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 Elumenotion/GuideAnts --skill video-timelinegit clone --depth 1 https://github.com/Elumenotion/GuideAntsWrote 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/elumenotion/guideants/video-timeline)<a href="https://agentmods.dev/skills/elumenotion/guideants/video-timeline"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/video-timeline.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 | $0.00081 | $0.02045 |
| Opus 5 | $0.00041 | $0.01022 |
| Sonnet 5 | $0.00016 | $0.00409 |
| Haiku 4.5 | $0.00008 | $0.00204 |
Grade A, and why
video-timeline 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 4d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video-timeline
Third step of the video-production pipeline (after
session-ingestion-scripting and TTS generation). Paths — fixed layout, do
not probe. The sandbox CWD is the notebook's output directory; write every
deliverable to the CWD with a bare filename (never prefix Output/).
Scripts live under Skills/<skill>/scripts/ relative to the CWD — run the
commands in this file exactly as written.
Requires openpyxl (for the .xlsx deliverable); everything else is stdlib.
pip install openpyxl if missing.
What this skill produces — and what it deliberately is not
The deliverable is a story document a human edits: one xlsx, one row per story moment, with dropdowns for visual type (New Image / Slide / Video Clip / Session B-roll / End Card / Hold), an empty Asset/file column the user fills, and a Status workflow (To-do → Have → Verify → Done).
It is not a frame map. Extracting frames, aligning raw-footage spans, and building storyboards are optional internal means to inform suggestions — never the deliverable. The user's standing instruction: help me build the visual timeline to tell a story, not to map the video frames.
Learnings that are binding for this skill (from the 2026-08-27 intro-video session — do not regress):
- Audit the audio first. The picture plan is driven by measured numbers (WPM per 30-s bucket, the real pause ladder, 0-s/1-s TTS seams, missing tail), not by taste.
- Rows are story moments, chained with no gaps from 0:00 to audio-end + a 1.5–2.5 s tail pad. Split or merge freely; keep the chain unbroken.
- "What Doug says" is a plain-English summary of the narration at that time — never a verbatim transcript dump, never longer than ~60 words.
- The assistant proposes, the user decides. Pre-fill Visual type + What to show as suggestions; the user owns the asset choices.
- QA is scripted, not vibes.
qa_timeline.pyproduces a 100-point score with per-check evidence; quote it, do not assert.
What ships with it
4 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.
- 4d ago First seen · 161 lines · 81 tokens per session scan A cbc83e446838
video-timeline is a skill published in the GitHub repository Elumenotion/GuideAnts (57 stars, last pushed yesterday), licensed Apache-2.0. It adds 81 tokens to every session and 2,045 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
download-media
Use when user wants to download, save, or extract media files such as photos, videos, and documents from Telegram messages.
document-skills
Professional document creation, editing, and analysis for Office formats (docx, pdf, pptx, xlsx). Use when working with Word documents, PDFs, PowerPoint presentations, or Excel spreadsheets.
recipe-backup-sheet-as-csv
Export a Google Sheets spreadsheet as a CSV file for local backup or processing.
recipe-bulk-download-folder
List and download all files from a Google Drive folder.
recipe-create-events-from-sheet
Read event data from a Google Sheets spreadsheet and create Google Calendar entries for each row.
recipe-create-expense-tracker
Set up a Google Sheets spreadsheet for tracking expenses with headers and initial entries.