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 skills add indranilbanerjee/neels-plugins --skill create-previewsgit 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/skills/indranilbanerjee/neels-plugins/create-previews)<a href="https://agentmods.dev/skills/indranilbanerjee/neels-plugins/create-previews"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/create-previews/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/skills/indranilbanerjee/neels-plugins/create-previews"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/create-previews.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 | $0.00388 |
| Opus 5.5 | $0.00012 | $0.00155 |
| Sonnet 5.5 | $0.00006 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
create-previews 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.
What it actually says
/socialforge:create-previews — Preview Generator
Generate a preview card per platform (post copy, image, platform badge) to check copy, line breaks and crop before publishing. The card is one built-in layout with the platform named; it is not a replica of the platform's feed.
Execution gate
Rendering writes preview images under production/previews/. State the scope (posts x platforms, destination) and proceed only on an explicit yes; any other reply cancels with nothing written.
Process
- For each post × each platform:
- Load the generated/composed image
- Load the adapted copy
- Use the built-in card (or
assets/preview-templates/<platform>.htmlif you supplied one; none ship) - Inject: brand name and handle, platform badge, image and the post copy (hashtags included in the copy passed in)
- Render via Playwright → PNG preview
- Save to
production/previews/post-{id}-{platform}-preview.png
Layouts
One built-in card serves every platform. To get a platform-specific layout, put <platform>.html in assets/preview-templates/ using the placeholders {{name}}, {{handle}}, {{platform}}, {{image_uri}} and {{copy}}. No templates ship.
Timeout & Fallback
- Per preview: 10-second timeout. If Playwright hangs, save raw image + copy as fallback.
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.
- 2d ago First seen · 32 lines · 31 tokens per session scan A 1d8cc5f45167
create-previews is a skill published in the GitHub repository indranilbanerjee/neels-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 388 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-12.
Other skills, from other repositories
design-ops
Design operations and creative excellence for B2B SaaS marketing. Use this skill when building brand identity, designing landing pages, creating presentations, producing ad creative, or building infographics. Also triggers on: brand identity, landing page design, presentation, sales deck, ad creative, infographic…
continuous-improvement-loop
Run the Part 12 continuous improvement loop into a quarterly brief for leadership. "produce the quarterly improvement brief".
yearly-planner
Produce the Part 8 yearly planner: quarterly themes and monthly initiatives. "plan the whole year month by month".
attribution-report
Run attribution on real conversion paths, comparing models. "which channels actually drive revenue".
multilingual-score
Score translated content for publication: quality, brand voice, market compliance. "is this German translation ready to publish".
attribution-model
Design an attribution model and credit rules. Real path data → attribution-report. "set up multi-touch attribution".