Borrowing it
Nothing to install: this file belongs to st0012/cctop. 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/st0012/cctop/master/.agents/skills/video-assets/SKILL.mdgit clone --depth 1 https://github.com/st0012/cctopWrote 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/st0012/cctop/video-assets)<a href="https://agentmods.dev/skills/st0012/cctop/video-assets"><img src="https://agentmods.dev/badge/skills/st0012/cctop/video-assets.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00120 | $0.01326 |
| Opus 5 | $0.00060 | $0.00663 |
| Sonnet 5 | $0.00024 | $0.00265 |
| Haiku 4.5 | $0.00012 | $0.00133 |
Grade A, and why
video-assets 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 8d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Assets
Manage cctop video files as GitHub Release assets, not as committed repo binaries. The default pattern is one non-latest media release that acts as a stable asset bucket.
Rules
- Default release tag:
media-assets. - Default release title:
Media assets. - Always create media-only releases with
--latest=false. - Do not use a
v*tag for media-only work. In cctop,v*tags trigger.github/workflows/release.yml: app builds, notarization, GitHub Release creation, Sparkle appcast, and Homebrew updates. - Attach a video to a real
v*release only when the user explicitly asks and the video truthfully demonstrates that shipped app version. - Keep full MP4s and other large rendered video out of git. Do not commit
video/projects/*/.video-build/. - Commit a small animated README preview only when the user explicitly chooses that route and the file is intentionally small.
- Prefer stable purpose-based asset names over dates:
cctop-launch.mp4,cctop-launch-720p.mp4,cctop-launch-preview.avif. - For launch video uploads, always generate and upload the AVIF preview alongside the MP4s so the README preview and full video stay in sync.
Workflow
-
Identify the source files.
- Launch defaults:
video/projects/launch/.video-build/launch.mp4andvideo/projects/launch/.video-build/launch-720p.mp4. - Check existence and size with
ls -lh. - Check duration/codec with
ffprobewhen available.
- Launch defaults:
-
Pick the release target.
- Use
media-assetsfor reusable README/demo/launch assets. - Use an existing app release such as
v0.18.4only with explicit user direction. - Inspect before mutating:
gh release view media-assets --repo st0012/cctop.
- Use
-
Pick stable asset names.
- Reusing the same asset name plus
--clobberkeeps the download URL stable. - Use a new asset name when history matters or two variants should coexist.
- Remember:
gh release upload file.mp4#Labelsets a display label, not a stable download filename. Stage or copy the file to the intended asset filename before upload. - Default launch asset set:
cctop-launch.mp4fromlaunch.mp4cctop-launch-720p.mp4fromlaunch-720p.mp4cctop-launch-preview.avifgenerated fromlaunch-720p.mp4
- Reusing the same asset name plus
What ships with it
3 files 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.
- 8d ago First seen · 109 lines · 120 tokens per session scan A be51efbca198
video-assets is a skill published in the GitHub repository st0012/cctop (149 stars, last pushed 2d ago), licensed MIT. It adds 120 tokens to every session and 1,326 once invoked, about $0.0006 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
checkpoint-management
Git-backed state management for safe rollback. Create and restore checkpoints with tagged commits and metadata tracking.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
shipping-a-pr
Use when finished work needs to ship as a pull request, or when the ask is about a PR — creating one, bringing it up to date, adding screenshots, watching its checks, or addressing its review comments. Not for reviewing a PR you are not shipping.
agf
Find local coding-agent sessions, inspect bounded metadata or summaries, and prepare a read-only resume plan with AGF. Use for finding prior work across agent CLIs, not for executing agents, deleting sessions, or reading full transcripts.
makefile
Use when creating or updating a Makefile for a project, especially when standard targets (build, test, lint, format, etc.) are missing or when modifying targets that may already be wired into other tooling. Not for debugging why a build fails.
ring:generating-release-guides
Generating an internal Operations-facing update/migration guide from the git diff between two refs, documenting per-change client impact, deploy ordering, monitoring, and rollback notes in English, pt-br, or both. Use when preparing a version release or recording what changed for the Ops team. Runs read-only by…