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/giulioco/skills/codex-imagegennpx skills add giulioco/skills --skill codex-imagegengit clone --depth 1 https://github.com/giulioco/skillsWhat 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 | $0.00213 | $0.01552 |
| Opus 5 | $0.00106 | $0.00776 |
| Sonnet 5 | $0.00043 | $0.00310 |
| Haiku 4.5 | $0.00021 | $0.00155 |
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 2d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codex-imagegen
Generate and edit bitmap images from Claude Code by driving Codex's built-in image_gen tool through a one-shot codex exec run.
Why this works (the mechanism)
Codex ships a $imagegen skill with two modes:
- Built-in
image_gentool (this skill uses it) — runs against Codex's own backend using the user's ChatGPT/Codex login (~/.codex/auth.json). NoOPENAI_API_KEYrequired, no per-image API billing. It's the default Codex mode. - CLI fallback (
scripts/image_gen.py) — hits the OpenAI Image API directly, needsOPENAI_API_KEY. This skill does not use it.
The built-in tool is internal to Codex's agent runtime — there is no codex image subcommand. But a headless codex exec "<prompt>" run can invoke it. The wrapper script builds a tightly-scoped prompt that forces Codex to use only the built-in tool, runs codex exec, then locates the PNG Codex just wrote under $CODEX_HOME/generated_images/ and copies it into the working directory with a clean filename.
Source it wraps: ~/.codex/skills/.system/imagegen/ (Codex's installed skill).
Prerequisites
codexCLI on PATH and logged in (codex login). Verify:codex login statusor just run a generation — the wrapper reports a clear error if Codex isn't authed.- No API key needed. The wrapper explicitly tells Codex not to use the API/CLI fallback.
Usage
The wrapper lives at scripts/codex_imagegen.py (resolve its absolute path relative to this SKILL.md).
Generate
python3 scripts/codex_imagegen.py generate \
--prompt "a minimal hero image of a ceramic coffee mug, soft studio lighting, lots of negative space" \
--out ./hero.png
--outaccepts a file (./hero.png), a directory (./images/→ auto-named from the prompt), or is omitted (lands in cwd, named from a slug of the prompt).-n 3generates 3 distinct images (one built-in call each). With-n>1and a file--out, outputs are suffixed-1,-2,-3.- Existing files are never overwritten unless
--force; otherwise a-v2sibling is written.
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.
- 2d ago First seen · 93 lines · 213 tokens per session scan A c8c3b1c121fc
codex-imagegen is a skill published in the GitHub repository giulioco/skills (10 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 213 tokens to every session and 1,552 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
embedded-captions
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet…
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.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
剪辑环境的唯一管理者：就绪检查（skills 是否最新 → Runtime 是否配套）、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用；业务 Skill（剪口播/字幕/画面/导出）第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.
cap_llm_inspect_image
How to inspect a local image with inspectimage.