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 gabrielmoreira/agent-skills-mirror --skill batch-montage-variantsgit clone --depth 1 https://github.com/gabrielmoreira/agent-skills-mirrorWrote 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/gabrielmoreira/agent-skills-mirror/batch-montage-variants)<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/batch-montage-variants"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/batch-montage-variants/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/gabrielmoreira/agent-skills-mirror/batch-montage-variants"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/batch-montage-variants.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 | $0.00101 | $0.01163 |
| Opus 5 | $0.00051 | $0.00581 |
| Sonnet 5 | $0.00020 | $0.00233 |
| Haiku 4.5 | $0.00010 | $0.00116 |
Grade A, and why
batch-montage-variants 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 3d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batch Montage Variants
Use this workflow when the user wants many finished cuts from the same media pool — matrix accounts, A/B hook testing, platform variants, or daily batch output. Each output must satisfy the agreed mode: structural differentiation, a controlled hook test, or a platform adaptation.
This is an OpenChatCut-native workflow. Use the current project, source assets, asset-frame inspection, AV/script context, and built-in editing tools. Editing imported media requires no external service. Use external sources or processing pipelines only when explicitly requested by the user.
When to switch workflows
- One hero edit from many clips → Multi Clips to Reels. Do not use this skill to make a single cut.
- One long source defining a story → Long Video to Shorts.
- N distinct outputs from a shared pool → this skill.
Tell the user when you switch, and say why.
Workflow
- Read the project state before editing. Inventory the source pool: clip count, usable duration, aspect ratio, visual subjects, motion/energy, audio quality, and duplicates.
- Confirm the user wants more than one output and the pool supports the selected mode. Do not pad a distinct-cut batch with near-duplicates; controlled tests and platform adaptations may intentionally reuse an edit.
- Fix the batch contract before cutting — mode (distinct cuts, controlled hook test, or platform adaptations), count, target duration, platform, audience, language, and music bed. If more than one is missing, ask in one
<widget>after loadingwidget-forms. - Score every source asset for reuse headroom before planning. See references/variation-matrix.md. Reserve distinct hooks where the mode requires them; shared end cards and intentional shared bodies are allowed.
- Build the variation matrix before editing. For distinct cuts, plan different hooks and structural changes. For controlled hook tests, change only the hook and keep the body fixed. For platform adaptations, retain the approved content and adapt presentation. See references/variation-matrix.md.
- Plan the dedup budget with references/dedup-rules.md. Decide up front which dimensions carry the differentiation, and record the minimum separation each pair of cuts must clear.
- Get the matrix approved before cutting the whole batch. Show the plan as a table: cut number, hook, order signature, rhythm, duration, packaging, and the dimension that makes it different from every other cut in the batch.
- Cut the first variant end to end and verify it renders and exports before batching the rest. Do not generate eight timelines that share one unverified mistake.
- Cut remaining variants from the approved matrix. Reuse picks and trims according to the approved mode; distinct cuts and hook tests need different openings, while platform adaptations may share them.
- Name timelines so the batch is auditable:
<topic>-v<NN>-<hook-label>, consistent across the batch. - QA each cut individually and the batch as a set. See references/dedup-rules.md for the pairwise checks.
- Report per-cut timeline names, durations, the differentiation dimension for each, and which pair is the most similar — that is the pair the user should review first.
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.
- 3d ago First seen · 61 lines · 101 tokens per session scan A b96febb4c0ff
batch-montage-variants is a skill published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 1,163 once invoked, about $0.0005 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 2026-09-10.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…