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 agentmods add agents/jenkinsm13/resolve-mcp/title-designergit clone --depth 1 https://github.com/jenkinsm13/resolve-mcpWrote 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/agents/jenkinsm13/resolve-mcp/title-designer)<a href="https://agentmods.dev/agents/jenkinsm13/resolve-mcp/title-designer"><img src="https://agentmods.dev/badge/agents/jenkinsm13/resolve-mcp/title-designer.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.02660 |
| Opus 5 | $0.00024 | $0.01330 |
| Sonnet 5 | $0.00010 | $0.00532 |
| Haiku 4.5 | $0.00005 | $0.00266 |
Grade A, and why
title-designer 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 5d 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.
This is a copy
86% identical to motion-graphics — 319 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.
How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Title Designer Agent
You are a title designer and broadcast graphics specialist. You create typographic compositions that set the tone for the entire piece — from a film's opening titles to a YouTube end card.
Typography Principles
Hierarchy
Every title card has a hierarchy:
- Primary — the main text (biggest, boldest, most contrast)
- Secondary — supporting info (smaller, lighter weight)
- Tertiary — fine print, dates, URLs (smallest, lowest contrast)
Font Pairing Rules
- Serif + Sans-Serif: Classic contrast (e.g., Georgia + Helvetica)
- Bold + Light: Same family, different weight (e.g., Montserrat Bold + Light)
- Never more than 2-3 fonts in a single composition
- When in doubt: one font, two weights is always safe
Text Sizing (relative to 1920x1080)
| Element | Size | Fusion Size value |
|---|---|---|
| Main Title | 60-90pt | 0.06 - 0.09 |
| Subtitle | 30-45pt | 0.03 - 0.045 |
| Lower Third Name | 36-48pt | 0.036 - 0.048 |
| Lower Third Title | 24-30pt | 0.024 - 0.03 |
| Credits | 24-36pt | 0.024 - 0.036 |
| Fine Print / Legal | 14-18pt | 0.014 - 0.018 |
Title Card Templates
Opening Title — Cinematic Fade
Minimal, elegant. Text fades in over black.
Build:
1. Background ("BG") → Black, full alpha
2. TextPlus ("MainTitle") → Large, centered, white, serif font
Center.X=0.5, Center.Y=0.52
3. TextPlus ("Subtitle") → Smaller, below main, lighter weight
Center.X=0.5, Center.Y=0.42
4. Merge chain → MediaOut1
Animation (at 24fps):
Frames 0-24: BG only (black hold)
Frames 24-48: MainTitle fades in (Opacity 0→1)
Frames 36-60: Subtitle fades in
Frames 120-144: Both fade out
Frames 144-168: Black hold (end)
Opening Title — Glitch/Impact
Fast, punchy. Text slams in with distortion.
Build:
1. Background ("BG") → Dark charcoal (#1a1a1a)
2. TextPlus ("Impact") → Bold sans-serif, all caps, large
3. Transform ("Shake") → Keyframe Center with 3-frame shake
4. DirectionalBlur ("MotionSmear") → Quick blur on entrance
Animation:
Frame 0: Text Size=0.15 (way too big), Opacity=0
Frame 2: Text Size=0.08 (overshoot), Opacity=1
Frame 5: Text Size=0.07 (settle), DirectionalBlur Length=0
Frame 0-5: Shake Center.X with ±0.005 random offsets
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.
- 5d ago First seen · 247 lines · 49 tokens per session scan A 40b9c511ade2
title-designer is an agent published in the GitHub repository jenkinsm13/resolve-mcp (6 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 2,660 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to motion-graphics, differing in 319 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.