Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ao92265/claude-code-playbook/plugin install playbookWrote 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/ao92265/claude-code-playbook/loom-analyze)<a href="https://agentmods.dev/skills/ao92265/claude-code-playbook/loom-analyze"><img src="https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/loom-analyze/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/ao92265/claude-code-playbook/loom-analyze"><img src="https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/loom-analyze.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 | $0.00070 | $0.00614 |
| Opus 5 | $0.00035 | $0.00307 |
| Sonnet 5 | $0.00014 | $0.00123 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
loom-analyze 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 8d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loom Analyze
Local pipeline (no API key, no third-party MCP) that turns a Loom share URL into:
- A plain-text transcript via
whisper. - Optional keyframe PNGs for visual analysis when the user asks about UI / screen content.
When to invoke
- User pastes a
https://www.loom.com/share/...URL. - User says "transcribe", "analyze", or "watch this loom".
/loom-analyze <url>is typed.
How to run
The shell wrapper lives next to this file: loom-analyze.sh. Always call it through Bash.
${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}/skills/loom-analyze/loom-analyze.sh <URL> [--model M] [--frames N] [--keep]
Flags:
--model base|small|medium|large— whisper accuracy/speed tradeoff. Defaultbase(~140 MB download first time).--frames N— also extract one PNG every N seconds intoframes/. Skip this for transcript-only (faster).--keep— keep MP4/MP3 after transcribing. Default deletes them.
Output goes to ~/Downloads/loom-transcripts/<id>/. The transcript is printed to stdout, so the agent gets it in the tool result.
Decision rules for the agent
- Transcript-only is the fast default. Don't request frames unless the user asks about visuals, UI, screen content, or a demo walkthrough.
- Long videos (>10 min): stick to
--model base.--model smallor larger only when the user specifically complains about transcript accuracy. - When frames are extracted: read the PNGs from
~/Downloads/loom-transcripts/<id>/frames/via the Read tool when the user asks what's on screen at a given time. Don't bulk-read every frame; pick the ones that match the question. - First-time setup: if the script exits with "Missing dep", run
${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}/skills/loom-analyze/setup.shonce, then retry.
Setup (per-machine, one-time)
bash ${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}/skills/loom-analyze/setup.sh
Installs yt-dlp, ffmpeg, openai-whisper via Homebrew + pip. Idempotent.
For machine requirements, model disk sizes, troubleshooting, and limitations, see references/usage.md.
What ships with it
3 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.
- 8d ago First seen · 51 lines · 70 tokens per session scan A 4a585d94ffa0
loom-analyze is a skill published in the GitHub repository ao92265/claude-code-playbook (10 stars, last pushed 22d ago), licensed MIT. It adds 70 tokens to every session and 614 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 2026-08-31.
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).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
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.