content-carousel

A command for planning multi-frame carousel posts: short sequences of slides for platforms such as Instagram and LinkedIn.

In plain words
What is it for?
Choosing a platform, topic, tone, visual style, frame count, and slide-by-slide flow for social-media carousels.
Why use it?
It provides a defined structure for turning a topic into an educational, story-based, comparison, or list-style post.

Command for Claude Code

Part of the badi plugin — 28 commands, 30 agents shipped together

Install

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.

agentmods
npx agentmods add commands/fatihkan/badi/content-carousel
Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Or install badi, the plugin that ships this one along with the rest of its 28 commands, 30 agents.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,037 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01037
Opus 5 $0.00000 $0.00518
Sonnet 5 $0.00000 $0.00207
Haiku 4.5 $0.00000 $0.00104

Measured 3d ago against content hash 69440e2f59ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content-carousel 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.

.claude/commands/content-carousel.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Carousel (multi-frame) content command. Produces educational or storytelling carousel content for Instagram, LinkedIn, and other platforms.

Required Tools

  • Read (brand voice, topic, previous content) -- Write (carousel file) -- Grep (related content) -- ...

Procedure (6 Steps)

  • Platform: Instagram / LinkedIn / Twitter (thread adaptation) / Facebook / Other
  • Topic: detail
  • Purpose: Educational (tips, steps) / Story (experience, customer) / List (X things, X reasons, X mistakes) / Comparison (A vs B, before/after) / ...
  • Frame Count: 5-10 (default 7)
  • Tone: Friendly / Professional / Fun / Inspirational / Technical
  • Visual Style: Clean/Minimalist (white space) / Colorful-Bold (vivid, large typography) / Photographic (photo + overlay) / Illustrative (drawings, icons) / ...

2. Flow Structures

Educational: Frame 1: COVER (attention + "Save!" CTA) | Frame 2: INTRO (problem/context) | Frames 3-N: CONTENT (1 tip per frame) | Last: SUMMARY + CTA (Follow/Save/Share)

Story: Frame 1: COVER (curiosity) | Frame 2: SETUP (situation/problem) | Frames 3-N: DEVELOPMENT | Last-1: OUTCOME (lesson) | Last: CTA ("Has it happened to you?")

List: Frame 1: COVER ("[Number] [topic]") | Frames 2-N: ITEMS (1-2 items/frame) | Last: BONUS + CTA (Save)

Comparison: Frame 1: COVER ("A vs B" / "Don't/Do") | Frames 2-N: left-right or before-after | Last: CONCLUSION + CTA

Q&A: Frame 1: COVER ("The X most-asked questions") | Frames 2-N: 1 question+answer per frame | Last: CTA ("DM me")

3. Per-Frame Content

  • Copy: Heading (short, punchy, max 8 words) -- Body (2-4 sentences or 3-5 bullets) -- Emphasis (bold/color) -- ...
  • Design: Background color/image -- text position (top/middle/bottom, left/right/center) -- font size hierarchy (heading>body>note) -- ...
  • Readability: Heading readable in 2s -- body in 5s -- text/background contrast -- ...

4. Visual Consistency

  • Consistent elements: same color palette (slight variation OK) -- same font family + hierarchy -- primary/secondary/accent color consistent -- ...
  • Swipe motivation: "But the most important one..." (cliffhanger) -- arrow markers (→/↓) -- page numbers -- ...

Read the full file on GitHub · 78 lines

Changes

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.

  1. 3d ago First seen · 78 lines · 0 tokens per session scan A 69440e2f59ec

Subscribe to this mod's changes

content-carousel is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,037 tokens. 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.