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 music-intelligencegit 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/music-intelligence)<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/music-intelligence"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/music-intelligence/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/music-intelligence"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/music-intelligence.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 | $0.00058 | $0.00999 |
| Opus 5 | $0.00029 | $0.00500 |
| Sonnet 5 | $0.00012 | $0.00200 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
music-intelligence 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 6d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Music Intelligence
- Call
analyze_musicwhen the user asks to analyze music or no cache exists. It runs the installed local Beat This + CLAP models, waits for completion, and never downloads models; useforce:trueonly for an explicit reanalysis request. - Call
inspect_musicwhen only the existing cache is needed. - Before cutting video, call
music_edit_planand show its bounded cut/target summary. Before placing photos, callmusic_image_planand show its bounded placement summary. Prefertiming:auto; choose sparse, medium, or dense from the requested pace. - Only after the plan is accepted, call
sync_cuts_to_musicorsync_images_to_musicwith the returnedanalysisRef. Each tool recomputes the plan, rejects stale analysis, and applies its changes as one undo step. - If required model packs are missing, report the returned install guidance (Settings path + missing pack names), then ask whether to proceed with a
detect_beatsfallback for pure beat timing (BPM + beat frames only, no CLAP tags/sections/energy), or wait until the user installs the packs and retryanalyze_musicafter installation. - Never request, return, quote, summarize, or place the CLAP embedding in model context. Use tags, sections, confidence, and the opaque
analysisRefonly.
Preconditions
- Analysis is opt-in and on-device. The media-pool asset must already have a cache for its current
sourceRevision. rhythm-litesupplies Beat This rhythm data;music-semantics-litesupplies CLAP tags and the private similarity vector.- An Agent call must never install a pack, download a model, decode media, or start inference. Direct the user to Settings and the media-card analysis action when the cache is unavailable.
Inspect
- Identify the BGM by
itemId,assetId, or an unambiguous name. Prefer the timeline item when the user intends to edit, because returned points are then mapped to timeline frames through the clip trim and playback rate. inspect_musicreturns BPM, meter, confidence, tags, sections, counts, and bounded point lists. Lists are capped at 48 beats, 24 downbeats, 16 sections, and 12 tags; use a narrower range whentruncatedis true.- Treat
analysisRefas opaque. It binds later planning and execution to the exact cached analysis without exposing the 512-value CLAP embedding.
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.
- 6d ago Changed 415969ecd8cc
- 11d ago First seen · 50 lines · 58 tokens per session scan A 1a84851e9656
music-intelligence is a skill published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 999 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.