Enterprise DNAEnterprise DNA

Skills

deepseek-codex-subagent

by Zedong-Liu

Run DeepSeek-powered Codex sidecars as cost-effective worker agents under a GPT main brain.

This project appears archived and may no longer be maintained.

Our verdict

Not reviewed yet

We have not reviewed deepseek-codex-subagent yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About deepseek-codex-subagent

A Python tool that runs DeepSeek-powered Codex sidecars as worker agents under a GPT main brain. It coordinates tasks between the main GPT agent and cost-effective DeepSeek subagents.

Best for

Developers seeking to cut coding agent costs by using DeepSeek for subtasks under GPT orchestration.

Use cases

  • Delegating coding subtasks to DeepSeek agents while keeping GPT as orchestrator
  • Reducing API costs by using cheaper models for routine code generation
  • Running parallel Codex sidecars for multi-step development workflows

Notes

25 stars on GitHub. Last updated 2026-10-20.

Pros

  • Cost-effective by offloading work to cheaper DeepSeek models
  • Flexible architecture with a main brain and worker sidecars
  • Simple Python implementation for easy integration

Cons

  • Low star count (25) suggests limited community validation
  • Requires managing multiple agents and potential coordination overhead
  • Dependent on DeepSeek and GPT API availability and reliability

Key facts

What we have checked

Days since the last commit
11
Checked GitHub
GitHub forks
5
Checked GitHub
GitHub stars
25
Checked GitHub
Open issues
0
Checked GitHub
Releases in the last 90 days
0
Checked GitHub

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

Health and security

Is deepseek-codex-subagent looked after, and what do its setup files show

Security check static checks

87 out of 100

Reads what is published about the server: package advisories, licence, secrets in the documented setup and tool permissions. Nothing is installed or run, so this is not a security assessment. Checked by edna-skill-static-v1 main@fbd9253bd617. What it checks

  • Medium Reads or points the agent at stored credentials (the macOS keychain): scripts/codex-deepseek-keychain-token, line 14.
  • Low Downloads code and runs it straight away (a well-known installer), host cdn.deepseek.com: SKILL.md, README.en.md, README.md, line 45, 3 places in all.
  • Note No dependency list or install command was found in the skill, so there were no packages to look up on OSV.

Sources

Where this comes from

  • GitHubRegistry

    Checked · Days since the last commit, GitHub forks, GitHub stars, Open issues, Releases in the last 90 days

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.