connect conclusions to context and next actions;
+dedicated coding-specialist features are outside this version.
 
-**English** | [한국어](README.ko.md)
+**English** | [한국어](README.ko.md) | [简体中文](README.zh.md) | [日本語](README.ja.md)
 
 [![CI](https://github.com/ParkerHwang/OpenSocrates/actions/workflows/ci.yml/badge.svg)](https://github.com/ParkerHwang/OpenSocrates/actions/workflows/ci.yml)
 [![npm](https://img.shields.io/npm/v/opensocrates)](https://www.npmjs.com/package/opensocrates)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 
-## Get started
+## v1.5.1 on Mac and Windows
 
-Version **1.4.0 supports Codex only**, on **Apple-silicon macOS and Windows x64**.
-Install Node.js 20 or later, make the Codex CLI available, and sign in to Codex.
-The native runtime is bundled; users do not need Python.
+Version 1.5.1 adds Simplified Chinese (`zh`) and Japanese (`ja`) reasoning
+instructions alongside English and Korean, across all four existing host
+profiles. It preserves the v1.5.0 platform scope: Apple-silicon Mac and Windows
+x64, with native Claude Code on Mac only. Download archives and SHA-256 files from the
+[v1.5.1 release](https://github.com/ParkerHwang/OpenSocrates/releases/tag/v1.5.1),
+or use the [npm installer](https://www.npmjs.com/package/opensocrates/v/1.5.1).
 
-```sh
-npx --yes opensocrates@1.4.0 install
-```
+| Host | Delivery | Platform and activation |
+| --- | --- | --- |
+| Codex | Existing hooks, controller and native decision runtime | Apple-silicon Mac and Windows x64; review the seven hooks in an interactive session |
+| Claude Code CLI / Desktop local Code | Stateless native entry and complete installed references | Apple-silicon Mac; requires the Claude CLI, host login and plugin/hook permissions |
+| Claude web / Desktop Chat / Cowork | Standalone content-only account skill ZIP | Export on Mac or Windows; upload, enable and add the one-time account instructions below |
+| Antigravity conversation application | Owned modular rule and skill | Apple-silicon Mac and Windows x64; choose workspace or global scope |
+
+Windows native Claude Code in a terminal or Desktop Code is outside this
+release's scope. Account content does not install a native Claude integration.
+See the [Mac guide](docs/macos-v1.5.md) and [Windows guide](docs/windows-v1.5.md).
 
-Start a new interactive Codex session and review the seven OpenSocrates command
-hooks. Approve those hooks before relying on native discovery. Non-interactive
-`codex exec` skips untrusted hooks; installation alone does not establish hook
-approval or actual delivery. You can explicitly ask Codex to use the
-`opensocrates` controller skill.
+Trusted native hooks and Antigravity's standing rule provide entry during normal
+requests. For Claude account skills, add the standing instruction below to use
+OpenSocrates without repeating its name. Selection still depends on the host
+model and can be missed. Installation, loading, complete reads, application,
+and useful outcomes are separate evidence levels. No general quality, token-cost,
+or latency improvement is claimed.
 
-If you previously disabled these hooks, enable them in Codex's `/hooks` view.
-Updating the plugin preserves your hook enablement and trust preferences.
+**After installation:** follow the [visual setup guide](docs/setup-guide.md) for hook review, account skill switches, and host readiness. It also includes a request you can paste into an agent.
+
+## Install or update
+
+Install Node.js 20+, make the chosen host available, and sign in to that host.
+Native runtimes are bundled; installation does not require Python. Start with
+Codex on either supported platform:
 
 ```sh
-npx --yes opensocrates@1.4.0 status
-npx --yes opensocrates@1.4.0 update
+npx --yes opensocrates@1.5.1 install --host codex
+npx --yes opensocrates@1.5.1 status --host codex
 ```
 
-`--host codex` is optional. The compatibility alias `--host all` now means Codex
-only. Other host names are rejected before installation or removal.
+For an existing Codex installation, including v1.5.0, use:
 
-## Upgrading from a multi-host release
+```sh
+npx --yes opensocrates@1.5.1 update --host codex
+```
 
-Claude Code, Cowork, Claude Chat, Antigravity, Cursor, Grok Build, and OpenCode
-integrations and archives are removed in 1.4.0. Existing non-Codex installations
-are not silently erased. If your previous desired state includes another host,
-first use the version that installed it to remove that host, then update Codex:
+Review the seven Codex hooks in an interactive session and start a fresh
+conversation. Non-interactive execution may skip untrusted hooks. `status`
+reports installation and integrity; it does not prove automatic delivery.
+
+On Apple-silicon Mac, install the native Claude companion with:
 
 ```sh
-# Example for an installation managed by 1.3.1:
-npx --yes opensocrates@1.3.1 remove --host claude --purge
-npx --yes opensocrates@1.4.0 update --host codex
+npx --yes opensocrates@1.5.1 install --host claude
+npx --yes opensocrates@1.5.1 status --host claude
 ```
 
-Use the corresponding old host name for each retired integration. Review any
-pending cleanup reported by the old installer. User conversation history and
-unrelated files must be preserved. See [installation and removal](docs/advanced-usage.md).
+For Antigravity, choose an existing absolute workspace directory:
 
-## What it does
+```sh
+npx --yes opensocrates@1.5.1 install --host antigravity --workspace /absolute/path/to/workspace
+```
 
-- Choose a method for a judgment: compare alternatives, check a causal claim,
-  examine assumptions, or identify evidence that could change a recommendation.
-- Revisit a decision when the facts change, including multiple decision points
-  within one request. Mechanical steps need no method.
-- Read complete instructions, examples, applicability limits, and required public
-  results. All 48 methods retain their English and Korean procedure bodies.
-- Keep conclusions connected to evidence, uncertainty, and reopening conditions
-  while preserving the user's requested format.
+On Windows, replace the directory with an absolute local-drive path such as
+`C:\Work\Reading Workshop` and quote it. Omit `--workspace` for the global scope.
+For Claude account content, export to an absolute ZIP filename in an existing
+folder, then upload and enable the ZIP in Claude's Customize > Skills interface:
 
-Codex hooks provide lightweight discovery guidance. The active agent retrieves
-eligible methods through the packaged native decision command. A constrained
-complete-reference fallback remains when the runtime is unavailable. This path
-makes no separate selector-model call and adds no prompt or transcript storage.
-The integration fails open so ordinary work can continue when it is unavailable.
-See [decision-point retrieval](docs/decision-points.md) for the exact contract.
+```sh
+npx --yes opensocrates@1.5.1 export --host claude-chat --output /absolute/path/to/opensocrates-1.5.1-account.zip
+```
 
-## Platforms and limits
+### Claude Chat and Cowork: one-time account instructions
+
+For use without typing `/opensocrates` on each request, enable the account skill
+and append this instruction in **Settings → General → Instructions for Claude**.
+Preserve your existing instructions. In older Cowork interfaces, use
+**Settings → Cowork → Global instructions**; if Web and Desktop use different
+accounts, configure each account you use.
+
+```text
+For requests that require interpretation or judgment, such as synthesizing
+sources, comparing options, making decisions or drafting messages, load the
+enabled OpenSocrates skill and follow its instructions even when I do not
+mention it. Read the complete procedure and check applicability before applying
+a reasoning method. Do not add unnecessary procedures to mechanical work such
+as formatting.
+```
 
-| Platform | Package | Updates |
-| --- | --- | --- |
-| Apple-silicon macOS | Native runtime and `bin/launch.sh` | Manual; optional macOS LaunchAgent |
-| Windows x64 | Native `.exe` and `node bin/launch.mjs` | Manual only |
-
-Windows does not require WSL or a Unix shell. Windows automatic updates,
-Windows ARM64, Windows 10, macOS Intel, and Linux native packages are not claimed
-as validated. Signing and SmartScreen reputation are unvalidated.
-See the [Windows guide](docs/windows-support.md).
-
-## Privacy and evidence
-
-OpenSocrates runs locally, adds no product telemetry, and has no hosted backend or
-separate account. Your ordinary Codex model requests use Codex authentication and
-its service terms. Read [SECURITY.md](SECURITY.md) for integrity, rollback,
-permissions, and the retained legacy selector boundary.
-
-Package verification, hook delivery, complete reference reads, and actual method
-application are distinct evidence levels. No general quality, token-cost, or
-response-time improvement is claimed. Current release validation is tracked in
-[PR #93](https://github.com/ParkerHwang/OpenSocrates/pull/93) and the
-[release plan](docs/v1.4.0-release-plan.md); older evidence describes older versions.
-
-- [Installation, updates, removal, and runtime reference](docs/advanced-usage.md)
-- [Authored method catalog](content/methods/)
-- [Changelog](CHANGELOG.md)
-- [Contributing](CONTRIBUTING.md) · [Code of Conduct](CODE_OF_CONDUCT.md)
-
-OpenSocrates is [MIT licensed](LICENSE), independent of OpenAI, and not endorsed
-by OpenAI.
+Save once, then start a fresh conversation and describe your task normally.
+The instruction guides model-selected skill use; it adds no native hook or
+guaranteed every-turn enforcement. See the [step-by-step setup guide](docs/setup-guide.md#claude-standing-instructions)
+and [Claude's official instruction settings](https://support.claude.com/en/articles/10185728-understanding-claude-s-personalization-features).
+
+The platform guides cover Windows paths, account replacement, updates, disabling,
+removal, and verified local-archive alternatives. With no local asset flags,
+the installer downloads the pinned v1.5.1 archive and checksum from GitHub Releases.
+
+New profiles require explicit `--host claude`, `--host antigravity`, or
+`--host claude-chat`. The default and `--host all` continue to select Codex;
+they do not install every new host. New profiles have no purge, trust-reset,
+or automatic-update route.
+
+Old multi-host installations are not silently adopted or erased. Reconcile their
+exact origin and ownership before installing a new profile. Back up an existing
+OpenSocrates account skill and its enabled state before replacing it.
+
+## Reasoning instruction languages
+
+All 48 methods include complete English, Korean, Simplified Chinese and Japanese
+procedures and examples: 192 procedure files and three teacher questions per
+method per language, 576 questions in total. Content revision 4 adds the two
+languages while preserving the original English/Korean method text.
+
+Language selection prefers an explicit request over a stored locale preference,
+then uses the current input's script. Kana selects Japanese; otherwise a dominant
+Hangul script selects Korean and dominant Han characters select Chinese.
+Han-only text is ambiguous, so explicitly choose Japanese when needed. Empty,
+Latin-only and tied inputs fall back to English. See the
+[language guide](docs/v1.5.1.md) for exact invocation and preference details.
+The npm installer's command output is separate from reasoning instruction
+language; this release does not translate every installer message or host UI.
+Windows ARM64 support remains separate v1.6.0 work.
+
+## When attribution appears
+
+A final answer ends with the exact line `Powered by OpenSocrates` only when an
+eligible authored method was read in full and actually applied to that answer.
+The wording is the same in all four languages. Reader guidance alone and
+mechanical work do not qualify. The line is attribution, not proof of native
+application or a better result.
+
+## Privacy and development
+
+The default decision path makes no extra selector-model call and stores no raw
+prompts, transcripts, screenshots, or hidden reasoning. The native Claude entry
+does not read transcripts or initialize a database. The account skill has no
+executable surface; normal host conversations and model requests follow the
+host's own authentication, permissions, retention settings, and terms.
+See [SECURITY.md](SECURITY.md).
+
+- [Mac installation and evidence boundaries](docs/macos-v1.5.md)
+- [Windows installation and evidence boundaries](docs/windows-v1.5.md)
+- [Authored methods](content/methods/) · [Decision-point contract](docs/decision-points.md)
+- [v1.5.1 languages, selection and scope](docs/v1.5.1.md)
+- [v1.5.0 implementation baseline](docs/v1.5.0/IMPLEMENTATION_PLAN.md)
+- [Changelog](CHANGELOG.md) · [Contributing](CONTRIBUTING.md) · [Code of Conduct](CODE_OF_CONDUCT.md)
+
+OpenSocrates is [MIT licensed](LICENSE), independent of OpenAI, Anthropic, and
+Google, and not endorsed by them.

package/README.zh.md

@@ -0,0 +1,113 @@
+<p align="center">
+  <img src="https://raw.githubusercontent.com/ParkerHwang/OpenSocrates/main/docs/assets/opensocrates-banner.jpg" alt="OpenSocrates" width="820">
+</p>
+
+# OpenSocrates
+
+**帮助你得到能够理解、评估并使用的推理结果。**
+
+OpenSocrates 为资料综合、观点理解、方案比较和消息撰写提供 48 种完整的推理
+方法。v1.5.1 新增简体中文（`zh`）和日语（`ja`），并保留原有英文、韩文方法
+正文。四种语言共有 192 份完整步骤文件；每种方法每种语言有 3 个面向代理的
+教师问题，共 576 个。内容修订号为 4。此版本不新增编程专用方法。
+
+[English](README.md) | [한국어](README.ko.md) | **简体中文** | [日本語](README.ja.md)
+
+## 支持的平台与应用
+
+| 应用 | 交付方式 | 平台与启用要求 |
+| --- | --- | --- |
+| Codex | 现有钩子、控制器和原生判断运行时 | Apple Silicon Mac、Windows x64；在交互会话中检查 7 个钩子的信任状态 |
+| Claude Code CLI / Desktop 本地 Code | 无状态原生入口及完整本地参考文件 | Apple Silicon Mac；需要 Claude CLI、登录及插件和钩子权限 |
+| Claude 网页版 / Desktop Chat / Cowork | 不含可执行代码的账户技能 ZIP | 在 Mac 或 Windows 导出后，另行上传、启用并保存账户指令 |
+| Antigravity 对话应用 | 模块化规则与技能 | Apple Silicon Mac、Windows x64；选择工作区或全局范围 |
+
+平台范围沿用 v1.5.0。Windows 原生 Claude Code 不在此版本范围内；Windows
+ARM64 支持属于独立的 v1.6.0 工作。账户技能不会安装原生 Claude 集成。
+
+## 安装或更新
+
+准备 Node.js 20 或更高版本，安装并登录所需应用。安装包内含原生运行时，
+无需另装 Python。从 [v1.5.1 发布页](https://github.com/ParkerHwang/OpenSocrates/releases/tag/v1.5.1)
+获取归档和 SHA-256 校验文件，或使用版本固定的 npm 安装器。
+
+```sh
+npx --yes opensocrates@1.5.1 install --host codex
+npx --yes opensocrates@1.5.1 status --host codex
+# 更新现有 Codex 安装：
+npx --yes opensocrates@1.5.1 update --host codex
+```
+
+在交互式 Codex 中输入 `/hooks`，检查 OpenSocrates 的 7 个钩子，按应用提供的
+信任流程完成必要审批，然后开始新对话。`status` 说明安装及完整性状态，不能
+证明钩子已被信任或指令已在真实任务中应用。
+
+在 Apple Silicon Mac 安装 Claude Code 集成：
+
+```sh
+npx --yes opensocrates@1.5.1 install --host claude
+npx --yes opensocrates@1.5.1 status --host claude
+```
+
+为 Antigravity 指定已存在的工作区绝对路径；省略 `--workspace` 则选择全局范围。
+同一任务避免同时使用工作区和全局副本。
+
+```sh
+npx --yes opensocrates@1.5.1 install --host antigravity --workspace /absolute/path/to/workspace
+```
+
+Windows 使用本地驱动器绝对路径并加引号，例如 `"C:\Work\Reading Workshop"`。
+Claude 账户技能需导出到已存在文件夹内的绝对 ZIP 路径：
+
+```sh
+npx --yes opensocrates@1.5.1 export --host claude-chat --output /absolute/path/to/opensocrates-1.5.1-account.zip
+```
+
+随后在 Claude 的 **Customize → Skills** 上传并启用。替换已有 OpenSocrates
+技能前，下载备份并记录其启用状态。导出成功不等于上传、启用或自动选择成功。
+在 **Settings → General → Instructions for Claude** 追加以下指令，保留原有
+指令；旧版 Cowork 可使用 **Settings → Cowork → Global instructions**。
+网页版和 Desktop 若使用不同账户，应分别设置。
+
+```text
+对于需要解释或判断的任务，例如综合资料、比较方案、作出决策或撰写消息，
+即使我没有提到名称，也请加载已启用的 OpenSocrates 技能并遵循其指令。
+应用推理方法前，先完整阅读其步骤并确认适用条件。对于格式转换等机械性
+工作，不要增加不必要的推理步骤。
+```
+
+保存后开始新对话。账户技能由应用模型选择，可能遗漏；它不新增原生钩子，也
+不保证每条消息都会调用。默认安装和 `--host all` 仍只选择 Codex，其他应用
+必须显式指定。新集成不新增 purge、信任重置或自动更新操作。
+[设置指南（英文）](docs/setup-guide.md)说明后续界面步骤；
+[Mac 指南](docs/macos-v1.5.md)和 [Windows 指南](docs/windows-v1.5.md)保留
+v1.5.0 的安装与恢复基线，当前命令请使用上述 1.5.1 版本。
+
+## 指令语言
+
+优先使用明确指定的语言，其次使用已保存的语言偏好，再根据当前输入的文字
+判断。含平假名或片假名时选择日语；否则韩文占优时选择韩语，汉字占优时
+选择中文。只有汉字的输入无法可靠区分中文与日语，默认使用中文，需要日语
+时应明确指定。空输入、只有拉丁字符或字符数量持平时回退到英文。
+
+推理指令语言与 npm 安装器的命令输出、应用界面语言分开。本次更新不承诺
+翻译每条安装器消息。关于运行时 `locale` 偏好命令和显式 JSON 请求，请参阅
+[语言与范围指南（英文）](docs/v1.5.1.md)。
+
+## 使用标注与隐私
+
+只有完整读取并实际应用了适用的正典方法，最终答案才以完全相同的英文行
+`Powered by OpenSocrates` 结尾。仅使用阅读指导或完成机械性工作不满足条件。
+该行是来源标注，不能证明原生应用成功或答案质量提升。
+
+默认判断路径不额外调用选择模型，不保存原始提示、对话、截图或隐藏推理。
+Claude 原生入口不读取对话，也不初始化数据库；账户技能不含可执行代码。
+应用本身的认证、权限、留存设置及条款仍适用于正常对话。
+[安全政策](SECURITY.md)说明相关边界。安装、加载、完整阅读、实际应用和结果
+是否有用属于不同的证据；本项目不宣称普遍的质量、成本或速度提升。
+
+- [方法正文](content/methods/) · [判断点约定](docs/decision-points.md)
+- [版本变更](CHANGELOG.md) · [贡献指南](CONTRIBUTING.md) · [行为准则](CODE_OF_CONDUCT.md)
+
+OpenSocrates 采用 [MIT 许可证](LICENSE)，是独立项目，不隶属于 OpenAI、
+Anthropic 或 Google，也未获其背书。

package/SECURITY.md

@@ -2,8 +2,14 @@
 
 ## Supported versions
 
-Security fixes are provided for the latest `1.x` release. OpenSocrates 1.4.0
-supports Codex only. Pre-1.0 builds and retired host integrations are unsupported.
+Security fixes are provided for the latest `1.x` release. Version 1.5.0 preserves
+the v1.4 Codex foundation and adds native Mac Claude
+Code, content-only Claude account delivery, and modular Antigravity content.
+The Windows continuation supports content-only Claude account verification/export
+and Antigravity modular lifecycle on x64; native Windows Claude Code is excluded.
+Live account selection and conversation-app loading require separate observations.
+Pre-1.0 builds and retired
+host integrations are unsupported; they are not silently adopted by a new profile.
 
 ## Report a vulnerability
 
@@ -18,7 +24,7 @@ severity, safe fixes, and maintainer availability.
 
 ## Security boundary
 
-The default Codex submission entry emits discovery guidance only. It starts no
+The default native submission entry emits discovery guidance only. It starts no
 selector-model request and creates no initial method artifact. The decision
 command loads fixed canonical content and retains only volatile, context-scoped
 delivery identities and agent availability assertions. It never treats an agent
@@ -27,6 +33,29 @@ does not authorize a CWD-controlled fallback. This command adds no disk state,
 raw prompt logging, conversation retention, screenshot capture, authentication
 call, or telemetry.
 
+The Claude adapter has its own bounded JSON normalization and native response
+shape. It drops private prompt/transcript fields, resolves complete controller
+locations only inside the installed package, and never opens a transcript or
+initializes a database. Stop and SessionEnd do not require a repair or assert a
+native application receipt. Unavailable native entry fails open with empty output.
+
+Claude account exports and Antigravity modular packages contain complete authored
+content without hooks, runtimes, or credential access. An Antigravity standing
+rule links the owned controller; it never authorizes unrelated account or file
+actions. Workspace/global origins and existing user instructions remain separate.
+
+Windows addon operations refuse junctions/reparse ancestors, foreign ownership,
+untrusted writable DACLs, unknown files and changed inventories. New directories
+are created with the current user's explicit owner and protected DACL. A held
+directory lease blocks ancestor rename during mutations; an exclusive operation
+lock is never removed as stale automatically. Rollback preserves changed
+replacement content and its recovery backup. Local drive paths are required;
+network shares are not qualified. Existing settings are not normalized by
+rewriting permissions. ZIP paths reject aliases, streams, links, special entries,
+case collisions and file/directory conflicts before extraction. Portable content
+archives carry fixed regular-file modes and no executables. Account exports use
+verified captured bytes and refuse conflicting output files.
+
 The retained legacy Codex selector is a separate compatibility path. It uses the
 pinned SDK and existing Codex authentication in an isolated worker, with bounded
 read-only context access, disabled recursive hooks/plugins, a deadline, and
@@ -36,7 +65,10 @@ it cannot prove model understanding, method application, or improved answers.
 Legacy SDK credential-copy and POSIX context access are unavailable on Windows.
 
 OpenSocrates has no backend, telemetry, separate account, or API-key requirement.
-Ordinary model requests remain subject to Codex service terms. Host-managed policy
+Ordinary model requests and host conversation storage remain subject to the
+chosen host's authentication, privacy settings, permissions, and service terms.
+The product's no-retention contract does not replace the host's retention policy.
+Host-managed policy
 and hook approvals remain part of the host trust boundary. Installation and
 synthetic fixtures do not establish live hook delivery.
 
@@ -53,8 +85,14 @@ and reports its exact recovery path. Purge refuses unknown, changed, linked, or
 in-use payloads. Codex trust is preserved unless the explicit `--reset-trust`
 option requests removal of the seven exact OpenSocrates trust entries through a
 validated transactional configuration update. Conversation history is preserved.
-Retired-host installation state must be cleaned up with the installer version
-that owned it; 1.4.0 does not reinterpret it as Codex state.
+Retired-host installation state must be reconciled with the installer version
+that owned it; the new profiles do not reinterpret it as Codex or addon state.
+The additive Mac driver verifies exact package inventories and owned markers,
+preserves disabled state, and rejects unknown or modified collisions. Native
+Claude registration uses supported host operations; Antigravity touches only its
+owned rule/skill files. New profiles support exact owned removal, without purge,
+trust reset, or automatic updates. Account export never activates an account
+skill; preserve the old skill and its backup until replacement qualification.
 
 The optional macOS LaunchAgent uses the verified installer and the selected npm
 channel. It does not read or terminate active Codex sessions. Its owner-only
@@ -63,6 +101,11 @@ prompts, transcripts, credentials, workspace paths, or raw errors. Automatic
 updates and automatic major upgrades are opt-in. Windows scheduled updates are
 unavailable; use manual updates.
 
+Those scheduler controls remain in the existing Codex lane. `--host all` does
+not expand it to the additional profiles. Local archive installation
+requires paired `--asset` and `--checksum`; checksum matching does not create a
+published release or establish live host trust.
+
 Windows x64 packages use real owner/DACL checks, binary I/O, file locks, and ZIP
 path validation. Signing, notarization, SmartScreen reputation, Windows ARM64,
 and separate clean-machine or GUI behavior are not inferred from package tests.

package/VERSION

@@ -1 +1 @@
-1.4.0
+1.5.1