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 Pexafy/pexafy-mcp --skill find-stock-photosgit clone --depth 1 https://github.com/Pexafy/pexafy-mcpWrote 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/pexafy/pexafy-mcp/find-stock-photos)<a href="https://agentmods.dev/skills/pexafy/pexafy-mcp/find-stock-photos"><img src="https://agentmods.dev/badge/skills/pexafy/pexafy-mcp/find-stock-photos/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/pexafy/pexafy-mcp/find-stock-photos"><img src="https://agentmods.dev/badge/skills/pexafy/pexafy-mcp/find-stock-photos.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 | $0.00225 | $0.01014 |
| Opus 5.5 | $0.00090 | $0.00406 |
| Sonnet 5.5 | $0.00045 | $0.00203 |
| Haiku 4.5 | $0.00022 | $0.00101 |
Grade A, and why
find-stock-photos 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find stock photos with Pexafy
The user's explicit instructions come first: if they say they do not want photographs, or ask for an illustration, a drawing or an image to be created, do not use this skill.
Pexafy searches its own index of millions of free-to-use photographs, collected from stock libraries such as Unsplash, Pexels and Pixabay; every result names its licence. Matching is semantic: one sentence can describe the whole scene.
Which tool
- A scene described in words →
search_photos, with that scene as one English sentence inenglish_search_sentence. Translate when the user wrote in another language; English retrieves best. - A picture the user already has →
search_photos_by_imagewith the image as the reference: its public link inimage_url, or, when the user uploaded it and the host passes uploads to tools, the upload itself inimage_file. Addenglish_search_sentencewhen the user wants something changed or kept from it ("like this but at night"); the picture stays the main signal. A picture with no link that the host does not pass to tools — a local file, or on some hosts a picture pasted into the conversation — is searched in words instead: describe the scene it shows in one English sentence and search withsearch_photos. - More photographs like a Pexafy one already found or liked →
search_photos_by_imagewith itsphoto_idas the reference. Addenglish_search_sentencewhen you have the words that photograph was found under; staying on the subject is the safer default. Omit it only when they plainly want photographs that look like it. - The photographs the user liked in the Pexafy grid →
get_grid_selected_photos, rather than reading the selection off earlier results. - A photograph to insert in a document, attach or download, or to edit with the host's own tools →
get_photo_file_by_photo_idwith itsphoto_id: a URL is a link, the file is the picture.
The shape of the photo
Set explicit_orientation_filter only when the user asked for a shape in their own words, or named a format whose shape is part of its definition — a vertical Short, a banner, a square post, a phone wallpaper. Never infer it from the subject, the composition, or a purpose that fixes no shape. It is a hard filter: a shape nobody asked for drops better matches than it adds.
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 · 36 lines · 225 tokens per session scan A 29bf00fe4049
find-stock-photos is a skill published in the GitHub repository Pexafy/pexafy-mcp (0 stars, last pushed today), licensed MIT. It adds 225 tokens to every session and 1,014 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-10-04.
Other skills, from other repositories
design
Design and critique any visible UI, before and after building. Trigger on UI work: "improve the UI", "redesign", "polish", "make it look better", "visual upgrade", "design review", "design audit", "layout fix", "UX improvement", or any task whose deliverable is a page, screen, or component that renders. Shapes a…
zenith
Author and modify editable .zen designs with the Zenith CLI. Use for posters, slides, diagrams, charts, brand kits, size variants, and CSV mail-merge. Export PNG, self-contained SVG with outlined text, or PDF with explicit raster fallback reports. Use other tools for photo generation, raster editing, and unrelated…
html-design-revision
Revise an existing HTML/CSS design file with small, safe edits. Use when asked to change a color, text, size, position or add an element to a design that already exists. Use other tools for building a design from scratch.
html-author
Build a finished one-page or multi-page design (flyer, letterhead, handout, deck, poster, menu, card, report, invoice) as a single HTML/CSS file at a fixed pixel size. Use when asked to design something from a brief, starting from nothing. Use other tools to edit an existing file.
figma-edit
Use when reading or editing a Figma file through the figma-edit-mcp server — inspecting nodes; creating or modifying shapes, frames, text, styles, variables, components, instances, annotations, or prototype reactions; and recovering from the server's structured errors. Explains the plugin's hard constraints (scope…
site-header
Design and build the site-wide header (logo, menu, language switcher, cart, call to action) yourself, then have the site save it in the right places and check it. Activate whenever the user asks to create, fix, redesign, modernise, tidy or "make professional" a header or top navigation, or complains that the menu…