Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add indranilbanerjee/socialforge/plugin install 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/model-check)<a href="https://agentmods.dev/skills/indranilbanerjee/socialforge/model-check"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/socialforge/model-check.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 5.1 | $0.00104 | $0.01127 |
| Opus 5 | $0.00052 | $0.00563 |
| Sonnet 5 | $0.00021 | $0.00225 |
| Haiku 4.5 | $0.00010 | $0.00113 |
Grade A, and why
model-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/socialforge:model-check — which model to call, decided today
SocialForge does not know which model to use. That is deliberate.
A model id written into a plugin is a claim about the day it was written, and this plugin gets run long after that day. Six ids used to sit on the execution path. One video fallback stayed pinned to a superseded generation for about six months, and nothing in the system could say so — which matters because a retired id does not degrade gracefully. It fails at the exact moment the two providers ahead of it have already failed and the fallback is all that is left.
So the code asks for a kind of model. You find out what currently satisfies it.
The rule
Never supply a model id from memory. Not from this file, not from a recipe,
not from what a model was called last time you looked. If model_book.py says
unknown or stale, go and read the provider's catalogue.
What the code asks for
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/model_book.py" --action kinds
Capabilities, not products — video.image-to-video, not a version number. A kind
outlives every model that has ever satisfied it, which is the entire point.
Finding the current best
- See where to look, and what is odd about each provider:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/model_book.py" --action discovery
Two things it will tell you that save time: Higgsfield puts the model in the URL path (so a hardcoded path is a hardcoded model), and Kie AI blocks automated fetches — HTTP 403, measured. Do not report that as "no model exists"; ask the user.
-
Read the provider's model list with your own web tools. This is a plugin — there is no crawler and no server, which is why the answer is as fresh as your last look rather than as old as the last release.
-
Judge what is actually best for the kind, not what is newest or loudest. A reference-heavy brief and a prompt-driven cinematic brief are different jobs, and the model that wins one often loses the other. Check what the brief needs: start-frame support, duration ceiling, reference-image count, whether audio is required.
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.
- 8d ago First seen · 108 lines · 104 tokens per session scan A 4dfe4be1cad5
model-check is a skill published in the GitHub repository indranilbanerjee/socialforge (36 stars, last pushed 21d ago), licensed MIT. It adds 104 tokens to every session and 1,127 once invoked, about $0.0005 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
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…
postgres-hybrid-text-search
Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Trigger when user asks to: Combine keyword and semantic search Implement hybrid search or multi-modal retrieval Use BM25/pgtextsearch with pgvector together Implement RRF (Reciprocal…
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.
prompt-engineering
ComfyUI prompt engineering knowledge covering CLIP text encoding syntax, weight modifiers, model-specific prompting strategies, and best practices.
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
higgsfield-seedance
Rewrites scene descriptions using professional cinematography language, structures prompts with a six-slot formula (camera + subject + action + setting + style + lighting), and diagnoses content filter rejections via a preflight linter. Use whenever the user asks for a Seedance 2.0 / Seedance Pro prompt, describes a…