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 beat-sync-montagegit 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/beat-sync-montage)<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/beat-sync-montage"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/beat-sync-montage/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/beat-sync-montage"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/beat-sync-montage.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 | $0.00081 | $0.01122 |
| Opus 5 | $0.00041 | $0.00561 |
| Sonnet 5 | $0.00016 | $0.00224 |
| Haiku 4.5 | $0.00008 | $0.00112 |
Grade A, and why
beat-sync-montage 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.
Beat Sync Montage
Use this workflow when the edit should be driven by music. The failure mode to avoid is a metronome edit: every cut technically lands on a beat, and the result still feels mechanical, tiring, or unrelated to what is on screen.
This workflow decides what to cut and why. It does not re-explain the
music tools — when you reach an execution step, follow music-intelligence for
analyze_music, music_edit_plan, and sync_cuts_to_music. Load it there.
This is a OpenChatCut-native workflow. Use the current project, source assets, asset-frame inspection, AV/script context, and OpenChatCut editing tools.
When to switch workflows
- Beat-synced photos on a locked, empty track →
music-intelligencehandles this directly withmusic_image_plan. This workflow is for video montage. - One long source cut to speech rhythm →
long-video-to-shorts. - Many clips packaged as highlights without music driving the cut →
multi-clips-to-reels. - N distinct beat-synced variants from one pool →
batch-montage-variants, using this workflow for each cut.
Workflow
- Confirm the track is on the timeline and identified. Read the music first: BPM, meter, sections, and energy shape. Use
music-intelligence→analyze_musicorinspect_music; never request the CLAP embedding. - Judge whether the material actually suits a beat edit. See references/shot-fitness.md. Footage with no clear motion onset, or whose motion contradicts the music's energy, will not improve by cutting on every beat. Say so instead of forcing it.
- Choose the density arc before choosing individual cut points. See references/beat-density.md. Density is a property of the whole piece, not a per-cut decision: a verse and a chorus should not be cut the same way.
- Assign content to the music's structure. Map sections to narrative roles — intro to the hook, verse to context, build to escalation, drop/chorus to payoff. Cut density follows that map.
- Pick the anchor points first: 3–6 moments where a cut must hit a downbeat or a section boundary because the content has real impact there. See references/beat-density.md. Everything else is filler rhythm between anchors.
- Fill between anchors at the density chosen for that section. Do not fill uniformly — uniform filling is what makes an edit feel mechanical.
- Reserve breathing room. See references/beat-density.md. A montage that never stops cutting exhausts the viewer and hides the anchors you built in step 5.
- Check motion continuity across cuts. See references/shot-fitness.md. Consecutive cuts should not fight each other in screen direction or motion axis unless the collision is deliberate.
- Plan with
music_edit_plan, show the bounded summary and any cap warning, and get acceptance. Then apply withsync_cuts_to_musicand the returnedanalysisRef. Followmusic-intelligencefor both. - QA by watching, not by counting. See the rules below. A cut list that is 100% on-beat can still be a bad 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.
- 3d ago First seen · 61 lines · 81 tokens per session scan A aa4f43ff2061
beat-sync-montage is a skill published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 1,122 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 2026-09-10.
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…