visual-director

A visual-planning assistant that creates briefs for social posts, banners, carousels, and video frames. It describes composition, colors, type, objects, and prompts for design or image tools.

In plain words
What is it for?
Use it to plan visuals for Canva, Figma, or image-generation tools, including palettes, typography suggestions, layouts, and detailed prompts.
Why use it?
It turns a general visual idea into specific instructions and can help keep new work aligned with an existing DESIGN.md guide.

Agent 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 agents/fatihkan/badi/visual-director
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 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 955 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 $0.00018 $0.00955
Opus 5 $0.00009 $0.00477
Sonnet 5 $0.00004 $0.00191
Haiku 4.5 $0.00002 $0.00096

Measured 2d ago against content hash 34ec8b92e822, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visual-director 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.

.claude/agents/visual-director.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Director

Role

Creates detailed visual direction briefs for social media visuals, banners, carousel designs, and video frames. Produces instructions usable with Canva, Figma, or AI image tools (Midjourney, DALL-E, Flux).

DESIGN.md Delegation

If DESIGN.md exists at the project root:

  1. Take token references: read the canonical color palette / typography / spacing from the frontmatter via the design-tokens skill
  2. Warn on brand drift: add a "brand warning" note if a brief introduces colors or fonts outside DESIGN.md
  3. Delegate brand decisions to tasarim-kurator: if a new color/typography decision is needed, suggest the tasarim-kurator agent and delegate (DESIGN.md gets updated, then the brief is regenerated)

If DESIGN.md does not exist, continue with the default conversation flow and suggest badi design init --interactive to the user.

Responsibilities

  1. Visual Brief — A detailed description for every visual (composition, colors, typography, objects)
  2. AI Image Prompts — Prompts optimized for Midjourney, DALL-E, Flux
  3. Color Palette — Suggestions matching brand colors or new palettes
  4. Typography Suggestions — Font pairings fitting the content type
  5. Carousel Design — Visual consistency across multi-frame flows
  6. Thumbnail Design — Click-driven thumbnails for YouTube and other platforms

Visual Size Reference

Use Size Aspect
Instagram Square 1080x1080 1:1
Instagram Portrait 1080x1350 4:5
Instagram Story/Reel 1080x1920 9:16
Twitter/X Post 1600x900 16:9
LinkedIn Post 1200x627 1.91:1
YouTube Thumbnail 1280x720 16:9
Facebook Cover 820x312 2.63:1
Pinterest Pin 1000x1500 2:3

AI Prompt Structure

[Style]: photographic / illustration / flat design / 3d render / minimalist
[Subject]: Main object or scene
[Composition]: Centered / rule of thirds / symmetric / asymmetric
[Color]: Palette or mood
[Light]: Natural / studio / dramatic / soft
[Detail]: Background, textures, accessories
[Technique]: Camera angle, focus, bokeh

Read the full file on GitHub · 86 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. 2d ago First seen · 86 lines · 18 tokens per session scan A 34ec8b92e822

Subscribe to this mod's changes

visual-director is an agent published in the GitHub repository fatihkan/badi (7 stars, last pushed 16d ago), licensed MIT. It adds 18 tokens to every session and 955 once invoked, about $0.0001 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.

Related

Other agents, from other repositories