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 lossless-group/lossless-agent-skills --skill overlay-svg-textgit clone --depth 1 https://github.com/lossless-group/lossless-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/lossless-group/lossless-agent-skills/overlay-svg-text)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/overlay-svg-text"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/overlay-svg-text/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/lossless-group/lossless-agent-skills/overlay-svg-text"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/overlay-svg-text.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 | $0.00262 | $0.04608 |
| Opus 5 | $0.00131 | $0.02304 |
| Sonnet 5 | $0.00052 | $0.00922 |
| Haiku 4.5 | $0.00026 | $0.00461 |
Grade A, and why
overlay-svg-text 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 12d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overlay SVG Text on Brand Imagery
Two layers of brand identity on every share image. The base image — generated via
generate-consistent-og-images— already follows the empty-region-first composition rule, leaving the top 1/3 of the frame deliberately clean. This skill paints that clean zone with three text elements: a thin sans eyebrow, a Hack-Bold gradient-filled h1, and a Poor Story handwritten note. Everything else (layout, colors, font weights) is locked at the project'sDESIGN.mdlevel.
When to use this skill
- An OG image was just generated and needs a wordmark / title overlay before it ships
- An existing OG image looks too anonymous in unfurls — needs a brand-flavored title or subtitle
- A fundraise-deck slide / hero illustration needs a brand-consistent title overlay
- A user-facing share preview is launching and needs the project's name + a one-liner baked in
- The user says: "overlay text on this", "add a title to the banner", "make the unfurl say something", "drop a wordmark on this", "compose the OG with text"
The Lossless brand type system for overlays
Three text elements, in canonical vertical order from top of frame to bottom of overlay zone:
| Element | Font | Weight | Color | Notes |
|---|---|---|---|---|
| Eyebrow | Project's display sans (or Inter as fallback) | Thin (200) or Light (300) | white at 70–80% alpha, OR --color-text-soft |
Often uppercase with wide tracking (0.18em–0.24em); the project's typography.eyebrow token wins if present |
| H1 (gradient) | Hack Bold (Hack Nerd Font Mono Bold is what most Lossless dev machines have installed) | Bold (700) | gradient-filled from the project's imagery.gradient or components.gradient-text.background in DESIGN.md |
Monospaced + gradient is the brand's "data" aesthetic — short noun-phrase or shell-command-style; never sentence-case prose |
| Note (handwritten) | Poor Story (Google Fonts, Korean handwriting family) — preferred. Any cartoonish handwriting font is acceptable as fallback (e.g. Caveat, Patrick Hand, Indie Flower) | Regular | white (#ffffff) — almost always |
The handwriting/Hack contrast is the brand move; never serif, never another mono |
What ships with it
2 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.
- 12d ago First seen · 281 lines · 262 tokens per session scan A 86364b533cbf
overlay-svg-text is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 19d ago), licensed MIT. It adds 262 tokens to every session and 4,608 once invoked, about $0.0013 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
infographics
Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.
svg-primitives
Use when the user asks to build a programmatic SVG schematic in Python: flowcharts, boxes and arrows, auto-fit SVG text, mm-precise diagrams, edge-snapped arrows, tangent-correct curve arrowheads, orthogonal or Manhattan routing, deterministic z-order layers, labeled groups, bracket groupings, leader-line annotations…
transparent-icons
This skill should be used when the user asks to "make an icon", "generate an icon", "create a scientific icon", "make a transparent icon", "make a minimal icon", "icon for a figure", "icon for a paper", "generate an icon set", "batch icons", "icon batch", "batch generate icons", or wants flat scientific icons (brain…
excalidraw-visual-designer
Create and revise editable visual drawings directly in the Excalidraw website through the in-app browser. Use when the user asks Codex to draw in Excalidraw or update an Excalidraw canvas, including diagrams, flowcharts, architecture sketches, process maps, infographics, teaching visuals, product explanation graphics…
wechat-sticker-assets-designer
A design skill for creating the supporting images used when publishing WeChat sticker packs, including a banner, a support-request image, and a thank-you image.
design-trends-2026
Apply 2026's top graphic design trends to any creative brief. Based on Kittl × Savee's 2026 Design Trends Report (10 trends + 2 honorable mentions), backed by Adobe, Figma, and Pinterest data. Use when: Designing a brand identity — pick the right aesthetic for your audience; Creating social media assets — use trending…