Agent skill

Codex Deepseek Subagent

by oil-oil in oil-oil/codex-deepseek-subagent

配置和维护 Codex 桌面应用中的 DeepSeek 原生子 Agent,支持模型选择、路由验证、修复、停用和卸载。仅在用户要求配置或管理该集成时使用;普通 API 问题与配置后的日常编码任务不触发。

MITAuto-check passedAgent Workflows

Install Codex Deepseek Subagent

skills CLI
$ npx skills add oil-oil/codex-deepseek-subagent --skill codex-deepseek-subagent -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install oil-oil/codex-deepseek-subagent codex-deepseek-subagent --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/oil-oil/codex-deepseek-subagent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/codex-deepseek-subagent .claude/skills/codex-deepseek-subagent && rm -rf skills-src

Use ~/.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/

Facts

Skill name
codex-deepseek-subagent
GitHub stars
374
Token cost
~673 tokens
SKILL.md length
161 words
Files
36 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

配置和维护 Codex 桌面应用中的 DeepSeek 原生子 Agent,支持模型选择、路由验证、修复、停用和卸载。仅在用户要求配置或管理该集成时使用;普通 API 问题与配置后的日常编码任务不触发。

  • Works in 7 steps: 运行 status --json,根据结构化状态继续,不靠文件名猜测。 → 首次配置时,如果用户没有指定模型,先让用户选择:DeepSeek V4… → 配置请求运行 setup --model <模型>… → …
  • Tasks that involve Subagents
  • SKILL.md covers API Key 配置入口, 关键契约, 触发后的流程 and 管理命令, plus 1 more section
  • Runs Python and JavaScript scripts from its folder; calls codex

What it does

Codex Deepseek Subagent is an agent skill from oil-oil/codex-deepseek-subagent. 配置和维护 Codex 桌面应用中的 DeepSeek 原生子 Agent,支持模型选择、路由验证、修复、停用和卸载。仅在用户要求配置或管理该集成时使用;普通 API 问题与配置后的日常编码任务不触发。

Its SKILL.md is about 670 tokens, which your agent loads only when the skill is triggered. The skill folder holds 42 other files, including scripts and reference files (for example `agents/openai.yaml`, `evals/evals.json` and `references/api-key-setup.md`).

It sits in Agent Workflows, covering Subagents. It works with DeepSeek. The repository describes itself as: 配置和维护桌面应用中的原生子 Agent,支持选择模型、检查路由、修复、停用和卸载。 The licence is MIT.

When your agent uses it

  • Tasks that involve Subagents

Example prompts

  • “/codex-deepseek-subagent”

Requirements

  • Python 3
  • Node.js

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. 运行 status --json,根据结构化状态继续,不靠文件名猜测。
  2. 首次配置时,如果用户没有指定模型,先让用户选择:DeepSeek V4 Flash(更快、更省)或 DeepSeek V4 Pro(能力更强,推荐复杂任务)。不要替用户静默选择。
  3. 配置请求运行 setup --model <模型> --json;切换模型或修复配置时运行 repair --model <模型> --json。不传 --model 的 repair 会保留当前选择。
  4. 缺少凭据时按配置说明展示固定页面,由用户保存后,经 run 入口运行 setup 并传 --api-key-env,接入运行时原生凭据;不在聊天中索要 API Key。--api-key-stdin 仅供可信凭据程序传递,不拼接密钥命令。
  5. setup、repair 或 test 使用桌面内置运行时创建隔离验收会话。若返回 new_task_required 或 restart_required,提示用户重启桌面应用并打开新任务。
  6. 验收必须检查子线程数据库 threads 表的实际元数据,并确认子 Agent 返回口令 NATIVE_DEEPSEEK_OK。实际 model 必须等于用户选择的模型,两者缺一不可。
  7. 最终只汇报状态、实际 Provider、模型、思考程度、角色和备份位置;不要输出密钥或原始事件日志。

What it can do on your machine

Read from SKILL.md and the folder at commit 978b079. 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

    Ships 9 files in scripts/ (Python and JavaScript, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • codex

    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

Codex Deepseek Subagent loads about 673 tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 31 tokens; SKILL.md has 161 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~673
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.7k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from oil-oil/codex-deepseek-subagent at commit 978b079, republished under its MIT licence (© oil-oil). 161 words, ~673 tokens.

Download SKILL.mdSave it as .claude/skills/codex-deepseek-subagent/SKILL.md (or your agent's skills folder). This skill also uses 35 other files; get the full folder from GitHub.
name
codex-deepseek-subagent
description
配置和维护 Codex 桌面应用中的 DeepSeek 原生子 Agent,支持模型选择、路由验证、修复、停用和卸载。仅在用户要求配置或管理该集成时使用;普通 API 问题与配置后的日常编码任务不触发。

Codex DeepSeek 子 Agent

本 Skill 只维护配置,不承接日常用户任务。确定性的文件、模型目录和凭据操作交给 scripts/codex_deepseek.py;不要手动改 TOML、JSON、Agent 文件或系统凭据库。

API Key 配置入口

需要外部服务凭据时先读API Key 配置与业务读取:复用已有安全入口;本机缺少 Key 时使用随附固定页面,保存后通过业务包装入口读取。内置能力与纯本地流程不要求配置 Key。

关键契约

  • 只使用桌面应用内置的 Codex 运行时;版本仅用于诊断,兼容性以真实派发验收为准。

  • 从桌面配置读取父模型,并由管理程序应用 v1 明文派发设置;不要硬编码父模型或手改配置。技术原因见 references/compatibility.md。

  • 父模型变化后必须运行 repair,再重新验收。

  • 支持 deepseek-v4-flash 与 deepseek-v4-pro。Flash 更快、更省;Pro 能力更强,适合复杂 Agent 任务。两者默认思考程度均为 high。

  • DeepSeek 是纯文本 Agent,不处理图片、视频、截图或其他视觉输入。父 Agent 先识别视觉内容,再传入文字事实。

  • 日常任务只能直接调用:

    text
    spawn_agent(agent_type="DeepSeek", fork_turns="none", ...)

    不要为日常任务运行本 Skill、管理脚本或 codex exec。

  • 当前工具若不认识 DeepSeek 角色,只提示用户打开新任务或重启 Codex;不得改用默认角色、脚本或 codex exec 代做当前任务。

触发后的流程

  1. 运行 status --json,根据结构化状态继续,不靠文件名猜测。
  2. 首次配置时,如果用户没有指定模型,先让用户选择:DeepSeek V4 Flash(更快、更省)或 DeepSeek V4 Pro(能力更强,推荐复杂任务)。不要替用户静默选择。
  3. 配置请求运行 setup --model <模型> --json;切换模型或修复配置时运行 repair --model <模型> --json。不传 --model 的 repair 会保留当前选择。
  4. 缺少凭据时按配置说明展示固定页面,由用户保存后,经 run 入口运行 setup 并传 --api-key-env,接入运行时原生凭据;不在聊天中索要 API Key。--api-key-stdin 仅供可信凭据程序传递,不拼接密钥命令。
  5. setup、repair 或 test 使用桌面内置运行时创建隔离验收会话。若返回 new_task_required 或 restart_required,提示用户重启桌面应用并打开新任务。
  6. 验收必须检查子线程数据库 threads 表的实际元数据,并确认子 Agent 返回口令 NATIVE_DEEPSEEK_OK。实际 model 必须等于用户选择的模型,两者缺一不可。
  7. 最终只汇报状态、实际 Provider、模型、思考程度、角色和备份位置;不要输出密钥或原始事件日志。

管理命令

入口。macOS 使用 python3,Windows 使用 py -3:

text
python3 <skill-dir>/scripts/codex_deepseek.py <command> --json
  • status:只读检查桌面内置运行时、配置、模型目录、凭据和客户端能力。
  • setup:使用 --model deepseek-v4-flash 或 --model deepseek-v4-pro 写入配置并验收;未选择时返回 model_selection_required。
  • test:通过桌面内置运行时执行一次直连测试和一次原生 spawn_agent(agent_type="DeepSeek") 验收。
  • repair:按当前父模型重新应用配置并验收;传 --model 可切换模型,不传则保留当前模型。
  • disable:停用本 Skill 创建的角色,保留 Provider、模型目录和凭据。
  • uninstall:移除本 Skill 管理的配置;只有用户明确要求删除凭据时才传 --remove-credential。

默认使用当前 CODEX_HOME;仅在用户明确指定其他 Codex Home 时传 --codex-home。

状态处理

  • ready:直连、原生路由、数据库元数据和返回口令均通过。
  • configured:静态配置完整,但尚未完成实时验收。
  • credential_missing:引导用户通过固定页面保存,再经包装器完成运行时配置后继续原流程。
  • model_selection_required:向用户展示 Flash/Pro 选项,得到选择后继续原流程。
  • operation_in_progress:已有配置操作正在运行,稍后重试,不并发修改。
  • conflict:报告冲突文件和字段,等待用户决定是否替换。
  • unsupported:报告缺少的系统能力,不按固定版本号猜测兼容性,也不手工绕过。
  • failed:读取结构化 errors;若程序已回滚,明确说明,不再手改配置。

更详细的路径、版本和安全边界见 references/compatibility.md。

© oil-oil, MIT. 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 35 other files (scripts, references) in codex-deepseek-subagent of oil-oil/codex-deepseek-subagent.

  • SKILL.md
  • agents/openai.yaml
  • evals/evals.json
  • references/api-key-setup.md
  • references/compatibility.md
  • scripts/codex_deepseek.py
  • scripts/credential-ui/README.md
  • scripts/credential-ui/component.json
  • scripts/credential-ui/manifests/default.json
  • scripts/credential-ui/manifests/profiles.json
  • scripts/credential-ui/package-lock.json
  • scripts/credential-ui/package.json
  • scripts/credential-ui/public/app.js
  • scripts/credential-ui/public/favicon.svg
  • … and 22 more

Open the folder on GitHubat commit 978b079

Compare with similar skills

Codex Deepseek Subagent 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.

Codex Deepseek Subagent compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codex Deepseek Subagent this skilloil-oil/codex-deepseek-subagent374—~673Automated safety check: PassMIT
Subagentethanhq/cc-fleet216—~4.9kAutomated safety check: PassApache-2.0
Subagentethanhq/cc-fleet216—~4.3kAutomated safety check: PassApache-2.0
DeepSeek V4 Thinking-Mode Rulescodewhale-hq/Codewhale41k—~443Automated safety check: PassMIT
DeepSeek Harness DelegationCherryHQ/cherry-studio53k—~359Automated safety check: PassAGPL-3.0
Ade Harnessesarul28/ADE114—~1.6kAutomated safety check: PassAGPL-3.0

Similar skills

  • Subagent

    ethanhq/cc-fleet

    Fan out a one-shot or flat parallel batch of cc-fleet PROVIDER subagents (headless cc-fleet subagent) that return a result — DeepSeek / GLM / Kimi / Qwen / MiniMax, or a Codex/Claude subscription.

    216 GitHub stars~4.9k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed
  • Subagent

    ethanhq/cc-fleet

    Run a one-shot or flat parallel batch of provider LLM subagents (headless cc-fleet subagent) that return a result.

    216 GitHub stars~4.3k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed
  • DeepSeek V4 Thinking-Mode Rules

    codewhale-hq/Codewhale

    Three rules for multi-step work with DeepSeek V4 thinking models: verify references, use a verifier subagent before big edits, and write plans with exact path and line.

    41k GitHub stars~443 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • DeepSeek Harness Delegation

    CherryHQ/cherry-studio

    Hands a bounded repository task to the DeepSeek Harness CLI (dsh) in headless mode, then checks the exit code and the diff before reporting back.

    53k GitHub stars~359 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Ade Harnesses

    arul28/ADE

    A skill your agent uses when you need to run a chat, a CLI session, or a subagent on a specific setup — any model you pay for inside any harness (e.g.

    114 GitHub stars~1.6k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Go Spec Reviewer

    inference-gateway/inference-gateway

    Review a Go design spec before implementation begins - dispatch a subagent that checks a design doc for completeness, consistency, and idiomatic Go (simplicity, small consumer-defined interfaces…

    214 GitHub stars~1.2k tokensUpdated today
    DevOps & CloudAuto-check passed

Works with

Categories

Questions about Codex Deepseek Subagent

What does Codex Deepseek Subagent do?

配置和维护 Codex 桌面应用中的 DeepSeek 原生子 Agent,支持模型选择、路由验证、修复、停用和卸载。仅在用户要求配置或管理该集成时使用;普通 API 问题与配置后的日常编码任务不触发。. Codex Deepseek Subagent is an agent skill from oil-oil/codex-deepseek-subagent.

When should I use Codex Deepseek Subagent?

Codex Deepseek Subagent fits situations like: tasks that involve Subagents.

How do I install Codex Deepseek Subagent in Claude Code?

Run `npx skills add oil-oil/codex-deepseek-subagent --skill codex-deepseek-subagent -a claude-code`. Or copy the skill folder (codex-deepseek-subagent in oil-oil/codex-deepseek-subagent) into .claude/skills/codex-deepseek-subagent in your project. Claude Code loads it when a task matches its description.

How do I install Codex Deepseek Subagent in Codex?

Run `npx skills add oil-oil/codex-deepseek-subagent --skill codex-deepseek-subagent -a codex`. Or copy the skill folder (codex-deepseek-subagent in oil-oil/codex-deepseek-subagent) into .agents/skills/codex-deepseek-subagent in your project. Codex loads it when a task matches its description.

Can I use Codex Deepseek Subagent 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 oil-oil/codex-deepseek-subagent --skill codex-deepseek-subagent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codex-deepseek-subagent, .gemini/skills/codex-deepseek-subagent, .github/skills/codex-deepseek-subagent and .opencode/skills/codex-deepseek-subagent in your project.

What does Codex Deepseek Subagent need to run?

Going by SKILL.md and its folder, Codex Deepseek Subagent needs Python and JavaScript for the scripts in its folder and the command-line tools its instructions call (codex). Our summary lists: Python 3; Node.js.

Does Codex Deepseek Subagent 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 Codex Deepseek Subagent 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Codex Deepseek Subagent use?

Codex Deepseek Subagent is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codex Deepseek Subagent use?

About 673 tokens (SKILL.md is roughly 2.7k 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 2k tokens, read only when the agent opens those files.

What are the alternatives to Codex Deepseek Subagent?

Skills that share tags, products or a category with Codex Deepseek Subagent: Subagent (ethanhq/cc-fleet, 216 stars), Subagent (ethanhq/cc-fleet, 216 stars), DeepSeek V4 Thinking-Mode Rules (codewhale-hq/Codewhale, 41k stars) and DeepSeek Harness Delegation (CherryHQ/cherry-studio, 53k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codex Deepseek Subagent?

oil-oil (a GitHub user) maintains it in oil-oil/codex-deepseek-subagent, which has 374 GitHub stars. The repository was last updated on September 10, 2026.

Source: oil-oil/codex-deepseek-subagent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.