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 Mathews-Tom/armory --skill concept-to-imagegit clone --depth 1 https://github.com/Mathews-Tom/armoryWrote 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/mathews-tom/armory/concept-to-image)<a href="https://agentmods.dev/skills/mathews-tom/armory/concept-to-image"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/concept-to-image.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Prompt Injection · line 129 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium MCP Rug Pull · line 131 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00066 | $0.02209 |
| Opus 5 | $0.00033 | $0.01104 |
| Sonnet 5 | $0.00013 | $0.00442 |
| Haiku 4.5 | $0.00007 | $0.00221 |
Grade A, and why
concept-to-image 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 9d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concept to Image
Creates polished visuals from concepts using HTML/CSS/SVG as a refineable intermediate, then exports to PNG or SVG.
Reference Files
| File | Purpose |
|---|---|
references/design-guide.md |
Design patterns, anti-patterns, color palettes, typography choices, layout examples |
scripts/render_to_image.py |
Playwright-based export script — takes HTML in, PNG or SVG out |
assets/template.html |
Base HTML template with .canvas container and CSS custom properties pre-configured |
Why HTML as intermediate
HTML is the refineable layer between idea and image. Unlike direct canvas rendering, the user can see the HTML artifact, request changes ("make the title bigger", "swap the colors", "add a third column"), and only export once satisfied. This makes the workflow iterative and controllable.
Workflow
Concept → HTML artifact (view + refine) → PNG or SVG export
- Interpret the user's concept — determine what kind of visual best fits (diagram, infographic, card, chart, etc.)
- Design a self-contained HTML file using inline CSS and inline SVG — zero external dependencies
- Present the HTML as an artifact so the user can preview and request refinements
- Iterate on the HTML based on user feedback (colors, layout, content, sizing)
- Export to PNG and/or SVG when the user is satisfied, using
scripts/render_to_image.py
Step 1: Interpret the concept
Determine the best visual format:
| User intent | Visual format | Approach |
|---|---|---|
| Explain a process/flow | Flowchart or pipeline diagram | SVG paths + boxes |
| Compare items | Side-by-side or matrix | CSS Grid |
| Show hierarchy | Tree or layered diagram | Nested containers + SVG connectors |
| Present data | Chart or infographic | SVG shapes + data labels |
| Social/marketing graphic | Card or poster | Typography-forward HTML/CSS |
| Icon, logo, badge | Compact symbol | Pure SVG |
| Educational concept | Annotated diagram | SVG + positioned labels |
What ships with it
4 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.
- 9d ago First seen · 182 lines · 66 tokens per session scan A 26e6463e343a
concept-to-image is a skill published in the GitHub repository Mathews-Tom/armory (316 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 2,209 once invoked, about $0.0003 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
art-director
Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
open-design-landing-deck
OpenDesign's brand-story deck for partners and press: why it exists, what it believes, and where design is going. Built as a decision-grade marketing & GTM deck for partners, press, community.
hps-retro-tv
A family history told through five decades of home movies — the opening question, the eras, and what the footage reveals. Built as a decision-grade story deck for family, close friends.
ve-terminal-mono
OpenDesign from the CLI: driving the full design workflow with the od command — scripted, composable, agent-ready. Built as a decision-grade AI literacy deck for developers, power users.
html-ppt-zhangzara-blue-professional
OpenDesign's QBR for the executive committee: what moved, what stalled, and the resource reallocation ask. Built as a decision-grade corporate strategy deck for executive committee.
html-ppt-zhangzara-neo-grid-bold
A designer's portfolio narrative for a senior interview — three case studies, the craft, and the judgment behind each. Built as a decision-grade career deck for hiring panel.