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 ZSeven-W/craft-skills --skill native-transparent-imagegengit clone --depth 1 https://github.com/ZSeven-W/craft-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/zseven-w/craft-skills/native-transparent-imagegen)<a href="https://agentmods.dev/skills/zseven-w/craft-skills/native-transparent-imagegen"><img src="https://agentmods.dev/badge/skills/zseven-w/craft-skills/native-transparent-imagegen/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/zseven-w/craft-skills/native-transparent-imagegen"><img src="https://agentmods.dev/badge/skills/zseven-w/craft-skills/native-transparent-imagegen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high System Prompt Leakage · line 73 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00085 | $0.00919 |
| Opus 5 | $0.00043 | $0.00460 |
| Sonnet 5 | $0.00017 | $0.00184 |
| Haiku 4.5 | $0.00009 | $0.00092 |
Grade A, and why
native-transparent-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 11d 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.
Native Transparent ImageGen
Generate the asset with native alpha. Treat a visible checkerboard, a prompt that says "transparent," and a successful tool call as unverified until the original file passes alpha inspection.
Keep the boundary strict
- Use this skill only for a newly generated asset whose deliverable must contain native transparency.
- Treat supplied images as identity, subject, composition, or medium references unless the user explicitly requests an edit.
- Do not invoke background removal, segmentation, chroma-key extraction, masks, or local alpha synthesis to rescue an opaque output.
- Do not call a rendered checkerboard "transparent." An RGB checkerboard is a failed asset.
- If the user instead wants a background removed from an existing opaque image, route to a background-extraction workflow and disclose that it is an edit, not native generation.
Generate conservatively
- Preserve the user's subject, identity, style, composition, and text constraints.
- Add one concise output requirement: return a PNG or WebP whose area outside the subject is genuine pixel transparency with a real alpha channel.
- With a prompt-only built-in image tool, issue native-alpha deliverables one at a time. Do not parallelize unless the current tool exposes an explicit per-request background control and concurrent native-alpha behavior has been verified.
- When the user explicitly chooses an API path that exposes output controls, request
background: "transparent"andoutput_format: "png"or"webp". - Preserve the original returned bytes. Validation must not rewrite, optimize, composite, resize, or otherwise alter the deliverable.
Read references/prompting-and-retry.md when preparing a prompt, retrying a failed output, generating more than one asset, or reporting limitations.
Validate the untouched file
Install the validator dependency only when it is missing:
python3 -m pip install -r \
"${CODEX_HOME:-$HOME/.codex}/skills/native-transparent-imagegen/scripts/requirements.txt"
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.
- 11d ago First seen · 93 lines · 85 tokens per session scan A 4266225c640e
native-transparent-imagegen is a skill published in the GitHub repository ZSeven-W/craft-skills (149 stars, last pushed 6d ago), licensed Apache-2.0. It adds 85 tokens to every session and 919 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
html-ppt-zhangzara-retro-zine
A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.
html-ppt-zhangzara-studio
A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
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.
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…