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 nathanonn/agent-skills --skill codex-imagegengit clone --depth 1 https://github.com/nathanonn/agent-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/nathanonn/agent-skills/codex-imagegen)<a href="https://agentmods.dev/skills/nathanonn/agent-skills/codex-imagegen"><img src="https://agentmods.dev/badge/skills/nathanonn/agent-skills/codex-imagegen.svg" alt="Measured on agentmods" 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 Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00154 | $0.01369 |
| Opus 5 | $0.00077 | $0.00685 |
| Sonnet 5 | $0.00031 | $0.00274 |
| Haiku 4.5 | $0.00015 | $0.00137 |
Grade A, and why
codex-imagegen 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 7d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Imagegen
Generate images with Codex's built-in $imagegen skill and land them in the
project, keeping ~/.codex/generated_images/ from silently growing (it
accumulates ~10MB per generation and is never cleaned by Codex itself).
Everything is driven by one bundled script that survives plugin version bumps
and works on machines without the codex plugin (it falls back to codex exec).
Prerequisites
Either of these (the script auto-detects which is present):
- Codex plugin in Claude Code —
/plugin marketplace add openai/codex-plugin-cc, then/plugin install codex@openai-codex(Full guide: https://github.com/openai/codex-plugin-cc#install). - Codex CLI (any agent) —
npm i -g @openai/codex, thencodex login.
Auth is OpenAI/ChatGPT-account backed. Without one of these the script exits with code 3 and prints these install steps.
Workflow
1. Determine the destination
- If the user named a destination folder, use it.
- Otherwise default to
.codex-image/at the project root (the script creates it). - If a file the user wants to create already exists at the destination (same intended name), ask the user before overwriting — never silently replace.
2. Compose the image prompt
Write plain prompt text — do NOT include the $imagegen token; the script
prepends it safely (a $imagegen typed into a double-quoted shell string gets
expanded to an empty string and the skill silently never triggers — the script
exists partly to make that mistake impossible).
Include in the prompt text:
- A clear description of the image (subject, style, mood, colors).
- Desired dimensions or aspect ratio. The raw model output is ~1254px square; Codex resizes/crops to what you ask, so always state it (e.g. "1200x630 landscape" for a featured image).
- The exact output filename(s), e.g. "save it as featured-image.png".
- Number of variants if the user wants more than one.
The script appends the destination directory instruction automatically.
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.
- 7d ago First seen · 111 lines · 154 tokens per session scan A 13cda842ebdc
codex-imagegen is a skill published in the GitHub repository nathanonn/agent-skills (19 stars, last pushed 19d ago), licensed MIT. It adds 154 tokens to every session and 1,369 once invoked, about $0.0008 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.