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 mgiovani/cc-arsenal --skill project-illustratorgit clone --depth 1 https://github.com/mgiovani/cc-arsenalWrote 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/mgiovani/cc-arsenal/project-illustrator)<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/project-illustrator"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/project-illustrator/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/mgiovani/cc-arsenal/project-illustrator"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/project-illustrator.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 | $0.00062 | $0.01622 |
| Opus 5.5 | $0.00025 | $0.00649 |
| Sonnet 5.5 | $0.00012 | $0.00324 |
| Haiku 4.5 | $0.00006 | $0.00162 |
Grade C, and why
project-illustrator scanned grade C 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 22d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
Derive the fixed-size crops with the script rather than by hand. It needs [uv](https://docs.astral.sh/uv/) (`curl -LsSf https://astral.sh/uv/install.sh | sh`) and installs Pillow itself: Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Derive the fixed-size crops with the script rather than by hand. It needs [uv](https://docs.astral.sh/uv/) (`curl -LsSf https://astral.sh/uv/install.sh | sh`) and installs Pillow itself: How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Illustrator
Build a project art system that stays recognizable at every size. A tiny avatar has to read as clearly as a wide README hero, and so does whatever illustration follows later. Base every decision on the product and its existing identity rather than on generic technology imagery.
1. Discover the identity
Inspect the target repository before writing a prompt:
- Read the README and product copy to learn the problem, mechanism, audience, and tone.
- Search
assets/,public/,static/, documentation, social cards, favicons, and app icons for existing brand material. - Inspect the actual candidates. Do not treat a framework or template icon as project branding.
- Record the current output paths, dimensions, formats, and every place the artwork is referenced.
If the project already has a logo or mascot, preserve its defining silhouette, anatomy, colors, and personality. Improve execution and consistency without replacing its identity.
If it has no identity, turn the product's mechanism into a character or visual action. Prefer a specific idea that explains the project over a mascot holding unrelated developer props.
Read references/art-direction.md for the default visual language, asset specifications, and review checklist.
2. Establish one canonical mascot
When no mascot has been approved, generate three clearly different high-resolution concepts. Vary the central metaphor, silhouette, or staging while keeping the same art direction. Do not produce superficial color swaps.
Keep each concept:
- square and at least 1024px;
- readable inside a circular crop;
- centered with generous breathing room;
- limited to one clear action or idea;
- free of labels, slogans, mock UI, and decorative clutter.
Show the three options together at a useful review size and name them plainly: Option 1, Option 2, and Option 3. Pause for the user's selection before creating dependent heroes or illustration sets. The selection is a creative dependency, not a permission gate.
What ships with it
12 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.
- evals/evals.json 2.2 KB
- evals/trigger-eval.json 1.2 KB
- references/art-direction.md 5.7 KB
- references/visuals/ai-arsenal-hero.webp 56 KB
- references/visuals/ai-arsenal-mascot.webp 88 KB
- references/visuals/cc-wellness-hero.webp 80 KB
- references/visuals/cc-wellness-mascot.webp 92 KB
- references/visuals/stopslop-hero.webp 61 KB
- references/visuals/stopslop-mascot.webp 69 KB
- references/visuals/water-gate-hero.webp 62 KB
- references/visuals/water-gate-mascot.webp 72 KB
- scripts/derive_assets.py 3.2 KB runs code
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.
- 22d ago Changed · +19 lines scan A → C f36c79ff4349
- 1mo ago Changed 4d205c1bd687
- 1mo ago Changed 1f02429d6d88
- 1mo ago Changed · +1 lines b5fb72c90af5
- 1mo ago First seen · 100 lines · 62 tokens per session scan A 8e02ad9dbb9b
project-illustrator is a skill published in the GitHub repository mgiovani/cc-arsenal (8 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 1,622 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.
Other skills, from other repositories
frontend
Builds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack. Use for any styling, layout, animation, or visual-quality task, or when asked to make something look or feel a certain…
cli-anything-photoshop
A command-line tool that controls Adobe Photoshop through Windows automation. It can work with Photoshop documents, layers, selections, text, image adjustments, and exports.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
app-screenshot-debug
Drive the running termio app via AppleScript / System Events to reach a UI state (focus the window, click a sidebar project, a terminal pane, a control), capture a pixel-accurate screenshot of just that window, and read it back for visual analysis — for diagnosing layout / spacing / alignment / 'this looks ugly'…
user-research-cookiy
End-to-end user research assistant — qualitative and quantitative. Use this skill whenever the user mentions user research, user interviews, discussion guides, interview guides, research plans, qualitative research, quantitative research, user surveys, survey design, usability studies, participant recruitment…
write-zot-themes
Help the user create, install, or package zot themes, including theme-only extensions.