latent-spaces/brag is a Claude Code skill that turns a newly created software project into a short launch video with music, motion, and accompanying sharing text. It is for developers who want to present and promote their projects, and the catalogue entry contains the skill and plugin used by coding agents to run it.
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 latent-spaces/brag --skill brag-slimgit clone --depth 1 https://github.com/latent-spaces/bragWrote 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/latent-spaces/brag/brag-slim)<a href="https://agentmods.dev/skills/latent-spaces/brag/brag-slim"><img src="https://agentmods.dev/badge/skills/latent-spaces/brag/brag-slim/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/latent-spaces/brag/brag-slim"><img src="https://agentmods.dev/badge/skills/latent-spaces/brag/brag-slim.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
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 | $0.00121 | $0.02059 |
| Opus 5.5 | $0.00048 | $0.00824 |
| Sonnet 5.5 | $0.00024 | $0.00412 |
| Haiku 4.5 | $0.00012 | $0.00206 |
Grade A, and why
brag-slim 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 2d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/brag-slim
You built it. Now brag. You make the whole video yourself — story, visuals, audio, render — with whatever tools are on the machine.
Whatever the tone, it should feel like a modern, slick, polished launch video: nothing on screen or in the soundtrack that doesn't earn its place.
Usage: /brag-slim [input] [options]. Options (flags or plain language):
| Option | Default |
|---|---|
--tone <preset or freeform> |
inferred; default if nothing clearly fits |
--format landscape|vertical|square |
landscape (1920×1080; vertical 1080×1920, square 1080×1080), 30fps |
--duration <s> |
about 20s |
Write the deliverables to brag-output/ in the current directory (timestamped brag-output-YYYY-MM-DD-HHmmss/ if it already exists). Keep every intermediate file (frames, downloads, scripts, stems) in a work/ subfolder inside it.
1. Inspect
First decide what the input is, then gather material from it. Only the source changes; everything from the questions below onward is the same for every input.
| Input | How to recognize it | Where the material comes from |
|---|---|---|
| Project | No input given, and the current directory is a project | The code |
| Website | An http(s):// URL, or a bare domain like example.com |
The live site |
If the input matches no type, or there's no input and the current directory isn't a project, ask the user what to brag about.
Project
Read the code: the main page, styles (exact colors and fonts), README, routes and key components. The best material is the product in use — find its 2–3 beats: entry → key action → result.
You have the source, so use it directly: import or render the project's real components, stylesheets, fonts, images and animations in the video instead of rebuilding them.
Don't read build output (dist/, .next/, build/), lock files, test files, .git/, env and secret files (.env, .env.*), key and credential material (.pem, .key, id_rsa, service-account JSON, anything under secrets/ or credentials/), local config that commonly holds tokens, or anything .gitignore excludes for those reasons.
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.
- 2d ago Changed · +4 lines 3079af81f423
- 14d ago Changed c97ea53d7c5d
- 21d ago First seen · 102 lines · 121 tokens per session scan A c78b6f56905b
brag-slim is a skill published in the GitHub repository latent-spaces/brag (16,156 stars, last pushed 3d ago), licensed MIT. It adds 121 tokens to every session and 2,059 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-25.
Other skills, from other repositories
hyperframes-motion-director
Direct and produce Chinese-first cinematic motion videos with HyperFrames. Use this skill when the user wants a rendered promo film, article-to-video piece, product launch film, website-to-video piece, keynote reveal, kinetic typography sequence, text/icon transition promo, music-synced motion graphic…
tryworld-paper
A workflow for turning a Chinese voiceover script and optional images into a branded 16:9 AI-knowledge video in the “Paper Algorithm” style.
tryworld-koubo
A Chinese-language workflow for making AI voiceover videos, covering topic selection, script writing, editing, and production.
tryworld-topics
A topic-planning skill for AI news videos, based on current AI news from a specified website. It creates several possible story ideas in the style of the TryWorld channel.
ad-restyler
Restyle any ad or video into a completely different visual style — Aardman claymation, LEGO-style bricks, X-ray, 16-bit pixel art, Ghibli anime, felt puppets, voxel art, knitted yarn, premium 3D Pixar-style animation, or a custom style built live — while preserving the original shots, camera moves, motion, and timing…
interflow-ip-video
A tool for turning Chinese scripts into 1080×1920 vertical MP4 videos with a talking character, cloned voice narration, animated charts, and word-level subtitles. It follows the Interflow Bold-Mono visual style.