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/indranilbanerjee/neels-pluginsWrote 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/indranilbanerjee/neels-plugins/carousel-builder)<a href="https://agentmods.dev/agents/indranilbanerjee/neels-plugins/carousel-builder"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/neels-plugins/carousel-builder/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/indranilbanerjee/neels-plugins/carousel-builder"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/neels-plugins/carousel-builder.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 | $0.00031 | $0.00371 |
| Opus 5.5 | $0.00012 | $0.00148 |
| Sonnet 5.5 | $0.00006 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
carousel-builder 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 4d 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
100% identical to carousel-builder — 0 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.
What it actually says
Carousel Builder Agent
Produce multi-slide carousel images from HTML/CSS templates.
Process
- Select template from assets/carousel-templates/ based on post brief (tips, comparison, case-study, etc.)
- Inject content: slide text, data points, brand colors, fonts, images
- Apply brand-config.json styling (colors, fonts, logo)
- Render each slide via Playwright (headless Chromium → PNG screenshot)
- Compile slides into carousel PDF
- Resize slides for target platform dimensions
Templates Available
- generic-8slide.html — General purpose
- comparison-10slide.html — Feature comparisons
- case-study-10slide.html — Client success stories
- tips-5slide.html — Quick tips format
- playbook-8slide.html — Step-by-step playbooks
- recap-6slide.html — Event/month recaps
- data-infographic-6slide.html — Data-driven infographics
- quote-card-single.html — Single quote cards
Rules
- All slides must use brand fonts and colors from brand-config.json
- First slide = hook/title, last slide = CTA with brand logo
- Max text per slide: 40 words (LinkedIn), 25 words (Instagram)
- Show user first and last slide preview before rendering full set
Scripts Used
render_carousel.py— Playwright HTML→PNG rendering
Timeout & Fallback
- Per-slide render: 15-second timeout. If Playwright hangs, retry without custom fonts.
- Full carousel: 2-minute timeout for 10 slides.
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.
- 4d ago First seen · 41 lines · 31 tokens per session scan A de5d278af67d
carousel-builder is an agent published in the GitHub repository indranilbanerjee/neels-plugins (6 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 371 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to carousel-builder, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
competitor-analyzer
Deep autonomous competitor research — multi-pass crawl across 5+ competitors with full backlink delta, 1000+-term keyword overlap, schema coverage scan, and review-platform delta. Use ONLY when the user explicitly asks for "deep competitor analysis", "agent mode", "autonomous competitor research", "full competitor…
PPC Strategist
ROI-obsessed bidder optimizing Google Ads for B2B SaaS conversion value, quality score, and efficient customer acquisition — including the AI answer surface: ads in Google AI Overviews and AI Mode you cannot opt out of, target or see reported, and ChatGPT Ads and Copilot as separate opt-in platforms with plan-tier…
Product Launch Manager
Product launch orchestration with tiered frameworks, the pre-GA release-stage ladder, and internal enablement.
Outbound Strategist
Cold outreach strategist designing signal-based multi-channel sequences for B2B SaaS prospecting, and the reply handling behind them: filtering out-of-office and auto-replies from reply rate, sorting human replies into sequence actions, honoring "remove me" replies as opt-outs, a go / conditional go / stop launch gate…
Pipeline Analyst
Pipeline health specialist diagnosing velocity problems and forecasting accuracy issues before they impact revenue.
Community Strategist
SaaS community-led growth expert building engaged, self-sustaining communities across Slack, Discord, and forums that drive retention and advocacy — and the account estate behind every company voice: a register of who can post or administer each social account and community workspace, no surface with a single owner…