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 benyki/gtm-engine --skill vidwatch-buildergit clone --depth 1 https://github.com/benyki/gtm-engineWrote 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/benyki/gtm-engine/vidwatch-builder)<a href="https://agentmods.dev/skills/benyki/gtm-engine/vidwatch-builder"><img src="https://agentmods.dev/badge/skills/benyki/gtm-engine/vidwatch-builder/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/benyki/gtm-engine/vidwatch-builder"><img src="https://agentmods.dev/badge/skills/benyki/gtm-engine/vidwatch-builder.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 | $0.00089 | $0.02041 |
| Opus 5.5 | $0.00036 | $0.00816 |
| Sonnet 5.5 | $0.00018 | $0.00408 |
| Haiku 4.5 | $0.00009 | $0.00204 |
Grade A, and why
vidwatch-builder 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 2mo 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vidwatch Builder
vidwatch is a local Electron app that answers one question: "what did my automated posting pipeline actually put out, and how is it doing?" It walks folders of rendered videos, joins them against a posting ledger, and renders a grid of cards with poster frames, per-platform status, and live view/like counts.
This skill builds it on any machine, against any folder layout and any metadata format. Nothing here assumes a particular author's paths.
When to Use This Skill
- "Build vidwatch on this computer" / "set up vidwatch for my project"
- "Port vidwatch to Linux/Windows" or "my videos live somewhere else"
- "My metadata looks different — make vidwatch read it"
- "Add YouTube/Instagram/Bluesky metrics to vidwatch"
- "Make vidwatch's paths configurable instead of hardcoded"
- Building any local dashboard over a render-and-post pipeline's output
The One Idea You Must Get Right
Everything in vidwatch derives from one join:
a video file on disk ⋈ a record of it being posted ⋈ live platform metrics
(the artifact) (the ledger / status file) (fetched on demand)
The app is a viewer over that join. Every feature — status dots, the leaderboard, engagement rates, filters — is a projection of it. Get the join right and the UI is straightforward. Get it wrong and no amount of UI work helps.
The join key is the stem: the mp4's filename without extension. Everything else (metadata sidecars, ledger records, platform status) is keyed off that stem or the mp4's absolute path.
Build Order
Work in layers. Each layer is independently useful and independently skippable — stop whenever the app is good enough for the user's needs. Do not build layer N+1 before layer N renders something real on screen.
| Layer | Gives you | Skippable? |
|---|---|---|
| 0 · Shell | Empty window, build pipeline, hot rebuild | No |
| 1 · Sources | Which folders hold finished videos | No |
| 2 · Posts | A card per video + its metadata | No |
| 3 · Ledger | Real post times, accounts, permalinks | Yes → falls back to file mtime |
| 4 · Platform status | Per-platform posted/pending badges | Yes |
| 5 · Live metrics | Views/likes, removal detection, leaderboard | Yes |
| 6 · Thumbnails | Poster frames from the video | Yes → shows a placeholder |
| 7 · Packaging | A real .app/.exe in the dock/taskbar | Yes → npm start works fine |
What ships with it
7 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.
- 2mo ago First seen · 175 lines · 89 tokens per session scan A 6eed682d910e
vidwatch-builder is a skill published in the GitHub repository benyki/gtm-engine (4 stars, last pushed 6d ago), licensed MIT. It adds 89 tokens to every session and 2,041 once invoked, about $0.0004 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 2026-08-31.
vidwatch-builder compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vidwatch-builderbenyki/gtm-engine | Skill | 4 | 6d ago | MIT | A | 89 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |