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 skills/fusedio/fused-render/changing-suggested-modelsnpx skills add fusedio/fused-render --skill changing-suggested-modelsgit clone --depth 1 https://github.com/fusedio/fused-renderWrote 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/fusedio/fused-render/changing-suggested-models)<a href="https://agentmods.dev/skills/fusedio/fused-render/changing-suggested-models"><img src="https://agentmods.dev/badge/skills/fusedio/fused-render/changing-suggested-models.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 | $0.00074 | $0.02594 |
| Opus 5 | $0.00037 | $0.01297 |
| Sonnet 5 | $0.00015 | $0.00519 |
| Haiku 4.5 | $0.00007 | $0.00259 |
Grade A, and why
changing-suggested-models scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -i https://render.fused.io/mirror/models/<org>/<name>/manifest.json How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Changing Suggested Models
Overview
fused_render/ai/catalog.py's SUGGESTIONS table is the curated list the AI Models page shows per runner. Editing that table is only half the change. The other half is scripts/build_model_mirror.py, which publishes the model to our own CloudFront/S3 mirror (SPEC AI-5l/AI-5m). Skip it and the model still works — every download falls back to huggingface.co — but silently: the whole point of the mirror is that CloudFront's access logs are the only telemetry this app has for "did a user download a model" (D421), and a suggested model with no mirror objects is invisible to those logs forever, with nothing on screen to say so.
The invariant that matters: every id in catalog.all_suggested_ids() should have a manifest on the mirror — FUSED_MODEL_MIRROR ships ON by default (mirror.DEFAULT_BASE, https://render.fused.io/mirror), so an unpublished suggested model is not hypothetical, it 404s against the live distribution today and falls back to the Hub, invisibly. scripts/build_model_mirror.py --check <base-url> is what proves a target is actually published, and it is meant to gate a release the same way making-a-release's steps gate a version bump.
Step 1 — find the row, and get its id shape right
The curated lists live in fused_render/ai/catalog.py's SUGGESTIONS dict, keyed by runner code (mlx-text, llamacpp-text, diffusers-image, mflux-image, mlx-whisper, faster-whisper). Every list is sorted smallest size_gb first — position 0 is also default_for()'s answer — so insert the new row at the size-sorted position, not at the end.
Read the id before writing anything else. There are exactly two shapes:
- Every runner except
llamacpp-text: theidfield is a plain Hub repo id,org/name(e.g.mlx-community/Qwen3.5-4B-OptiQ-4bit). llamacpp-text: theidfield is a bare.gguffilename (e.g.Qwen3.5-4B-Q4_K_M.gguf), not a repo id. One GGUF repo publishes dozens of quantizations, so the page keys the curation by file, and the filename maps to a repo throughfused_render/ai/runners/formats.py'sGGUF_RECIPES:
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 · 113 lines · 74 tokens per session scan A 0ce682dd96ff
changing-suggested-models is a skill published in the GitHub repository fusedio/fused-render (11 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 2,594 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.