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 creativescope/creativescope-mcp --skill image-similarity-scangit clone --depth 1 https://github.com/creativescope/creativescope-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/creativescope/creativescope-mcp/image-similarity-scan)<a href="https://agentmods.dev/skills/creativescope/creativescope-mcp/image-similarity-scan"><img src="https://agentmods.dev/badge/skills/creativescope/creativescope-mcp/image-similarity-scan/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/creativescope/creativescope-mcp/image-similarity-scan"><img src="https://agentmods.dev/badge/skills/creativescope/creativescope-mcp/image-similarity-scan.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 | $0.00087 | $0.01297 |
| Opus 5 | $0.00044 | $0.00648 |
| Sonnet 5 | $0.00017 | $0.00259 |
| Haiku 4.5 | $0.00009 | $0.00130 |
Grade A, and why
image-similarity-scan 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reference-Image Similarity Scan
CreativeScope's image search is asynchronous: submit a job, poll its status, then fetch results. Follow this lifecycle exactly — never call the results endpoint without submitting first, and never submit twice for the same image. For general tool/filter rules, follow the creativescope-best-practices skill.
Step 0: Validate the image URL (before submitting)
submit_reference_image_search requires a directly downloadable public HTTPS
image URL. It must return raw image bytes. Before submitting, check:
- ❌ Local file paths, base64 blobs → not supported. If the user only has a local file, ask them to host it (or host it for them if you have a file tool/upload channel available) and come back with an HTTPS URL.
- ❌ Google Drive / Dropbox / WeChat / Notion "share" links → these return HTML
pages, not image bytes. Ask for a direct link (e.g. Dropbox
dl=1) or a re-host. - ❌ URLs behind login or hotlink protection.
If unsure, fetch the URL headers yourself first when you have a fetch tool:
the response must be Content-Type: image/* with HTTP 200. If you cannot
verify, submit once and let the service validate — then handle the failure
in step 2.
Step 1: Submit the job
Call submit_reference_image_search with:
image_url(required)- Optional filters the user asked for:
country(ISO code),genre,platform,format limit: default 10 (max 20)
Plan wall: The image-search tools (submit / status / results) and
find_similar_creatives are Pro-tier. On PLAN_UPGRADE_REQUIRED, say so
honestly and provide the upgrade link — do not simulate results with keyword
search and present them as image matches.
Save the returned job_id. Tell the user the search started and typically
takes under a minute — do not stay silent while polling.
Step 2: Poll status — patiently
Call get_reference_image_search_status with the job_id.
- Poll at most every 10–15 seconds, up to ~3 minutes total. Do not hammer the endpoint in a tight loop.
- If the status response includes polling guidance, follow it.
- If the job fails, read the
error_messageand act generically:- URL-related error ("fetch", "download", "URL") → go back to Step 0 and get a better URL from the user.
- Image-format-related error ("format", "size", "invalid image") → ask for a different image (standard JPG/PNG, reasonable dimensions).
- Transient/infrastructure error ("timeout", "queue", "retry") → one retry is reasonable; if it fails again, report the error and stop.
- Do not hard-code specific error-code strings — the API may change
them. Use the
error_messagetext heuristically.
- If still running after ~3 minutes, report the job is taking long, give the
user the
job_id, and offer to check again later instead of polling forever.
What ships with it
1 file 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 · 108 lines · 87 tokens per session scan A 102143fa2721
image-similarity-scan is a skill published in the GitHub repository creativescope/creativescope-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 1,297 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…