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 escoffier-labs/skillet --skill reel-checkgit clone --depth 1 https://github.com/escoffier-labs/skilletWrote 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/escoffier-labs/skillet/reel-check)<a href="https://agentmods.dev/skills/escoffier-labs/skillet/reel-check"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/reel-check/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/escoffier-labs/skillet/reel-check"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/reel-check.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 | $0.00087 | $0.01295 |
| Opus 5 | $0.00044 | $0.00647 |
| Sonnet 5 | $0.00017 | $0.00259 |
| Haiku 4.5 | $0.00009 | $0.00129 |
Grade A, and why
reel-check scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Shell prompts** - `user@hostname` in the terminal prompt, the path in `pwd`, a private IP in an `ssh`/`curl` command. How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reel-check
The video equivalent of plate: the last look before a reel leaves the kitchen. A reel leaks differently from prose, so it needs its own pass. plate scrubs a block of text you can read and edit. A reel is a rendered MP4 you cannot grep, built from two surfaces that each leak:
- The composition source - the text that gets burned into the frames.
- The recording footage - whatever the screen capture happened to show.
You scrub the source, re-render or re-record, then verify the actual frames. The MP4 is the source of truth for what viewers see; source files can diverge from what got drawn.
What to scan
1. Composition source (on-screen text)
The captions, titles, and labels viewers read come from source files, not the video. Scan each:
- Cue / timeline JSON -
captions[].text,titleCard.text,outroCard.text, any label fields. - Composition file -
index.html/*.tsxtext nodes,data-*titles, alt text. - Narration -
SCRIPT.md, TTS input text, voiceover scripts (a leak spoken aloud is still a leak). - Brand sheet -
DESIGN.mdand any generated metadata that ships with the project.
Leak types are the same as plate: internal hostnames and machine names, private IPs (RFC 1918), LAN URLs / ports / dashboards, absolute home paths (/home/<user>, /Users/<name>), non-public personal emails, and AI-authorship disclosure. See plate for the full list, the doc-range replacements (RFC 5737 192.0.2.x), and the writing conventions (no em dashes). A cold agent will not know the user's machine names - ask, or flag any internal-looking host for confirmation.
2. Recording footage (incidental leaks)
A screen recording shows far more than the text you authored. This is the surface plate has no concept of, and it is the one most often missed. Eyeball the footage for:
- Shell prompts -
user@hostnamein the terminal prompt, the path inpwd, a private IP in anssh/curlcommand. - Browser chrome - the URL bar, an internal dashboard, a private IP, logged-in account name or avatar.
- Notifications and chrome - toast popups, email/Slack/Discord previews with real names, the OS clock/menubar, other window titles.
- Anything the cursor or a zoom cue emphasizes - emphasis draws the eye straight to whatever is under it. Make sure that is not a leak.
What ships with it
2 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.
- 11d ago First seen · 82 lines · 87 tokens per session scan A ba9420defaeb
reel-check is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed 10d ago), licensed MIT. It adds 87 tokens to every session and 1,295 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
create-video-seedance-2-fal
Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills…
create-workflow-diagram
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…
render-cosmic-mythology-voiceover
Assemble a cosmic-mythology-voiceover reel from a config — a warm spoken voiceover carries the whole narrative while N curated cosmic stills are weighted beat-synced across the delivered VO duration (cutdur = VOdur times weight over the weight sum, so emotional beats hold longer), Ken-Burns-zoomed per still (scale 2x…
render-mosaic-grid-reveal
Render a 'mosaic-grid-reveal' video from a config — a real-DOM FULL-BLEED N×N mosaic of real product tiles that pops in one tile at a time (scatter order, ease-out-back overshoot), the grid clears, then the brand wordmark builds line-by-line followed by a sub-label, tagline, and CTA; frame-stepped via Playwright and…