social-media-graphics

social-media-graphics is an agent for Claude Code from jenkinsm13/resolve-mcp. It costs 72 tokens per session (3,905 once invoked), scanned A, a copy of motion-graphics, MIT.

A DaVinci Resolve Fusion graphics specialist for vertical short videos on Instagram Reels, TikTok, YouTube Shorts, and Stories. It creates elements such as hook text, captions, calls to action, countdowns, and motion graphics.

In plain words
What is it for?
Use it to design 9:16 graphics for short-form social videos, including opening hooks, captions, calls to action, and platform-style overlays.
Why use it?
It helps keep text readable and positioned away from platform controls that cover the top and bottom of vertical videos.

Agent for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Part of the resolve-mcp plugin — 16 skills, 25 agents, 2 hooks, 1 MCP server shipped together

Good fit Use it to design 9:16 graphics for short-form social videos, including opening hooks, captions, calls to action, and platform-style overlays.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jenkinsm13/resolve-mcp/social-media-graphics
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.

Clone the repo
git clone --depth 1 https://github.com/jenkinsm13/resolve-mcp

Made for: Claude Code.

Or install resolve-mcp, the plugin that ships this one along with the rest of its 16 skills, 25 agents, 2 hooks, 1 MCP server.

Wrote 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.

agentmods badge for social-media-graphics

README.md
[![agentmods](https://agentmods.dev/badge/agents/jenkinsm13/resolve-mcp/social-media-graphics/github.svg)](https://agentmods.dev/agents/jenkinsm13/resolve-mcp/social-media-graphics)
Your own site
<a href="https://agentmods.dev/agents/jenkinsm13/resolve-mcp/social-media-graphics"><img src="https://agentmods.dev/badge/agents/jenkinsm13/resolve-mcp/social-media-graphics/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.

agentmods 80×15 button for social-media-graphics

Your own site · 80×15
<a href="https://agentmods.dev/agents/jenkinsm13/resolve-mcp/social-media-graphics"><img src="https://agentmods.dev/badge/agents/jenkinsm13/resolve-mcp/social-media-graphics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,905 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 88% copy Near-identical to another mod 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 5.1 $0.00072 $0.03905
Opus 5 $0.00036 $0.01953
Sonnet 5 $0.00014 $0.00781
Haiku 4.5 $0.00007 $0.00391

Measured 10d ago against content hash 106ea67dbc73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

social-media-graphics 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 10d 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.

Origin

This is a copy

88% identical to motion-graphics — 458 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agents/social-media-graphics.md · 398 lines

How it starts

The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Social Media Graphics Agent

You build Fusion-page graphics for short-form vertical content — Instagram Reels, TikTok, YouTube Shorts, and Stories. Every element must be designed for 9:16 vertical, thumb-stopping on a phone screen, and readable at small sizes. You work in parallel with the social-media-editor agent.

Vertical Design Space (1080x1920)

┌──────────────────┐
│   SAFE ZONE TOP  │ ← Platform UI (username, follow button)
│   (top 15%)      │    Keep clear: Y > 0.85
│──────────────────│
│                  │
│   HOOK TEXT      │ ← First 3 seconds, large bold text
│   (upper third)  │    Center.Y = 0.70
│                  │
│──────────────────│
│                  │
│   MAIN CONTENT   │ ← Subject/action
│   (center)       │    Center.Y = 0.50
│                  │
│──────────────────│
│                  │
│   CTA / CAPTION  │ ← Call to action, captions
│   (lower third)  │    Center.Y = 0.25
│                  │
│──────────────────│
│   SAFE ZONE BOT  │ ← Platform UI (comments, share, like)
│   (bottom 10%)   │    Keep clear: Y < 0.10
└──────────────────┘

CRITICAL: All text must avoid top 15% and bottom 10%.
Platform UI overlays cover these areas on every platform.

Core Graphics Kit

1. Hook Text (First 3 Seconds)

The most important graphic — determines if the viewer stops scrolling.

Bold, center-screen text that grabs attention immediately:

  1. resolve_fusion_add_tool("TextPlus", "Hook_Line1")
     → StyledText = "YOU WON'T", Size = 0.09, Bold
     → White, black outline (Width = 0.015)
     → Center.X = 0.5, Center.Y = 0.72

  2. resolve_fusion_add_tool("TextPlus", "Hook_Line2")
     → StyledText = "BELIEVE THIS", Size = 0.11, Bold
     → Accent color (yellow/red), black outline
     → Center.X = 0.5, Center.Y = 0.62

  3. resolve_fusion_add_tool("Background", "Hook_Shadow")
     → Black, Alpha = 0.4
     → Full width band behind text for readability

  Animate:
    Frame 0: Hook_Line1 Scale = 0
    Frame 3: Hook_Line1 Scale = 1.15 (pop overshoot)
    Frame 5: Hook_Line1 Scale = 1.0 (settle)
    Frame 4: Hook_Line2 Scale = 0
    Frame 7: Hook_Line2 Scale = 1.15
    Frame 9: Hook_Line2 Scale = 1.0

  Total duration: 2-3 seconds, then fade out or cut away.

Read the full file on GitHub · 398 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. 10d ago First seen · 398 lines · 72 tokens per session scan A 106ea67dbc73

Subscribe to this mod's changes

social-media-graphics is an agent published in the GitHub repository jenkinsm13/resolve-mcp (6 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 3,905 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to motion-graphics, differing in 458 lines, and is treated as a copy.

Related

Other agents, from other repositories

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

proposal-writer

Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.

Zeekeey-jpeg/LeRoy-HQ · 34 tokens

cover-artist

Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.

howells/fiction · 38 tokens

ollama-vision

Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.

PratikHotchandani22/claude-ollama-agents · 59 tokens

forge-modeler

Headless 3D geometry specialist for the Forge suite. Builds, repairs, and validates polygon meshes, parametric CAD (CadQuery/Build123d/OpenSCAD), and procedural geometry (Geometry Nodes, SDF, L-systems) via Python — no GUI. Use for mesh construction, parametric modeling, procedural generation, topology/retopo/LOD…

luminary19/atelier · 126 tokens

gds-agent-game-designer

Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.

PabloLION/bmad-plugin · 38 tokens