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.
Borrowing it
Nothing to install: this file belongs to duolahypercho/codex-router. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/duolahypercho/codex-router/main/.claude/skills/codex-subagents/SKILL.mdgit clone --depth 1 https://github.com/duolahypercho/codex-routerWrote 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.
[](https://agentmods.dev/skills/duolahypercho/codex-router/codex-subagents)<a href="https://agentmods.dev/skills/duolahypercho/codex-router/codex-subagents"><img src="https://agentmods.dev/badge/skills/duolahypercho/codex-router/codex-subagents/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.01747 |
| Opus 5.5 | $0.00029 | $0.00699 |
| Sonnet 5.5 | $0.00014 | $0.00349 |
| Haiku 4.5 | $0.00007 | $0.00175 |
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 1mo ago.
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.
How it starts
The opening of the file, as written. The whole thing — 167 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.
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.
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.
- 1mo ago Changed · +13 lines f7a8e7be3975
- 2mo ago First seen · 154 lines · 72 tokens per session scan A 021e9786a3f8
codex-subagents is a skill published in the GitHub repository duolahypercho/codex-router (3,971 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,747 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
plugin-creator
Create and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries…
codex-pr-body
Update the title and body of one or more pull requests.
qa-testing
Verify your work by actually operating the app or website you changed, instead of assuming it works. Strongly recommended whenever you build, modify, or debug a web app, website, or desktop GUI app. Drive real browsers with the agent-browser CLI and native desktop apps with the cua-driver CLI. These are installed on…
remote-tests
Testing against remote executors in integration tests.
update-v8-version
Update Codex's pinned v8 / rustyv8 versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update rustyv8 artifacts, prepare or validate a V8 release candidate, check v8-canary, or diagnose why a V8 version update no longer builds.