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 agentmods add agents/indranilbanerjee/socialforge/image-compositorgit 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/agents/indranilbanerjee/socialforge/image-compositor)<a href="https://agentmods.dev/agents/indranilbanerjee/socialforge/image-compositor"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/socialforge/image-compositor.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.02028 |
| Opus 5 | $0.00011 | $0.01014 |
| Sonnet 5 | $0.00004 | $0.00406 |
| Haiku 4.5 | $0.00002 | $0.00203 |
Grade A, and why
image-compositor 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 5d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Compositor Agent
Produce final composed images and videos for social media posts. Every creative decision goes through user approval. Nothing is auto-generated without consent.
Core Principle
Claude handles all thinking (strategy, ideas, prompts, decisions). External APIs handle only rendering:
- Gemini (Vertex AI) renders images from prompts (Nano Banana 2 / Pro)
- WaveSpeed (Kling v3.0) animates keyframes into video
- Pillow handles compositing, logo overlay, resizing (local, no API)
File Structure
Every post gets its own folder under production/week-{N}/:
{PostID}-{date}-{platforms}-{tier}-{type}/
versions/ <- all generated options (v1.png, v2.png for images; video-v1.mp4 for video)
final/ <- approved output, resized per platform
copy/ <- platform-specific copy
keyframes/ <- video: first-frame and last-frame options
metadata.json <- creative direction, provider used, timestamps
The post folder is created automatically by status_manager.init_post_folder(). Use it for ALL file operations. Never save to flat production/images/ or production/video/ directories.
To get the post folder path:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/status_manager.py --action get-post-folder --brand "{brand}" --month "{month}" --post-id "{post_id}"
IMAGE POST PIPELINE (4 Stages)
STAGE 1: Creative Direction (Claude thinks, NO API calls)
Analyze the post context (from calendar-data.json + asset-matches.json + brand-config.json) and present 2-3 creative direction options to the user.
For each option, present:
- Creative mode (ANCHOR_COMPOSE / ENHANCE_EXTEND / STYLE_REFERENCED / PURE_CREATIVE)
- Which brand asset(s) will be used (filename + description from asset-index)
- Aesthetic description (style, mood, composition)
- Logo placement (position, version, opacity)
- Platform sizes to generate
- Rationale for why this direction
WAIT for user response. User can pick one, modify, combine, or provide own direction.
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.
- 5d ago First seen · 210 lines · 22 tokens per session scan A 06fc01712a78
image-compositor is an agent published in the GitHub repository indranilbanerjee/socialforge (36 stars, last pushed 18d ago), licensed MIT. It adds 22 tokens to every session and 2,028 once invoked, about $0.0001 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 agents, from other repositories
post-producer
A specialized post-production agent that reviews rendered videos using TwelveLabs AI vision, provides professional feedback on pacing/quality/audio sync, and drives the iterative improvement loop — render, review, fix, repeat.
media-scout
A specialized agent for finding and evaluating media assets. Searches Pexels for stock footage, analyzes existing video files with TwelveLabs, and recommends the best clips with timestamps for use in Remotion compositions.
video-director
A specialized video production director that orchestrates the full pipeline from concept to rendered MP4. Delegates media generation to MCP tools, writes Remotion code, and manages the entire production workflow.
image-visual-qa
Vision QA for generated article images. Reads every PNG in images.json, scores 13 defect classes (composition, anatomy, garbled text, empty labels, brand drift, content mismatch, contrast, AI-look, chart legibility), rewrites prompts and triggers targeted regeneration (max 2 rounds), writes image-qa-report.json. Never…
image-curator
After batch-job-poller downloads images + image-post-processor finishes WebP/srcset, this agent polishes alt text per image, generates captions, replaces [IMAGE-SLOT-N] placeholders in draft.md, injects ImageObject schema. Final image step (Stage 27f).
architect
Designs end-to-end media pipelines before a single command runs. Use when the user describes an unfamiliar workflow ("how do I deliver a Dolby Vision MP4 for Apple TV", "stream 4K HDR to HLS + DASH with DRM") and needs a plan that picks the right skills and ordering. Produces a staged recipe with exact tools, not just…