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 krusemediallc/cursor-ad-agent --skill claymation-ad-arcads-mcpgit clone --depth 1 https://github.com/krusemediallc/cursor-ad-agentWrote 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/krusemediallc/cursor-ad-agent/claymation-ad-arcads-mcp)<a href="https://agentmods.dev/skills/krusemediallc/cursor-ad-agent/claymation-ad-arcads-mcp"><img src="https://agentmods.dev/badge/skills/krusemediallc/cursor-ad-agent/claymation-ad-arcads-mcp/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/krusemediallc/cursor-ad-agent/claymation-ad-arcads-mcp"><img src="https://agentmods.dev/badge/skills/krusemediallc/cursor-ad-agent/claymation-ad-arcads-mcp.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 | $0.00103 | $0.05029 |
| Opus 5 | $0.00051 | $0.02514 |
| Sonnet 5 | $0.00021 | $0.01006 |
| Haiku 4.5 | $0.00010 | $0.00503 |
Grade A, and why
claymation-ad-arcads-mcp scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. `PUT` the bytes: `curl -s -o /dev/null -w "%{http_code}\n" -X PUT -H "Content-Type: image/png" --upload-file "<file>" "<presignedUrl>"` → expect `200`. How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claymation Ad — Arcads MCP
Build a narrative claymation (Aardman/Laika stop-motion) product ad fully on the
Arcads MCP server. Same proven creative pipeline as the REST claymation-ad guide —
gpt-image-2 storyboard → Seedance 2.0 image-to-video → narrator VO → stitch →
captions — but every API step is an Arcads MCP tool call. The MCP handles auth and
job orchestration, so there's no hand-rolled HTTP Basic header or POST /v2/... plumbing.
⚠️ Remote-client caveat (read first). The MCP server cannot read local disk unless the client provides explicit filesystem bridging. In Cursor, every reference file (a user product photo, a generated still you chain into the next call, a clip you feed into v2v/stitch) must be uploaded via
arcads_get_upload_url+ an HTTPPUTfirst, then referenced by the returned S3filePath. TempfilePaths are single-use. And keep a.envwithARCADS_BASIC_AUTHfor the polling fallback. See Uploading & fetching.
REST claymation-ad step |
MCP replacement |
|---|---|
POST /v2/images/generate (gpt-image-2) + presigned upload of each reference |
arcads_generate_image_gpt (model gpt-image-2); references via arcads_get_upload_url + PUT → S3 filePath (see Uploading) |
POST /v2/videos/generate (seedance-2.0) with startFrame URL |
arcads_generate_video_seedance_20 with referenceImages:[still] (i2v) |
| ElevenLabs TTS per beat | arcads_text_to_speech (one voiceId across all beats) — or keep ElevenLabs if the user insists |
GET /v1/assets/{id} polling (+ the "Seedance polls /assets not /videos" gotcha) |
arcads_watch_asset (status + download URL) — gotcha gone |
ffmpeg -f concat stitch |
arcads_stitch_videos (2–6 clips/call) — or ffmpeg |
.ass / HyperFrames caption burn |
arcads_add_subtitles (style catalogue) — or HyperFrames for exact brand styling |
Manual Authorization: $ARCADS_BASIC_AUTH header on every call |
MCP injects auth — you only need .env for the polling fallback |
What does not change vs REST: reference files are still uploaded per call and
temp filePaths are still single-use (see Uploading below). What the MCP does remove:
hand-rolled auth headers, the "Seedance polls /v1/assets not /v1/videos" gotcha
(arcads_watch_asset abstracts it), and N-parallel-POSTs for variations (nbGenerations).
The only non-MCP step: muxing the VO mp3 onto each silent clip + tight-trimming
to kill dead space (the "VO drives clip duration" rule). No single Arcads MCP tool
muxes a standalone audio track onto a video, so that one step uses local ffmpeg.
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 · 223 lines · 103 tokens per session scan A 006f87350679
claymation-ad-arcads-mcp is a skill published in the GitHub repository krusemediallc/cursor-ad-agent (10 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 5,029 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
RunAPI Media Generator
A workflow for creating images, videos, music, and audio through RunAPI, a service that provides access to media-generation models. It checks the chosen model and request before submitting the job.
RunAPI Model Explorer
A RunAPI catalogue assistant that lists available AI models, explains their required inputs, and provides current pricing information.
imaginode
Generate AI images and videos through the Imaginode MCP server (imaginode.ai). Use when the user asks to create, generate or illustrate an image, picture, visual, thumbnail, or a short video clip, and the Imaginode MCP tools (generateimage, generatevideo, listmodels, getgenerationstatus) are available.
uni1-image-ad
Use when the user wants to generate a Meta/Facebook image ad with Luma uni-1 and attach it to an existing Meta ad set. Triggers on phrases like "uni-1 ad", "make a Luma ad creative", "new image ad in ", "uni-1 image ad for Meta", "generate uni-1 ad creative", "upload uni-1 image as Meta ad". Anchors on uni-1 + Meta…
image-ad-clone
Use when the user wants to reverse-engineer an existing image ad into a reusable, parameterizable prompt template that can be reused with any brand and any product. Triggers on phrases like "clone this ad as a template", "reverse engineer this ad", "turn this ad into a prompt", "extract a template from this image"…
distribea-media
Generate or place on-brand media (images, video, music, voice) with Distribea. Use whenever a project needs imagery or audio — a hero/illustration/avatar, a page full of placeholders, a video clip, background music, or a voice-over — instead of shipping stock photos, placeholders, CSS-gradient-only sections, or raw…