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/.agents/skills/repo-maintainer/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/repo-maintainer)<a href="https://agentmods.dev/skills/duolahypercho/codex-router/repo-maintainer"><img src="https://agentmods.dev/badge/skills/duolahypercho/codex-router/repo-maintainer/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/repo-maintainer"><img src="https://agentmods.dev/badge/skills/duolahypercho/codex-router/repo-maintainer.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 | $0.00077 | $0.01316 |
| Opus 5 | $0.00039 | $0.00658 |
| Sonnet 5 | $0.00015 | $0.00263 |
| Haiku 4.5 | $0.00008 | $0.00132 |
Grade A, and why
repo-maintainer 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 13d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Maintainer
Make cross-repository consequences visible before accepting, implementing, or declaring a change complete. Scale review and verification to semantic risk, not diff size alone.
Select the operation
- Assess an incoming change: inspect it read-only and recommend
adopt,adapt,defer, orreject. Do not pull, merge, cherry-pick, or edit merely because assessment was requested. - Implement maintenance: map impact, make the smallest complete change, and verify the resulting diff.
- Audit existing work: review every changed hunk, find omissions and regressions, and report findings before editing unless the user also asked for fixes.
- Prepare a release: inspect the complete release delta and read references/verification.md plus any repository release instructions.
Read repository instructions before acting. In this repository, also read references/codex-router-surfaces.md when a change touches routing, providers, clients, installers, credentials, the gateway, model publication, desktop surfaces, or releases.
Establish the evidence baseline
-
Preserve unrelated work. Inspect status, current branch or detached state, relevant instructions, and the requested comparison boundary.
-
Run the analyzer from the repository root. The command below is read-only; adding
--manifest PATHatomically creates or replaces that named JSON artifact:python3 <skill-dir>/scripts/repo_maintainer.py analyze --repo . --format markdownFor an existing commit range, pass
--base REF --head REF. For only staged changes, pass--staged. Treat its classifications as conservative signals, not proof of semantic impact. -
State observable acceptance outcomes before implementation. Keep them in the working plan unless the task genuinely needs a durable artifact. Each outcome is
pending,verified,blocked, ornot-applicablewith a reason. -
Identify affected and explicitly unaffected surfaces. Search callers, consumers, mirrored implementations, platform variants, configuration writers/readers, tests, documentation, generated artifacts, and release metadata.
What ships with it
7 files 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.
- 13d ago First seen · 85 lines · 77 tokens per session scan A 232170c2d8c6
repo-maintainer is a skill published in the GitHub repository duolahypercho/codex-router (3,250 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,316 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.
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…
review-agent
Perform a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit, or custom review instructions.
code-review
Run a final code review on a pull request.
code-review-change-size
Change size guidance (800 lines).
code-breaking-changes
Search for breaking changes in external integration surfaces.
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…