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 Boring-Stuff-Club/the-scribble-thing-skill --skill the-scribble-thinggit clone --depth 1 https://github.com/Boring-Stuff-Club/the-scribble-thing-skillWrote 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/boring-stuff-club/the-scribble-thing-skill/the-scribble-thing)<a href="https://agentmods.dev/skills/boring-stuff-club/the-scribble-thing-skill/the-scribble-thing"><img src="https://agentmods.dev/badge/skills/boring-stuff-club/the-scribble-thing-skill/the-scribble-thing/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/boring-stuff-club/the-scribble-thing-skill/the-scribble-thing"><img src="https://agentmods.dev/badge/skills/boring-stuff-club/the-scribble-thing-skill/the-scribble-thing.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 | $0.00058 | $0.00604 |
| Opus 5 | $0.00029 | $0.00302 |
| Sonnet 5 | $0.00012 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
the-scribble-thing 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Scribble Thing
Use the connected The Scribble Thing MCP server when it is available. Its public
endpoint is https://scribble.boringstuff.club/mcp and the REST fallback guide
is https://scribble.boringstuff.club/docs/agent-api.
Before creating
- Require one PNG or JPEG image. Line art and simple illustrations work best.
- Ask only for missing choices: drawing order is optional, hand display defaults to off, and speed defaults to normal.
- Call
get_scribble_service_infofor current limits, retention, terms, and pricing. Do not rely on values remembered from an earlier run. - Before the first creation, tell the user that uploaded and generated files are retained for up to the reported retention period. Obtain explicit confirmation that the user accepts the current terms and has the rights needed to use the artwork. Do not infer acceptance.
Create and monitor
- Call
create_scribe_animationwith the image as raw base64, not a data URL. Supply a fresh non-personal idempotency key. Reuse that key only when retrying the identical request. - Preserve the returned animation ID and capability token as secrets. Never put them in ordinary chat text, logs, analytics, filenames, or unrelated tools.
- Poll
get_scribe_animationevery 3-5 seconds until it reportscompletedorfailed. Do not hold a long-running request open. - On completion, give the user the watermarked preview and private management link. State that the free preview contains a watermark.
- If the user wants the clean video, prefer the management link so the user can
purchase or enter a code privately. Call
redeem_scribe_unlock_codeonly when the user explicitly supplies a code and asks the agent to redeem it. - Use
get_scribe_animation_downloadfor a short-lived download URL. Do not place video bytes into the model context.
If the MCP host cannot send the attached image as base64, follow the REST guide's multipart upload workflow instead of fetching an arbitrary remote image URL.
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.
- 11d ago First seen · 52 lines · 58 tokens per session scan A 96ff55aa51a8
the-scribble-thing is a skill published in the GitHub repository Boring-Stuff-Club/the-scribble-thing-skill (16 stars, last pushed 16d ago), licensed MIT. It adds 58 tokens to every session and 604 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
lanshu-create-ai-presenter-video
Turn a topic or finished script plus an authorized adult presenter image into a complete, publish-ready AI presenter video. Use for new presenter videos and for continuing, revising, captioning, lip-sync repairing, or re-exporting an existing presenter-video job. Keep model and provider selection capability-based and…
videoagent-video-studio
Generate short AI videos from text or images — text-to-video, image-to-video, and reference-based generation — with zero API key setup. Use when the user wants to create a video clip, animate an image, or generate video from a description.
multimodal-llm
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via gen4turbo), or building multimodal AI pipelines.
marketing
Use when the user wants the complete marketing asset suite for a product in one run — "/marketing", "build all the marketing assets", "generate everything for the launch", "all the animations and brand assets for X". Not for a single asset (use that asset's own skill) and not for launch copywriting alone (use /launch).
fal
Use when calling a fal.ai endpoint by id to generate image, audio, or video from JS/Python/curl: subscribe vs submit, queue states, ED25519 webhook signature verification, per-call cost, or migrating off @fal-ai/serverless-client. NOT which model or art direction (that is ai-media); NOT the same models on another…