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 openstory-so/openstory --skill stitch-playergit clone --depth 1 https://github.com/openstory-so/openstoryWrote 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/openstory-so/openstory/stitch-player)<a href="https://agentmods.dev/skills/openstory-so/openstory/stitch-player"><img src="https://agentmods.dev/badge/skills/openstory-so/openstory/stitch-player/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/openstory-so/openstory/stitch-player"><img src="https://agentmods.dev/badge/skills/openstory-so/openstory/stitch-player.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 | $0.00064 | $0.00620 |
| Opus 5.5 | $0.00026 | $0.00248 |
| Sonnet 5.5 | $0.00013 | $0.00124 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
stitch-player 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 today.
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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stitch-player
Play PlaybackClip[] in order with StitchedPlayer from @openstory/stitch/react. The package README (node_modules/@openstory/stitch/README.md) has the install and the component example. This file is the contract that example leaves easy to miss.
Clips
A video clip is { videoUrl, posterUrl, cues }. It plays the audio inside the file.
A still is { imageUrl, fallbackImageUrl, durationSeconds, audioUrls, width, height, cues }. audioUrls play back to back from the start of the still. The still lasts the longer of that sound and durationSeconds. width and height are the still's pixel size. durationSeconds stays positive even when the sound is longer.
posterUrl is for a host to show while it waits. The engine and StitchedPlayer do not paint it.
Cue times are seconds from the start of that clip.
Pass the new array through when the list changes. Identity is order plus the media (playbackClipsKey): for a video, videoUrl only; for a still, the image URLs, audioUrls, durationSeconds, width, and height. Cue text is outside that identity, so a wording-only change leaves the engine running. Download writes the cues on the array you passed.
Music
musicUrl is a bed under the whole sequence. musicGainDb changes only that bed. 0 leaves it as recorded. musicEnabled: false mutes the bed. Dialogue stays at its own level.
The player downloads clips whole, in order, up to two past the one playing. Play starts when the current clip is all here, and a stall at a cut lasts until the next clip is. Music still streams. There is nothing to tune.
Bytes
Video, music, and a still's audioUrls need an HTTP URL that answers Range with 206, or a blob: URL whose fetch does. A still's line may be a data: URL.
A cross-origin still with no CORS still displays. Export and picture-in-picture read the canvas, so that still taints it and those two throw SecurityError.
The file
The MP4 comes from exportSequence, downloadSequence, or the player's Download button. It is the same stitch as playback: H.264 and AAC. subtitles is sidecar (a .vtt beside the file), burn-in, or none. The default is sidecar.
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.
- today Changed · +2 lines 26804823d73e
- yesterday Changed · +4 tokens per session 9006c61361ea
- 2d ago Changed 2bc23d048d88
- 3d ago First seen · 37 lines · 60 tokens per session scan A 6a7621ecddf7
stitch-player is a skill published in the GitHub repository openstory-so/openstory (675 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 620 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-13.
Other skills, from other repositories
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.
frontend-verify
Verify frontend changes end to end after editing a web app, instead of manually clicking through pages. Use this whenever you have changed UI code and need to confirm nothing broke: "verify my frontend", "check the site after these edits", "did my UI break", "did my changes break anything", "make sure these routes…
demo
Record a short demo VIDEO of a PR or feature — drive the repo's web UI in a real headless browser, capture the session, and composite a titled, size-capped mp4 with ffmpeg. Use on the docker QA image when the deliverable is a playable demo clip (single walkthrough or before/after comparison), not a text/screenshot…
telegram-userbot
Use when full MTProto control of Telegram account via Telethon. DM, Voice Note, Call, Video Call, Group/Channel management, member scraping, bot cloning, outreach automation, broadcast, CRM tracking, content reposting, scheduled messaging, webhook triggers. Use for all Telegram automation as a real user (not bot API).
bilibili-cli
A command-line skill for Bilibili, a Chinese video-sharing platform. It retrieves videos, user profiles, searches, trending content, subtitles, favorites, and supported interactions in machine-readable output.
youtube-watcher-zh
A YouTube subtitle tool that downloads available captions with yt-dlp and uses them to summarize videos, answer questions, search for terms, and examine topics or word use.