codex-subagents

codex-subagents is a skill for Claude Code, Codex from duolahypercho/codex-router. It costs 72 tokens per session (1,596 once invoked), scanned A, original, MIT.

A setup and troubleshooting guide for having Codex delegate work to other AI models through codex-router, a tool that selects which models can be used as subagents.

In plain words
What is it for?
It helps check which models can currently be spawned, configure the allowed model list, and verify that delegated agents work.
Why use it?
It helps identify why a model is unavailable, why the wrong model was selected, or why creating a subagent fails.

Skill for Claude CodeCodex

About the project

Codex Router is a local model-routing setup that connects Codex and several other coding agents to external providers such as Kimi, DeepSeek, Anthropic, xAI, and GitHub Copilot. It is for users who want to configure routed models and manage provider credentials locally across supported agent clients. Its catalogue entries provide skills and instructions for installing and operating the router.

duolahypercho/codex-router · 3,100 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/duolahypercho/codex-router/codex-subagents
Any agent
npx skills add duolahypercho/codex-router --skill codex-subagents
Clone the repo
git clone --depth 1 https://github.com/duolahypercho/codex-router

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for codex-subagents

README.md
[![agentmods](https://agentmods.dev/badge/skills/duolahypercho/codex-router/codex-subagents.svg)](https://agentmods.dev/skills/duolahypercho/codex-router/codex-subagents)
Your own site
<a href="https://agentmods.dev/skills/duolahypercho/codex-router/codex-subagents"><img src="https://agentmods.dev/badge/skills/duolahypercho/codex-router/codex-subagents.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,596 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.01596
Opus 5 $0.00036 $0.00798
Sonnet 5 $0.00014 $0.00319
Haiku 4.5 $0.00007 $0.00160

Measured 6d ago against content hash 021e9786a3f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

codex-subagents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (subagent-report.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/codex-subagents/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spawning subagents through codex-router

Codex can delegate a task to a subagent running on a different model. codex-router decides which models Codex is allowed to pick. This skill covers getting the right models offered, proving they actually work, and fixing it when they don't.

Run every command from the codex-router checkout.

Start here, always

node .claude/skills/codex-subagents/subagent-report.mjs

This answers the only question that matters — if I ask Codex to spawn a subagent right now, what can it pick? — and it is the one question control subagents status does not answer. That command reports your intent. The merged catalog is what Codex actually reads. They drift apart silently, and the report catches the drift.

If the report says a model is spawnable, it is offered to Codex. If it doesn't appear there, nothing else you do in Codex will surface it.

How a model becomes spawnable

A model carries multiAgentVersion: "v2" in the catalog. Three modes decide who gets it:

Mode Effect
proven Only models the registry ships as verified. Conservative default.
selected Proven models plus ones you explicitly turn on. Use this.
all Every non-hidden model, regardless of whether it works.
./bin/control subagents status                    # current mode, enabled, disabled
./bin/control subagents mode selected
./bin/control subagents set opencode-go/glm-5.2 on
./bin/control subagents set qwen-plan/qwen3.6-flash off
./bin/control subagents select-all                # turn every model on
./bin/control subagents unselect-all              # clear the list, back to a clean slate

An explicit off beats every mode, including all. That is how you keep a model out without leaving all — verified: under mode: all, a model in disabled still resolves to v1.

unselect-all is the fastest way out of a crowded list when the models you want have been pushed past what Codex advertises.

Read the full file on GitHub · 154 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 154 lines · 72 tokens per session scan A 021e9786a3f8

Subscribe to this mod's changes

codex-subagents is a skill published in the GitHub repository duolahypercho/codex-router (3,100 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 1,596 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.