Borrowing it
Nothing to install: this file belongs to nozomi-koborinai/terradart. 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/nozomi-koborinai/terradart/main/.agents/skills/terradart-promo-video/SKILL.mdgit clone --depth 1 https://github.com/nozomi-koborinai/terradartWrote 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/nozomi-koborinai/terradart/terradart-promo-video)<a href="https://agentmods.dev/skills/nozomi-koborinai/terradart/terradart-promo-video"><img src="https://agentmods.dev/badge/skills/nozomi-koborinai/terradart/terradart-promo-video/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/nozomi-koborinai/terradart/terradart-promo-video"><img src="https://agentmods.dev/badge/skills/nozomi-koborinai/terradart/terradart-promo-video.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 | $0.00065 | $0.04328 |
| Opus 5.5 | $0.00026 | $0.01731 |
| Sonnet 5.5 | $0.00013 | $0.00866 |
| Haiku 4.5 | $0.00006 | $0.00433 |
Grade A, and why
terradart-promo-video 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 24d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TerraDart promo video
Policy lives in AGENTS.md. This skill is the repeatable workflow for a release announcement clip. The deterministic work belongs to tool/promo/ (a release clip) and tool/promo_video.sh (one screen recording, cut and branded); what stays here is the part a script cannot decide.
Contents
- When to use
- What a clip may claim
- Workflow
- Writing the beats
- Narration
- The brand system on screen
- One screen recording
- Delivery
- Writing the copy
- Pitfalls
When to use
- A release ships a user-visible command or capability the maintainer wants to announce.
- An existing clip needs re-cutting (different zoom, different end card, a delivery encode for a new platform).
Not for docs GIFs or website/ assets — those are authored with the page, not as a release artifact.
What a clip may claim
The copy may only claim what the clip shows. This is the highest-value rule here, because a wrong claim is a public credibility problem rather than rework.
- A clip of a fixture or sample tree supports "converts a Terraform tree". It does not support "migrated a real app".
- Only claim
terraform planreports No changes once the status gate for it is actually ticked — that gate needs a real tree against real state, and it is maintainer work, not an agent's. - Numbers spoken in the copy must be the numbers on screen (
82 migrated, 0 kept), from the version in the clip. - Never name a third-party repository as a migration success without the maintainer's explicit go-ahead.
When a claim is tempting but unsupported, cut the claim, not the caveat.
Workflow
tool/promo/ holds the whole clip as code: tapes/*.tape (the terminal beats, recorded by VHS), storyboard.json (scenes, cuts and holds, camera keyframes, masks, captions, which lines of the generated files to show, the ocr deny list) and a Remotion composition under src/ that reads the site's tokens and syntax theme. Re-recording after a CLI change is a re-run, not a re-edit.
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.
- 24d ago Changed · +10 lines e162c87a148a
- 25d ago Changed · +21 lines · +10 tokens per session 92c941da1abf
- 1mo ago Changed f1b9180f24ab
- 1mo ago First seen · 126 lines · 55 tokens per session scan A 1056ede01fb4
terradart-promo-video is a skill published in the GitHub repository nozomi-koborinai/terradart (52 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 4,328 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 2026-09-14.
Other skills, from other repositories
terraform-infrastructure-as-code
Comprehensive Terraform Infrastructure as Code skill covering resources, modules, state management, workspaces, providers, and advanced patterns for cloud-agnostic infrastructure deployment.
Terraform Infrastructure as Code
Production-grade Terraform development with HCL best practices, module design, state management, multi-cloud patterns, and AI-enhanced infrastructure as code for scalable cloud deployments.
reviewing-blogs
Reviews and critiques blog posts in src/content/blog/posts/ against Appwrite's established standards for voice, tone, structure, SEO, formatting, and accuracy. Use when the user asks to review, audit, critique, or improve an existing blog post.
auditing-terraform-infrastructure-for-security
Auditing Terraform infrastructure-as-code for security misconfigurations using Checkov, tfsec, Terrascan, and OPA/Rego policies to detect overly permissive IAM policies, public resource exposure, missing encryption, and insecure defaults before cloud deployment.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
effective-dart
Use when writing Dart code, reviewing for style, refactoring naming, adding doc comments, structuring imports, or enforcing type annotations.