Codexhost Release
BytePioneer-AI/codex-host
发布 codexhost 正式版、预览版，编写或确认 Release Notes，检查发布 CI，暂停、恢复或排查发布。支持正常正式发布，以及 npm latest + GitHub Prerelease、不给现有用户更新提示的预览发行。不用于普通代码提交或 Harness CLI 更新。
为 codexhost 新增 Harness 插件，或规划、审查、补全现有 Harness Adapter。按当前公共契约实现原生能力，区分插件后端、预装发行和 Desktop 产品接入；不用于单纯添加 Model、Provider 或账号。
LGPL-3.0Auto-check passed
Install Codexhost Add Harness
$ npx skills add BytePioneer-AI/codex-host --skill codexhost-add-harness -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install BytePioneer-AI/codex-host codexhost-add-harness --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/BytePioneer-AI/codex-host.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/codexhost-add-harness .claude/skills/codexhost-add-harness && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "codexhost-add-harness" agent skill from https://github.com/BytePioneer-AI/codex-host/tree/main/.agents/skills/codexhost-add-harness into .claude/skills/codexhost-add-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codexhost-add-harness", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/BytePioneer-AI/codex-host/tree/main/.agents/skills/codexhost-add-harnessType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add BytePioneer-AI/codex-host --skill codexhost-add-harness -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install BytePioneer-AI/codex-host codexhost-add-harness --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BytePioneer-AI/codex-host.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/codexhost-add-harness .agents/skills/codexhost-add-harness && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "codexhost-add-harness" agent skill from https://github.com/BytePioneer-AI/codex-host/tree/main/.agents/skills/codexhost-add-harness into .agents/skills/codexhost-add-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codexhost-add-harness", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add BytePioneer-AI/codex-host --skill codexhost-add-harness -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install BytePioneer-AI/codex-host codexhost-add-harness --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BytePioneer-AI/codex-host.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/codexhost-add-harness .cursor/skills/codexhost-add-harness && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "codexhost-add-harness" agent skill from https://github.com/BytePioneer-AI/codex-host/tree/main/.agents/skills/codexhost-add-harness into .cursor/skills/codexhost-add-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codexhost-add-harness", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/BytePioneer-AI/codex-host.git --path .agents/skills/codexhost-add-harness--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add BytePioneer-AI/codex-host --skill codexhost-add-harness -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install BytePioneer-AI/codex-host codexhost-add-harness --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BytePioneer-AI/codex-host.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/codexhost-add-harness .gemini/skills/codexhost-add-harness && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "codexhost-add-harness" agent skill from https://github.com/BytePioneer-AI/codex-host/tree/main/.agents/skills/codexhost-add-harness into .gemini/skills/codexhost-add-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codexhost-add-harness", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install BytePioneer-AI/codex-host codexhost-add-harnessInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add BytePioneer-AI/codex-host --skill codexhost-add-harness -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/BytePioneer-AI/codex-host.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/codexhost-add-harness .github/skills/codexhost-add-harness && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "codexhost-add-harness" agent skill from https://github.com/BytePioneer-AI/codex-host/tree/main/.agents/skills/codexhost-add-harness into .github/skills/codexhost-add-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codexhost-add-harness", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add BytePioneer-AI/codex-host --skill codexhost-add-harness -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install BytePioneer-AI/codex-host codexhost-add-harness --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BytePioneer-AI/codex-host.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/codexhost-add-harness .opencode/skills/codexhost-add-harness && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "codexhost-add-harness" agent skill from https://github.com/BytePioneer-AI/codex-host/tree/main/.agents/skills/codexhost-add-harness into .opencode/skills/codexhost-add-harness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codexhost-add-harness", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
codexhost-add-harness- GitHub stars
- 2.8k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 194 words
- Files
- 8 (incl. references)
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- LGPL-3.0
At a glance
为 codexhost 新增 Harness 插件，或规划、审查、补全现有 Harness Adapter。按当前公共契约实现原生能力，区分插件后端、预装发行和 Desktop 产品接入；不用于单纯添加 Model、Provider 或账号。
- Works in 4 steps: 确定交付范围和能力 → 实现插件的四个职责 → 按范围完成加载和产品接入 → …
- SKILL.md covers 当前架构边界, 1. 确定交付范围和能力, 2. 实现插件的四个职责 and 3. 按范围完成加载和产品接入, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Codexhost Add Harness is an agent skill from BytePioneer-AI/codex-host. 为 codexhost 新增 Harness 插件，或规划、审查、补全现有 Harness Adapter。按当前公共契约实现原生能力，区分插件后端、预装发行和 Desktop 产品接入；不用于单纯添加 Model、Provider 或账号。
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `references/cross-harness-delegation.md`, `references/current-harness-implementations.md` and `references/output-and-interactions.md`).
The repository describes itself as: Run Pi and Claude Code directly in Codex Desktop. 在 Codex Desktop 中直接运行 Pi 和 Claude Code。 The licence is LGPL-3.0.
Example prompts
- “/codexhost-add-harness”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 08c7d65. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Codexhost Add Harness loads about 1.2k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 36 tokens; SKILL.md has 194 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from BytePioneer-AI/codex-host at commit 08c7d65, republished under its LGPL-3.0 licence (© BytePioneer-AI). 194 words, ~1,185 tokens.
Download SKILL.mdSave it as
.claude/skills/codexhost-add-harness/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- codexhost-add-harness
- description
- 为 codexhost 新增 Harness 插件，或规划、审查、补全现有 Harness Adapter。按当前公共契约实现原生能力，区分插件后端、预装发行和 Desktop 产品接入；不用于单纯添加 Model、Provider 或账号。
新增 codexhost Harness 插件
目标：交付一个通过公共契约工作的独立插件，而不是在 Host 中增加一套 Harness 专用流程。插件是交付与加载单元，HarnessAdapter / HarnessSession 是运行时接口；不要求继承基类，也不要求使用 ACP。
本文代码路径以仓库根目录为基准，references/ 链接相对于本 Skill。接口签名、字段限制和当前行为以源码为准；参考文档是实现与验收清单，不是第二份接口定义。
当前架构边界
Host
├─ 发现 Manifest、读取显式启用配置、调用插件工厂
├─ 通过 HarnessAdapter / HarnessSession 执行业务
└─ 拥有 Thread 映射、持久化事务、委派和 Desktop 协议投影
│ 公共契约
▼
插件
├─ Manifest：身份、版本、展示信息、入口
├─ 工厂：把 Host Context 转成原生构造参数
├─ HarnessAdapter：检查、打开 Session、关闭共享资源
└─ HarnessSession：执行、输出、状态、历史、关闭
│ 插件内部
▼
原生 SDK / RPC / 服务 / CLI- 七个既有 Harness 和用户插件共用动态加载器，Host 不静态依赖具体 Adapter 包。新 ID 使用共享插件路由。
- 公共工具仍可复用：例如
harness-discovery实现搜索机制，插件声明命令名、环境变量和安装目录策略。 - 完整产品去专属化尚未完成：Renderer 仍有固定 Agent 名单、配置字段和展示接线；旧路由、部分恢复策略、Credits、导入、Broker 与远程配置仍有历史特例。插件加载成功不等于自动出现在 Desktop。
- 既有特例是兼容负担，不是新 Harness 的实现模板。公共契约无法表达真实需求时，记录缺口并在当前任务范围内设计公共扩展；不得通过新 Harness 专用 Host 分支绕过契约。
1. 确定交付范围和能力
从用户请求判断范围；只有会影响实现边界的歧义才询问，不默认扩展为全产品改造。
| 交付范围 | 必须完成 | 不自动包含 |
|---|---|---|
| 插件后端 | 原生适配、Manifest/工厂、可运行依赖、隔离目录加载、公共行为测试 | 仓库预装、Desktop UI |
| 预装发行 | 插件后端 + Workspace 构建、预装清单、独立 Bundle、许可与发行验收 | Renderer 自动发现 |
| Desktop 产品接入 | 插件后端 + Picker、配置、恢复、展示及 UI 验收 | 必须成为预装插件 |
普通持久化 Thread 和完整委派要求可写 resume。原生系统不支持时，可以交付明确受限的后端，但不能把它称为完整产品接入；当前没有自动 ephemeral Thread 降级。
先读取以下权威入口：
packages/harness-adapter/src/text-session.ts：Adapter、Session、命令、事件和可选接口。packages/harness-adapter/src/plugin.ts：工厂和 Context。packages/shared-contracts/src/harness-models.ts：Catalog、能力和检查结果。packages/shared-contracts/src/harness-plugins.ts：Manifest、描述与启用配置。docs/architecture/harness-plugin-runtime.md：已实现边界、安装、信任和发行规则。
核对目标 Harness 的当前原生接口、版本、认证和运行方式。实际可行时优先原生 SDK、RPC 或服务接口；只有原生接口不可用或确有理由时使用 ACP，并记录能力差异。不要以 CLI 名称相似推断协议兼容。
使用 实现导航 按传输和能力选参考，不整包复制。输出简短计划：
交付：插件后端 / 预装发行 / Desktop（可组合）
原生接口与版本：……
支持：create、resume、Turn、取消、历史、工具、Question……
不支持或受限：Fork、权限仅创建时设置……
待验证：……（不能当作不支持，也不能声明已实现）
参考模块：……
预计修改：插件目录；其他位置逐项说明原因本步完成条件：每项目标能力都有原生依据、公共映射或明确缺口，并且交付范围清楚。
2. 实现插件的四个职责
以下是职责清单，不是强制文件数量。Pi 的 Adapter 和 Session 就在同一个源文件中。
| 职责 | 必须提供 | 按需提供 |
|---|---|---|
| Manifest | manifestVersion、id、name、version、adapterApiVersion、entry | icon、文档/安装链接 |
| 工厂模块 | createHarnessAdapter(context)，返回身份匹配的实例 | warmup(adapter) |
HarnessAdapter | harnessId、inspect()、open()、close() | sessionImport、subagents、webUi |
HarnessSession | harnessId、capabilities、initialState、initialUsage、outputs、readSnapshot()、execute()、close() | commands、refreshUsage() |
execute() 必须处理公共命令的分派：turn.start、turn.cancel、interaction.respond、model.select、thinking.select、permissionMode.select。open() 必须识别 create、resume、fork、rollbackLastTurn。存在接口不代表必须支持所有原生操作：不支持的分支返回类型化 unsupported，不伪造成功。
所有新插件都读取并满足：
- 公共行为：检查、配置、并发、错误、环境和可选接口。
- 输出与交互：Turn/Item 时序、原生输出映射、取消和故障。
- 身份与历史：所有插件的 identity、快照要求；按能力实现 resume/Fork/Rollback。
- 加载、发行与验证：Manifest、工厂、依赖及 Host 接入验证。
实现需要的原生 Transport、模型转换、历史、Usage 和交互模块。优先复用 packages/harness-adapter/src/index.ts 导出的校验、输出流和诊断工具；CLI 搜索复用 packages/harness-discovery/src/index.ts。拆文件按职责，不为统一形式添加空模块、空 warmup 或多余封装。
本步完成条件：公共接口能跑通真实原生操作，声明与行为一致；所有支持能力已实现，未实现项明确标注，失败与关闭不遗留活动资源。
3. 按范围完成加载和产品接入
- 所有插件：按加载、发行与验证构建可搬移的插件，在隔离根目录显式启用，通过真实 Loader 验证；直接
new Adapter()的测试不能替代插件加载。 - 仓库内实现或预装发行：读取该参考中的 Workspace/发行分支。用户独立插件不需要修改预装清单；Host 包不得增加具体 Adapter 依赖。
- Desktop 产品接入：读取Renderer 产品接入，处理当前静态 UI 边界；新插件路由仍用共享 codec，不新增专用编码。「调整方向」沿用公共路径，插件侧验证取消与后续 Turn。
- 接收委派、继续向下委派或声明完整 Agent 协调：读取跨 Harness 委派。它复用普通可写 Thread，不另建一套执行接口。
- 新增公共能力：同时核对类型、schema、Host 投影、使用方和测试。浏览器共享契约保持 Node-free，Renderer 不导入原生 SDK 或 Electron 私有 API。
本步完成条件：每个范围都有对应产物和验收证据；未启用的范围不做机械接线。现有 Harness 无需知道新 Harness 的私有信息。
4. 验证和交付
按验证分层执行聚焦检查，不默认运行全仓库测试。新增插件不能以构建通过替代原生语义验证，也不能以一次聊天成功替代取消、交互、恢复和清理验证。
交付报告包含：
- 插件位置、ID、原生接口及验证版本；入口、依赖、资源和安装/启用方式。
- 支持、不支持、受限、未验证的能力，以及必要的认证或平台条件。
- 实际修改了哪些插件外文件及原因；公共专用分支是否有新增。
- 已执行检查、原生/目标环境验证；跳过或受阻检查及原因。
- 分别标记插件后端、预装发行、Desktop 和完整委派的完成情况；不适用项写不适用。
只有范围内的实现、能力声明、测试和文档一致，才能宣布该范围完成。发现公共层缺口或原生限制时交付明确结论，不把受限实现包装成完整支持。
© BytePioneer-AI, LGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 7 other files (references) in .agents/skills/codexhost-add-harness of BytePioneer-AI/codex-host.
- SKILL.md
- references/cross-harness-delegation.md
- references/current-harness-implementations.md
- references/output-and-interactions.md
- references/public-adapter-contract.md
- references/registration-and-validation.md
- references/renderer-product-integration.md
- references/thread-lifecycle-and-history.md
Open the folder on GitHubat commit 08c7d65
Compare with similar skills
Codexhost Add Harness next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Codexhost Add Harness this skillBytePioneer-AI/codex-host | 2.8k | — | ~1.2k | Automated safety check: Pass | LGPL-3.0 | |
| Codexhost ReleaseBytePioneer-AI/codex-host | 2.8k | — | ~998 | Automated safety check: Pass | LGPL-3.0 | |
| Codexhost PR TriageBytePioneer-AI/codex-host | 2.8k | — | ~1.1k | Automated safety check: Pass | LGPL-3.0 | |
| Codexhost Update Impact AuditBytePioneer-AI/codex-host | 2.8k | — | ~3.5k | Automated safety check: Pass | LGPL-3.0 | |
| Architecture GovernanceBytePioneer-AI/codex-host | 2.8k | — | ~710 | Automated safety check: Pass | LGPL-3.0 | |
| Dep RefsBytePioneer-AI/codex-host | 2.8k | — | ~488 | Automated safety check: Pass | LGPL-3.0 |
Similar skills
Codexhost PR Triage
BytePioneer-AI/codex-host
手动增量分诊 codexhost Issue 与 PR，评估 PR 价值和实现克制，生成只读本地看板与回复草稿. An agent skill from BytePioneer-AI/codex-host.
Codexhost Update Impact Audit
BytePioneer-AI/codex-host
Diagnose whether a Codex Desktop update changed codexhost Composer/CDP bindings, private Renderer DOM or React state, Host bridges, routing, the Codex usage submission gate, or injected UI.
Architecture Governance
BytePioneer-AI/codex-host
Apply codexhost package and native ownership rules when changing production code or dependency directions.
Dep Refs
BytePioneer-AI/codex-host
Trace TypeScript exports, imports, and re-exports in codexhost before refactoring interfaces or deleting code.
Feature Boundary Planner
BytePioneer-AI/codex-host
Trace a codexhost feature change across UI surfaces, Host routing, Harness capabilities, state ownership, persistence, and validation.
More from BytePioneer-AI/codex-host
All 9 skills in this repoWeb Gui Tester
BytePioneer-AI/codex-host
Verify web frontend behavior through real GUI interactions, read-only page inspection, and screenshots.
Control Browser
BytePioneer-AI/codex-host
Control a browser using the tools available in the current session to navigate, inspect, click, fill, capture and verify pages.
Questions about Codexhost Add Harness
What does Codexhost Add Harness do?
为 codexhost 新增 Harness 插件，或规划、审查、补全现有 Harness Adapter。按当前公共契约实现原生能力，区分插件后端、预装发行和 Desktop 产品接入；不用于单纯添加 Model、Provider 或账号。. Codexhost Add Harness is an agent skill from BytePioneer-AI/codex-host.
How do I install Codexhost Add Harness in Claude Code?
Run `npx skills add BytePioneer-AI/codex-host --skill codexhost-add-harness -a claude-code`. Or copy the skill folder (.agents/skills/codexhost-add-harness in BytePioneer-AI/codex-host) into .claude/skills/codexhost-add-harness in your project. Claude Code loads it when a task matches its description.
How do I install Codexhost Add Harness in Codex?
Run `npx skills add BytePioneer-AI/codex-host --skill codexhost-add-harness -a codex`. Or copy the skill folder (.agents/skills/codexhost-add-harness in BytePioneer-AI/codex-host) into .agents/skills/codexhost-add-harness in your project. Codex loads it when a task matches its description.
Can I use Codexhost Add Harness in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add BytePioneer-AI/codex-host --skill codexhost-add-harness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codexhost-add-harness, .gemini/skills/codexhost-add-harness, .github/skills/codexhost-add-harness and .opencode/skills/codexhost-add-harness in your project.
What does Codexhost Add Harness need to run?
SKILL.md names no scripts, command-line tools or credentials: Codexhost Add Harness is instructions for the agent only.
Does Codexhost Add Harness access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Codexhost Add Harness safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Codexhost Add Harness use?
Codexhost Add Harness is published under the LGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Codexhost Add Harness use?
About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.
What are the alternatives to Codexhost Add Harness?
Skills that share tags, products or a category with Codexhost Add Harness: Codexhost Release (BytePioneer-AI/codex-host, 2.8k stars), Codexhost PR Triage (BytePioneer-AI/codex-host, 2.8k stars), Codexhost Update Impact Audit (BytePioneer-AI/codex-host, 2.8k stars) and Architecture Governance (BytePioneer-AI/codex-host, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Codexhost Add Harness?
BytePioneer-AI (a GitHub user) maintains it in BytePioneer-AI/codex-host, which has 2,791 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 9, 2026.
Source: BytePioneer-AI/codex-host on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.