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 creative-int/kumori-plugins --skill kumori-stickersgit clone --depth 1 https://github.com/creative-int/kumori-pluginsWrote 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/creative-int/kumori-plugins/kumori-stickers)<a href="https://agentmods.dev/skills/creative-int/kumori-plugins/kumori-stickers"><img src="https://agentmods.dev/badge/skills/creative-int/kumori-plugins/kumori-stickers/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/creative-int/kumori-plugins/kumori-stickers"><img src="https://agentmods.dev/badge/skills/creative-int/kumori-plugins/kumori-stickers.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 | $0.00039 | $0.00708 |
| Opus 5 | $0.00019 | $0.00354 |
| Sonnet 5 | $0.00008 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
kumori-stickers 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 10d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kumori stickers
kumori turns a photo into a die-cut sticker. The grammar is fixed: image + style in → sticker out. There is no prompt anywhere in the flow. The image is the subject; the style is the only creative decision.
Connect to the kumori MCP server at https://mcp.kumori.camera/.
The loop
- Orient. Call
kumori_get_infofirst: it returns the user's credit balance, generation stats, and a compact style catalog. OAuth-capable clients authorize on first use. Each generation spends one credit. - Pick one style. Use the catalog from
kumori_get_info, or callkumori_list_filtersfor the full live list (slug, name, description). Choose ONE slug that suits the image. Never invent slugs. - Get the image in. Exactly one source per call, in priority order:
input_image_url— preferred whenever the image already has ANY URL (web, CDN, Slack, chat upload).input_image_data— base64 (raw or data URL) for local or chat images without URLs, up to 4MB.input_key— for large local files (>4MB) when shell access exists: callkumori_prepare_upload, HTTP PUT the bytes toupload_url, then pass the returnedinput_key.
- Generate. Call
kumori_generate_imagewithfilter_slugplus the one image source. Usewait=truefor a single blocking call (typical generation: 45-60s; timeout up to 120s), orwait=falseto poll. - Poll (when wait=false). Call
kumori_check_generationevery 2-3 seconds while status ispendingorprocessing. The response carriesprogress.percent, the current step, and loading text worth relaying to the user. Stop oncompletedorfailed. - Deliver. On
completed:- Save the sticker when the client has a filesystem: fetch
image_urland write the bytes as returned — the sticker ships with its die-cut edge. - ALWAYS include
share_urlin your reply. It is the public kumori.camera page for the finished sticker and the easiest way for the user to view, share, or save it from any device.
- Save the sticker when the client has a filesystem: fetch
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.
- 10d ago First seen · 57 lines · 39 tokens per session scan A 6cd3d1a8dc56
kumori-stickers is a skill published in the GitHub repository creative-int/kumori-plugins (0 stars, last pushed 25d ago), licensed MIT. It adds 39 tokens to every session and 708 once invoked, about $0.0002 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.