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 gitguffaw/codex-router --skill codex-cligit clone --depth 1 https://github.com/gitguffaw/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/gitguffaw/codex-router/codex-cli)<a href="https://agentmods.dev/skills/gitguffaw/codex-router/codex-cli"><img src="https://agentmods.dev/badge/skills/gitguffaw/codex-router/codex-cli/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/gitguffaw/codex-router/codex-cli"><img src="https://agentmods.dev/badge/skills/gitguffaw/codex-router/codex-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00089 | $0.02192 |
| Opus 5.5 | $0.00036 | $0.00877 |
| Sonnet 5.5 | $0.00018 | $0.00438 |
| Haiku 4.5 | $0.00009 | $0.00219 |
Grade A, and why
codex-cli 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex CLI
Operate Codex like a careful human CLI user. Let the installed codex binary own authentication, configuration, models, sessions, tools, plugins, and execution. Do not recreate those features in the outer harness.
Prefer Codex Router When Present
If the codex-router plugin is installed in this session, or the user asks for /codex-router:*, Router-managed jobs, /codex-router:status, /codex-router:result, /codex-router:cancel, context packs, rescue, or orphan recovery, stop using this skill and follow codex-router instead. This skill is only for explicit raw-CLI work.
Boundary
- Outer harness and inner Codex are separate agents and tool layers.
- Satisfy requests for Codex search, MCP, plugins, skills, browser, tools, or subagents inside Codex.
- Do not silently replace failed Codex work with outer-agent work.
- Do not claim durable background tracking, orphan recovery, or cross-session cancellation. This skill invokes native processes only.
- Preserve user changes and inspect the resulting diff before reporting success.
Preflight
Probe only what the request needs:
codex --version
codex <command> --help
codex debug models
codex features list
codex mcp list
codex plugin list
If codex is unavailable, stop and report that fact. If authentication or configuration fails, run codex doctor and return its remediation; do not invent an alternate login flow.
Treat CLI help and the live model catalog as authoritative over this skill. Flag locations and available commands change over time.
Resolve Models and Effort
Do not hardcode aliases. Read codex debug models, whose current output contains .models[] records with slugs, display names, visibility, supported reasoning levels, and speed tiers.
When the user names a model or shorthand such as sol, terra, luna, or spark:
- Match it case-insensitively against the live slug and display name.
- Require one visible match.
- Verify the requested reasoning effort appears in
supported_reasoning_levels[].effort. - Verify requested speed tiers appear in the model's advertised tiers.
- Fail explicitly if a requirement is unavailable; do not silently downgrade.
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 First seen · 195 lines · 89 tokens per session scan A c12b0ccc5ffa
codex-cli is a skill published in the GitHub repository gitguffaw/codex-router (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 89 tokens to every session and 2,192 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 2026-08-31.
Other skills, from other repositories
codex-review
Use when the user asks to "review code with codex", "run a codex review", "review my changes", "review this commit", "review my branch", or wants OpenAI Codex to review code changes. Provides automated code review using the Codex CLI.
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
genshijin-review
A compact pull-request review format that writes one actionable finding per line in Japanese or English.
triage
Triages a PR comment — from a bot (Copilot, CI) or a human reviewer. Routes to the triagehelper.py helper for identity checks, thread snapshotting, isolated-worktree fixes, and publish/reply/resolve mechanics; you classify the finding and apply a justified fix. --dry-run is fully read-only (investigation and a printed…
pr-review
Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for…