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/fused-render-authoringnpx skills add fusedio/fused-render --skill fused-render-authoringgit 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/fused-render-authoring)<a href="https://agentmods.dev/skills/fusedio/fused-render/fused-render-authoring"><img src="https://agentmods.dev/badge/skills/fusedio/fused-render/fused-render-authoring.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 | $0.00036 | $0.02783 |
| Opus 5 | $0.00018 | $0.01392 |
| Sonnet 5 | $0.00007 | $0.00557 |
| Haiku 4.5 | $0.00004 | $0.00278 |
Grade A, and why
fused-render-authoring 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 yesterday.
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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring fused-render views
View = sibling pair: .html (UI) + .py (data). Explorer renders html in iframe, injects window.fused (never <script src> runtime), page calls local Python via fused.runPython. UI state lives in URL params → refresh-proof, bookmarkable. Plain HTML/CSS/JS. No framework, no build step.
App markers (entry page <head>, first 4 KiB)
<meta name="fused-app" />
<meta name="fused-api-version" content="N" />
fused-app= ONLY thing making folder an app. No marker → never in /apps, never registered.fused-api-version: copy N fromfused_render/app_starter/index.html. Missing tag = version 0. Migration →fused-render-api-migration.- Optional
icon.svgbeside entry page = sidebar glyph + favicon →fused-render-app-icon.
Python side: main()
One plain fn main(**params). Rules:
- Annotate params — arrive as URL strings; annotations coerce (
limit: int,boolaccepts "true/1/yes/on"). Unannotated = raw string. - Default every param unless truly required.
- Return JSON-native only (dict/list/str/int/float/bool/None). DataFrame →
df.to_dict("records"); datetime/Decimal/numpy → cast. - Relative paths resolve beside
.py. - Fresh subprocess per call. No globals survive. Import cost paid every call (pandas ≈ 1 s). Killed at 60 s (
DEFAULT_TIMEOUT,fused_render/executor.py), no override. Longer work →fused-render-jobs. print()→ browser console as[python].
Available Python libraries
No pyproject.toml in folder → app interpreter: stdlib plus exactly this bundled set (authoritative: repo pyproject.toml — [bundled] extra, plus pyarrow/duckdb/httpx from core [project] deps). Prefer it — zero install.
- Data:
numpypandaspyarrowduckdbopenpyxlmsgpack - Images:
pillow - Documents:
python-pptxfpdf2(import name fpdf) - Network & cloud:
requestshttpxbotocoregoogle-auth - Logs:
drain3
Anything else needs folder pyproject.toml (project root only; add [tool.uv] package = false). Facts:
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.
- yesterday Changed · -313 lines · -68 tokens per session a45b8899c124
- 5d ago First seen · 470 lines · 104 tokens per session scan A decf3d7fbb11
fused-render-authoring is a skill published in the GitHub repository fusedio/fused-render (11 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 2,783 once invoked, about $0.0002 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
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.