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.
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.
npx skills add duolahypercho/codex-router --skill codex-computer-usegit 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-computer-use)<a href="https://agentmods.dev/skills/duolahypercho/codex-router/codex-computer-use"><img src="https://agentmods.dev/badge/skills/duolahypercho/codex-router/codex-computer-use/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-computer-use"><img src="https://agentmods.dev/badge/skills/duolahypercho/codex-router/codex-computer-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 15 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00096 | $0.00477 |
| Opus 5.5 | $0.00038 | $0.00191 |
| Sonnet 5.5 | $0.00019 | $0.00095 |
| Haiku 4.5 | $0.00010 | $0.00048 |
Grade A, and why
codex-computer-use 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 12d 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.
What it actually says
Codex Computer Use
Prefer purpose-built connectors, APIs, or CLIs when they can perform the task. For UI work, inspect the actual tool list before choosing a runtime:
- If
mcp__cua_repl__jsis exposed, use the current runtime below. - Otherwise, if
mcp__node_repl__jsis exposed, read the legacy runtime instructions. - If neither is exposed, report the missing capability. Do not start a REPL process, write a side-channel driver, or synthesize MCP calls.
Current runtime: cua_repl
Read the live tool instructions. The tool initializes cua; do not import
@oai/sky or bootstrap agent.browsers in this runtime.
On the first invocation, or after a reset, execute exactly one documented
entry-point API call, optionally assigning its result. Do not combine it with
another API call, a wait, a snapshot, or output helpers. Use the entry point
matching the user's requested surface; use await cua.getState() only when
an inventory is needed. Read the returned documentation and state before
continuing. For browser work, also read codex-in-app-browser.
Use only APIs described in the tool instructions or returned documentation. Check which surfaces are enabled: browser access does not imply native app control. If native APIs are disabled, report that limitation for a native app task. Never guess screen contents or claim an unavailable surface is enabled.
Reuse the existing bindings. After compaction into a summary of an ongoing
computer-use task, call await cua.rewriteDocumentation() before continuing.
Follow the live tool's reset and output rules; the legacy runtime's imports
and one-line input rules do not apply here.
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.
- 12d ago Changed · -12 lines · -14 tokens per session e023c6bb71a0
- 1mo ago First seen · 50 lines · 110 tokens per session scan A a4ad542b2970
codex-computer-use is a skill published in the GitHub repository duolahypercho/codex-router (3,955 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 477 once invoked, about $0.0004 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.