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/socialforge --skill build-review-gallerygit clone --depth 1 https://github.com/indranilbanerjee/socialforgeWrote 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/socialforge/build-review-gallery)<a href="https://agentmods.dev/skills/indranilbanerjee/socialforge/build-review-gallery"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/socialforge/build-review-gallery/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/socialforge/build-review-gallery"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/socialforge/build-review-gallery.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 | $0.00027 | $0.00777 |
| Opus 5.5 | $0.00011 | $0.00311 |
| Sonnet 5.5 | $0.00005 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
build-review-gallery 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 27d 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/socialforge:build-review-gallery — Review Gallery Builder
Build a self-contained HTML gallery showing every post in the month with its generated visual, metadata, and a copy excerpt.
Process
- Load calendar-data.json and status-tracker.json for the brand + month
- For each post, locate the generated image, video (plus any alternative cut), and copy file
- Build the gallery HTML —
build_gallery.pygenerates the markup inline; it does not read a template file - Embed images and videos as base64 data URIs so the file is self-contained
- Save to
${CLAUDE_PLUGIN_DATA}/socialforge/output/{brand}/{month}/review/gallery.html(falls back to~/socialforge-workspace/output/...when${CLAUDE_PLUGIN_DATA}is unset)
Step 6 (optional) — Offer a hosted copy for review
The local gallery.html is built first, always. It is the fallback and the source of truth; nothing below replaces it.
build_gallery.py reports size_bytes, size_mb and publishable_as_page (true only when the file is 15 MB or smaller, a conservative ceiling for a hosted page). After the local file exists:
- If this session has a tool that publishes an HTML page (for example an artifact or page-publishing tool) and
publishable_as_pageis true, offer to publish the gallery as a private page for review. Say in the offer that publishing uploads the month's creative and copy to a hosted service. Publish only on the user's explicit yes, and publish the file atoutput, unchanged. - Choose the private option wherever the tool has one. Never say or imply the page is shared with anyone: sharing is a separate step that is the user's to take. Give them the link and stop there.
- If
publishable_as_pageis false, say so in one line and use the result'snote: inlined video is what makes a gallery too large. Offerbuild_gallery.py --brand <name> --month <YYYY-MM> --no-inline-video, which links videos by relative path and keeps the file small. A published copy of that build shows images and copy but cannot play the linked videos — say that before offering it. - If no tool that publishes a page exists, say so in one line and give the local path. Do not suggest a hosting service.
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.
- 27d ago Changed · -63 tokens per session 1e5e525c90a5
- 1mo ago Changed · +11 lines 618c44edaeb3
- 2mo ago First seen · 28 lines · 90 tokens per session scan A b51f717a9b5e
build-review-gallery is a skill published in the GitHub repository indranilbanerjee/socialforge (43 stars, last pushed 6d ago), licensed MIT. It adds 27 tokens to every session and 777 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 2026-08-30.
Other skills, from other repositories
ai-media-generator
A workflow for turning ideas into prompts for AI-generated images, videos, and music across several media platforms. When needed, it can also send those prompts to the chosen platform through browser automation.
create-short
Create a short-form vertical video (TikTok, Instagram Reels, YouTube Shorts). Optimized 9:16 pipeline with a live Studio preview, auto-captions, hook-first structure, and background music mood selection; renders to MP4 only when you ask.
create-video
Full video production pipeline — from a text prompt to a live Studio preview with voiceover, music, sound effects, stock footage, and motion graphics, rendered to MP4 when you ask. The flagship command of Remotion Superpowers.
review-video
Review a Remotion video with AI vision. Starts with a cheap local check of rendered still frames, then has TwelveLabs watch the full render and score it against a JSON rubric (pacing, composition, text legibility, audio sync and more) with timestamped fixes, applies the fixes and re-reviews. The feedback loop that…
add-captions
Add TikTok-style, karaoke, YouTube or minimal captions to your Remotion video. Gets word-level captions through the official remotion-captions flow (whisper-webgpu, or ElevenLabs Scribe via @remotion/elevenlabs when there's no GPU), or imports the user's SRT with parseSrt, places one official caption element per clip…
analyze-footage
Analyze existing video files with TwelveLabs AI. Get a timestamped scene map of your footage, ask questions about it, find specific moments across a library, and get the best clips with timestamps for Remotion.