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 generate-videogit 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/generate-video)<a href="https://agentmods.dev/skills/indranilbanerjee/socialforge/generate-video"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/socialforge/generate-video/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/generate-video"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/socialforge/generate-video.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 | $0.00113 | $0.01710 |
| Opus 5 | $0.00056 | $0.00855 |
| Sonnet 5 | $0.00023 | $0.00342 |
| Haiku 4.5 | $0.00011 | $0.00171 |
Grade A, and why
generate-video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/socialforge:generate-video — Video Production Kit
Generate video production assets through a 5-stage human-in-the-loop pipeline. Each stage requires user approval before advancing.
Context efficiency
Asset-heavy skill. Grep before Read the asset catalog (${CLAUDE_PLUGIN_DATA}/socialforge/brands/<brand>/asset-index.json) — never list the asset directory. Reference generated images / videos by path, not by loading metadata. Brand profile loads once per session.
Prerequisites
- Credentials must be configured via
/socialforge:setup:- Vertex AI (Nano Banana Pro / Gemini 3 Pro Image, resolved via
latest-image-google) — used for first-frame and last-frame keyframe generation - WaveSpeed API — used for image-to-video generation via Kling v3.0 Pro
- Vertex AI (Nano Banana Pro / Gemini 3 Pro Image, resolved via
- Brand profile must be active (
/socialforge:switch-brandif needed) - Calendar must be parsed (
/socialforge:parse-calendar) with video posts identified
The 5-Stage Pipeline
Stage 1: Video Concept + Script (no API call)
Claude generates 2-3 video concept ideas based on the post brief, brand voice, and platform requirements. Each concept includes:
- Working title and hook
- Visual narrative arc (opening, middle, close)
- Suggested duration and pacing
- Tone and style direction
The user picks one concept (or requests refinements). Then fill the script
scaffold (generate_script in generate_video.py) from the chosen concept and
the post's actual brief, in the brand's voice — every [FILL] replaced, no
placeholder survives into Stage 2. The scaffold enforces the structure; this
pass supplies the craft, under four rules the scaffold carries with it:
- Hook first, never the logo. The open earns attention with the single most arresting thing the brief supports; the brand mark lives as the corner watermark and in the end card. Three seconds of logo reveal is the classic retention killer this pipeline used to scaffold by default.
- Payoff per scene. Every scene's
payofffield states what the viewer has gained by the time it ends. A beat that only sets up the next beat is where viewers leave — give it a payoff or fold it. - The pairing rule. The hook's text overlay and the post's caption (written by adapt-copy) do different jobs and never echo. Check against the adapted copy if it already exists for this post.
- Compliance before credits. Run the filled script's narration and
overlay text through
compliance_check.pyBEFORE Stage 2 — a banned phrase caught in a script costs nothing; caught in a rendered video it costs the whole generation chain. Claims in narration follow the same rules as claims in copy: sourced or absent.
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.
- 10d ago First seen · 130 lines · 113 tokens per session scan A f43fc0ffab71
generate-video is a skill published in the GitHub repository indranilbanerjee/socialforge (37 stars, last pushed 23d ago), licensed MIT. It adds 113 tokens to every session and 1,710 once invoked, about $0.0006 per session on Opus 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.
demo-shorts
Cut a vertical 9:16 Short (YouTube Shorts, Instagram Reels, TikTok) from a demo video project in one of four named styles — listicle (rapid numbered beats), cohost (split screen with presenter), flashcard (typographic interstitials), or glide (immersive pan). Use when the user asks for a "short", "shorts", "vertical…
demo-script
Writing the script and shot list for a demo video, and the demo.json manifest schema. Use when planning what a product video should say and show, writing voiceover narration, structuring scenes, or editing demo.json.
demo-assembly
Assembling and rendering a demo video with Remotion and ffmpeg — the timeline, transitions, captions, zoom-to-click, audio ducking, and diagnosing a render that comes out wrong. Use when rendering the final video, customising its look, or fixing timing, black frames or missing audio.
demo-capture
Craft and mechanics of capturing software on screen for a demo video — rehearsing a flow, staging a window, the action-script format, pacing to narration, and macOS permissions and coordinates. Use when recording an app, driving a UI for a video, debugging a capture that looks wrong, or when clicks land in the wrong…
higgsfield-comic-to-video
Animates comic panels, manga pages, webtoons, illustrated storyboards, and sequential art into video using Higgsfield. Routes to wan26 (primary, I2V — image required) or seedance20 (fallback). Use when the user wants to animate comics, bring illustrations to life, convert manga to video, animate storyboards, or create…