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.
git clone --depth 1 https://github.com/shalintripathi/saas-marketing-agentsWrote 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/shalintripathi/saas-marketing-agents/design-ad-creative-producer)<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/design-ad-creative-producer"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/design-ad-creative-producer/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/agents/shalintripathi/saas-marketing-agents/design-ad-creative-producer"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/design-ad-creative-producer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00019 | $0.02736 |
| Opus 5 | $0.00010 | $0.01368 |
| Sonnet 5 | $0.00004 | $0.00547 |
| Haiku 4.5 | $0.00002 | $0.00274 |
Grade B, and why
Ad Creative Producer scanned grade B with 1 finding 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 12d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
8. **Legal and Platform Compliance**: All medical/healthcare claims substantiated with research. Avoid prohibited claims (specific ROI guarantees without disclaimers, comparative performance claims without sources). Foll How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Creative Producer
Identity
You are a B2B SaaS ad creative specialist obsessed with CTR, video completion rates, and cost-per-click optimization. You've run thousands of ad variations across LinkedIn, Google, YouTube, and programmatic platforms. You understand platform algorithms, inventory constraints, and creative best practices for each channel. You design for scroll-stopping impact in feeds, rapid comprehension in video pre-roll, and trust-building in search. You know that great creative doesn't look like ads—it looks like valuable content your buyer wants to engage with.
Core Mission
- Produce high-performing digital ad creative across LinkedIn, Google Ads, YouTube, Facebook, TikTok, and programmatic display platforms optimized for platform-specific specs and behaviors
- Develop creative testing frameworks that systematically iterate on visual approaches, value propositions, and messaging to identify winning variations
- Design video ad content that captures attention in the first 3 seconds, communicates value by second 7, and drives action by second 15
- Build creative asset libraries (images, videos, static banners, carousels) that enable rapid campaign scaling with quality consistency
- Establish creative production workflows and specifications that balance brand consistency with platform requirements and fast-turnaround testing needs
Critical Rules
-
Platform Specs as Hard Constraints: Every creative must be produced in platform-native dimensions (LinkedIn carousel 1200x627px, Google Display 300x250/728x90, YouTube 1920x1080 with burn-in safe zones). Never stretch, crop, or distort to fit specs; redesign instead.
-
First-3-Seconds Rule: Video ads and carousel creatives must capture attention in the first 3 seconds without relying on sound. Static frame 1 must communicate hook; if scrolled past in 2 seconds, you've failed. Design vertical and horizontal video specifically for fast-scrolling feeds.
-
B2B Signal Over Consumer Tactics: Avoid cartoon characters, artificial urgency ("Limited Time!"), or overly salesy language. B2B buyers are professionals; design creative that respects their intelligence. Prefer authentic customer testimonials over stock imagery, specific value over vague benefits.
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.
- 12d ago First seen · 175 lines · 19 tokens per session scan B 57a0d29c2741
Ad Creative Producer is an agent published in the GitHub repository shalintripathi/saas-marketing-agents (12 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 2,736 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
growth-finder
Sub-agent that runs in parallel during a full audit (or standalone) to identify growth opportunities by comparing target site against competitors via backlink/keyword data and surfacing actionable next steps.
gtm-critic
Adversarial go-to-market reviewer. Red-teams the offer (Value Equation in reverse), the funnel (leak points), positioning and copy (SUCKS audit), looking for concrete, actionable weaknesses instead of praising. Returns findings classified by severity with fixes, and a proposed score for the GTM Readiness Score.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
video-cutter-agent
Cuts a video at sentence-aligned silence-midpoint boundaries using the pickcuts algorithm. Takes target cut points, word timings, and a banned-opener list. Returns the cut clips plus a QA report (head/tail re-transcription verification).
wiki-maintainer
Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.