Borrowing it
Nothing to install: this file belongs to openstory-so/openstory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/openstory-so/openstory/main/.claude/skills/update-model-versions/SKILL.mdgit 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/update-model-versions)<a href="https://agentmods.dev/skills/openstory-so/openstory/update-model-versions"><img src="https://agentmods.dev/badge/skills/openstory-so/openstory/update-model-versions/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/update-model-versions"><img src="https://agentmods.dev/badge/skills/openstory-so/openstory/update-model-versions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 73 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00125 | $0.02725 |
| Opus 5 | $0.00063 | $0.01362 |
| Sonnet 5 | $0.00025 | $0.00545 |
| Haiku 4.5 | $0.00013 | $0.00272 |
Grade C, and why
update-model-versions scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl https://genmedia.sh/install -fsS | bash # once, if missing Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Behind a proxy it routes through `curl` (Bun's fetch can't traverse a How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update model versions
Our model registries are the single source of truth:
| Class | File | Export |
|---|---|---|
| Text (OpenRouter) | src/models/models.config.ts |
SCRIPT_ANALYSIS_MODELS |
| Image (fal.ai) | src/models/models.ts |
IMAGE_MODELS |
| Video / motion (fal.ai) | src/models/models.ts |
IMAGE_TO_VIDEO_MODELS |
| Audio (fal.ai) | src/models/models.ts |
AUDIO_MODELS |
| BytePlus Ark ids | src/models/models.ts |
byteplusId fields |
A model with a native BytePlus route (#1157) carries two ids under one
key: the fal endpoint id AND a byteplusId (Ark model id). A version bump
must move BOTH — bumping only the fal id silently routes Ark traffic to the
older model (and vice versa), and the pricing alias
(applyBytePlusRouteAliases) would quote the wrong rate for whichever id was
left behind.
The goal each run: detect newer versions → verify each is a real successor → open a focused PR that bumps it → leave everything green.
npm dependencies are out of scope. Bumping @tanstack/ai* (or any other npm
package) is Dependabot's job, not this routine's — the detector no longer checks
the npm registry. Don't open model-freshness PRs or issues for package versions.
1. Detect candidates
bun models:check # human-readable report
bun models:check --json # { ok, errorCount, hasUpdates, models[] }
scripts/check-model-updates.ts reads the registries and queries public,
unauthenticated catalogs (fal.ai /api/models, OpenRouter /api/v1/models).
BytePlus Ark ids are checked offline against the installed
@tanstack/ai-byteplus model catalog — Ark publishes no unauthenticated
catalog, so the adapter's lists are the freshness source. Everything else is
HTTP-only so it runs anywhere — no FAL_KEY or MCP needed.
Behind a proxy it routes through curl (Bun's fetch can't traverse a
TLS-intercepting proxy), so curl must be on PATH in that case.
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 84b5a983caa3
- 11d ago First seen · 198 lines · 125 tokens per session scan C fa058fd0a27c
update-model-versions is a skill published in the GitHub repository openstory-so/openstory (607 stars, last pushed yesterday), licensed MIT. It adds 125 tokens to every session and 2,725 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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.
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.
seedance-2.0-prompter
Expert prompt engineering for Seedance 2.0. Use when the user wants to generate a video with multimodal assets (images, videos, audio) and needs the best possible prompt.
paidf-cosmos-predict
Prepare and run PAIDF Cosmos Predict video generation for DEFT media samples.
tao-finetune-cosmos-embed
Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user asks to "fine-tune Cosmos-Embed1", "run cosmos-embed inference", "export Cosmos-Embed1", "embed videos", or "search videos with text".
tao-finetune-video-clip
InternVideo2-CLIP L14 (TAO videoclip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorRT deployment. Use when the user asks to "fine-tune IV2CLIP", "run videoclip train/evaluate/inference/export", "build a Video-CLIP TensorRT engine"…