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 obto-inc/platform --skill obto-uploadgit clone --depth 1 https://github.com/obto-inc/platformWrote 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/obto-inc/platform/obto-upload)<a href="https://agentmods.dev/skills/obto-inc/platform/obto-upload"><img src="https://agentmods.dev/badge/skills/obto-inc/platform/obto-upload.svg" alt="Measured on agentmods" 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 | $0.00152 | $0.01426 |
| Opus 5 | $0.00076 | $0.00713 |
| Sonnet 5 | $0.00030 | $0.00285 |
| Haiku 4.5 | $0.00015 | $0.00143 |
Grade A, and why
obto-upload 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 7d 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.
- **Don't ask the agent's sandbox to PUT** — confirm an egress-capable client does it, or the curl How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Uploading local media/binary into OBTO
OBTO stores media/binary in a file worker and serves it at
https://{domain}.obto.co/ms/filereader.bto?n=<fileName> (video via videoplayer.bto).
This is a different subsystem from artifact-source deploys (obto-deploy): here the goal is to
get file bytes into the store and receive a served viewer URL back.
The hard rule: never inline file bytes into a tool-call argument. The agent→tool channel
truncates and corrupts large or dense values (a ~1.7KB clean-truncation ceiling; base64 also
corrupts above that). Any path that pushes the bytes through a chunk / base64 tool arg is
unreliable on its own. Move the bytes by a side channel and pass only a small reference.
Decision order
- Bytes already at an https URL OBTO can reach →
obto_upload_media({ url, filename, domain }). The server fetches it directly. Done. - Local file + a client with network egress (the user's terminal, a browser, the Cowork host, or a helper script) → signed-URL direct upload (PRIMARY, below).
- Local file + only the MCP channel (no egress anywhere) → chunked staging with the integrity gate (FALLBACK, below).
The agent's own sandbox usually has NO network egress (the egress proxy blocks all hosts; the "additional allowed domains" setting is currently non-functional and is fixed at sandbox start). So the agent generally cannot be the uploader itself — the actual PUT must run on an egress-capable client. Mint the URL via MCP, then have that client do the PUT.
Primary: signed-URL direct upload
- Mint a grant:
obto_request_upload_url({ domain, filename, [contentType], [folder] }). Returns a single-use, 5-minute presigned PUT URL (https://mcp.obto.co/ms/mcp_upload_receive?id=...), a ready-to-runcurl_command, and the limits. It is domain-scoped, so noappNameis required. - PUT from an egress-capable client as base64 inside a JSON body:
{"data":"<base64-of-file>"}withContent-Type: application/json. The receive route validates the grant (single-use, TTL), decodes, TUS-stores via the file worker, and returns the served URL.- The provided
curl_commanddoes exactly this (base64 in the shell, then PUT). Or run theobto-upload.jshelper:node obto-upload.js <file> --token <mcp-jwt> --domain staging.
- The provided
- Read the served URL from the PUT response:
{ ok:true, url, fileName, bytes }.
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.
- 7d ago First seen · 88 lines · 152 tokens per session scan A d7cbedfe33cb
obto-upload is a skill published in the GitHub repository obto-inc/platform (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 152 tokens to every session and 1,426 once invoked, about $0.0008 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
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
post-to-xhs
A publishing guide for 小红书, a Chinese social-media platform. It covers posting image-and-text content or a longer formatted article, using supplied content or a webpage.
screenshot-camera
Capture a screenshot from a Unity Camera and return it as a PNG image for direct LLM inspection. Falls back to Camera.main (then any active camera) when cameraRef is null. Width and height are capped to keep response size manageable.
screenshot-game-view
Capture a screenshot of the Unity Editor's Game View by reading its internal render texture directly. Image size matches the current Game View resolution; the tool corrects Y-flip on DirectX / Metal so the output is always upright. Requires an open Game View window.
screenshot-scene-view
Capture a screenshot from the Unity Editor Scene View at the requested size. Renders via the Scene View's active camera onto a temporary RenderTexture. Requires an open Scene View.
AI Image & Video Generator — GPT Image 2, Seedance, ComfyUI
Generate images and videos from text with multi-provider routing — supports GPT Image 2.0 (near-perfect text rendering), Nanobanana 2, Seedream 5.0, Midjourney V8.1 (unified photorealistic + anime), Flux 2 Klein (cheap drafts), Seedance 2.0 / Veo 3.1 / Grok Video / Agnes Video, and local ComfyUI workflows. Includes…