Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add smk-labs/claude-plugins/plugin install getpixWrote 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/smk-labs/claude-plugins/getpix)<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/getpix"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/getpix/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/smk-labs/claude-plugins/getpix"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/getpix.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 | $0.00072 | $0.01353 |
| Opus 5.5 | $0.00029 | $0.00541 |
| Sonnet 5.5 | $0.00014 | $0.00271 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
getpix 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 29d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
getpix
Find a good free image, then either show it in the chat or install it into a project. Everything goes through one script; never call the image APIs yourself and never dump raw API JSON into context.
Script: ${CLAUDE_PLUGIN_ROOT}/scripts/getpix.sh
Show in chat (no project file involved)
When the user just wants to see an image, or a photo would make an answer clearer:
search "english words" -n 5thumb Nfor the most promising result; it prints a local file path.- Read that file: it renders inline in the conversation for the user. If it is clearly wrong, try one other candidate, then stop.
- Under it, give a one-line source note: title, creator, source, license (all already in the search output). No
get, no optimization needed.
Cost: one search plus 1 to 2 thumbnails. Do this proactively when it genuinely helps, not on every reply.
Insert into a project (site, blog, docs)
- Query in English, 2 to 4 concrete words. Stock APIs are English-centric: translate the user's request first ("قهوه و لپتاپ" becomes
laptop coffee desk). Prefer subject + setting over abstract words. - Search:
Output is a compact numbered list: source, dimensions, license, title, creator. Sources without keys are skipped automatically; Openverse and Wikimedia always work keyless.bash "${CLAUDE_PLUGIN_ROOT}/scripts/getpix.sh" search "laptop coffee desk" -n 5 -o landscape - Pick.
- Fast mode (default): choose from the metadata alone: dimensions fit the slot, license is easy, title/alt matches the topic. Spend zero images.
- Picky mode (user asked for "best", "beautiful", a hero image, or the pick really matters): preview at most 2 to 3 candidates:
Read each printed file, judge subject, composition, and whether colors fit the site, then pick.bash "${CLAUDE_PLUGIN_ROOT}/scripts/getpix.sh" thumb 3 # prints a local file path
- Fetch and optimize (only the chosen one; never download originals of the losers):
The script downloads a reasonably sized variant, converts to WebP (magick, else cwebp, else JPEG via sips), and never upscales. Widths: content 1200 to 1600, hero 1920, card/thumb 640. Wikimedia files arrive at the next standard Commons width at or abovebash "${CLAUDE_PLUGIN_ROOT}/scripts/getpix.sh" get 3 -d ./public/images -w 1600 --name coffee-desk-hero-w(250, 330, 500, 960, 1280, 1920, 3840) and are resized down locally. - Insert. Use the printed path. Write a descriptive
alt(the printed alt suggestion is a starting point), addloading="lazy"below the fold, and set width/height if the framework wants them. - Attribution. The
getoutput says exactly what each source needs. Pexels and Pixabay: none required. Unsplash: required, add the credit line near the image or in the page footer. Openverse and Wikimedia: follow the printed license line. Never skip a printed "REQUIRED" attribution.
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.
- 29d ago Changed f4042b3aefbe
- 1mo ago Changed · +3 lines · +72 tokens per session afaaa745b2fd
- 1mo ago First seen · 79 lines · 0 tokens per session scan A eee6a82e50bf
getpix is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 28d ago), licensed MIT. It adds 72 tokens to every session and 1,353 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
pmm-resume
Reviews and tailors a PMM resume (IC to VP, including AI PMM roles): dissects the job description, ranks bullets by impact fit and rebuilds the complete resume in one pass. Trigger on: resume + JD paste, "tailor this", "which bullets for this role", "rebuild for [company]", "review my PMM resume", "reframe for…
product-marketing-context
Builds and maintains the shared GTM brain (product context, ICP, positioning, voice, market context, proof points, plus optional strategy and execution sections and the deal-reality fields) that every other skill reads before producing output. Works standalone from your own answers, and gets stronger when you connect…
competitor-deep-dive
Builds a long-form, fully sourced deep-dive on one competitor for a named decision (strategy call, RFP, pricing change, roadmap bet), with dated reviews, deal evidence, a head-to-head per offering and where they win. Triggers: "deep-dive on [competitor]", "full competitor write-up", "what do users really say about…
workflow-orchestrator
Chains positioning, competitive, GTM strategy, campaign briefs, stakeholder maps and retros into one coherent PMM program with a master document and brain updates. Trigger on: "run full GTM workflow", "run a full launch", "launch [product] end to end", "positioning refresh", "quarterly PMM cycle", "competitive…
positioning-messaging
Builds or audits positioning statements, messaging hierarchies, homepage copy and persona cards using April Dunford's Obviously Awesome framework, in five modes (build, audit, fletch, sales-enablement, homepage). Refuses to generate without a named primary persona and 3+ alternatives including status quo, and blocks…
writing-assistant
Rewrites, sharpens and drafts B2B writing in the writer's real voice: Slack messages, emails, memos, PRDs, decks, plus marketing content (blog posts, landing pages, press releases, case studies, newsletters, social posts). Use whenever someone wants to rewrite, tighten, draft or audit copy, asks why copy isn't landing…