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 agentmods add skills/yan-labs/yan-skills/codexnpx skills add yan-labs/yan-skills --skill codexgit clone --depth 1 https://github.com/yan-labs/yan-skillsWrote 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/yan-labs/yan-skills/codex)<a href="https://agentmods.dev/skills/yan-labs/yan-skills/codex"><img src="https://agentmods.dev/badge/skills/yan-labs/yan-skills/codex.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.04291 |
| Opus 5 | $0.00000 | $0.02145 |
| Sonnet 5 | $0.00000 | $0.00858 |
| Haiku 4.5 | $0.00000 | $0.00429 |
Grade B, and why
codex scanned grade B with 2 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.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. **Pick reasoning effort + sandbox** from context — do not interrupt the user with `AskUserQuestion` unless they explicitly ask to be prompted. **Do not pass `-m` / `--model`**; let Codex use its default model from `~/ Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run(['sips','-Z','120', src, '--out', thumb]) How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Sub-Agent Skill
Codex runs as a background sub-agent: you launch it, immediately return control to the user, and poll or read output only when needed. This makes it usable both as a standalone background worker and as one member of a multi-agent team.
This is the most-used capability of this skill on this machine. The owner reaches for Codex primarily to generate images, so that section comes first. Everything below it — background workers, agent teams — is the same launch machinery applied to code.
Image Generation
Codex can generate images. It has a built-in OpenAI image generation tool. This is a capability of the agent, not a CLI subcommand — there is no codex image / codex gen-image command, and codex exec --image is for attaching images as input, not producing them.
Do not go looking through
codex --helpfor an image flag, conclude "Codex has no image generation," and tell the user so. That conclusion is wrong. Treat Codex as an agent: describe the images you want in the prompt and let it choose its own method.
Launch it exactly like any other Codex worker — background, prompt via stdin:
cat /tmp/codex-prompt-img.md | codex exec --skip-git-repo-check \
--config model_reasoning_effort="medium" \
--sandbox danger-full-access \
-C <outdir> 2>/dev/null
- Sandbox: needs
danger-full-access(image generation hits the network). Just run it — see Error Handling; no permission prompt is required on this machine. - Effort:
mediumis plenty; this is not a reasoning-heavy task.
Writing the image prompt
Put these in the prompt file:
- Output directory — create it yourself first (
mkdir -p) and give the absolute path. - One numbered item per image, each with its exact filename and a concrete description.
- A shared style block so a multi-image set stays visually consistent: illustration style, background, an explicit hex palette, and aspect/size.
- "No text, no logos, no watermarks" — generated lettering is almost always garbled, and in a non-English UI it will be wrong.
- An explicit escape hatch: "if you genuinely cannot generate images, say so plainly — do not substitute placeholders, ASCII art, or images downloaded from the web."
- Ask it to report the absolute path of each file plus the method it actually used.
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.
- 6d ago First seen · 237 lines · 0 tokens per session scan B 03fcfd2bd2b7
codex is a skill published in the GitHub repository yan-labs/yan-skills (172 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,291 tokens. A static security scan graded it B with 2 findings (reads agent configuration directories, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
loki-yan-seo
Use when diagnosing or executing Google SEO, international/cross-border sites, AIO, or GEO. Unofficial engine distilled from Loki Yan (@lokiyanseo) public tweets. Not a generic SEO encyclopedia. Does not imitate his voice. Not affiliated or endorsed.
youtube-comment-management
Lister, modérer et répondre aux commentaires de chaînes YouTube via l'API v3, avec maillage SEO vers vos sites WordPress.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.