gradio: Skill for Claude Code

.agents/skills/hf-gradio/SKILL.md

hf-gradio is a skill for Claude Code, Codex from gradio-app/gradio. It costs 55 tokens per session (704 once invoked), scanned A, original, Apache-2.0.

A command-line tool for calling Gradio applications, which are browser-based Python apps, through an API. It can inspect an app's available endpoints and send prediction requests to them.

In plain words
What is it for?
Use it to inspect a Gradio or Hugging Face Space app and submit inputs to its prediction endpoints.
Why use it?
It removes guesswork about an app's request format by showing its parameters and return values first. This lets you use public Gradio apps from scripts or the terminal.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is gradio-app/gradio's own configuration. It tells Claude Code and Codex how to work on gradio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gradio configures →

About the project

Gradio is a Python package for building web interfaces around machine learning models, APIs, or ordinary Python functions. It is used by developers and data scientists to create and share interactive demos without writing frontend code.

gradio-app/gradio · 43,523 stars · on GitHub · gradio.app

Reuse

Borrowing it

Nothing to install: this file belongs to gradio-app/gradio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gradio-app/gradio/main/.agents/skills/hf-gradio/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/gradio-app/gradio

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for hf-gradio

README.md
[![agentmods](https://agentmods.dev/badge/skills/gradio-app/gradio/hf-gradio/github.svg)](https://agentmods.dev/skills/gradio-app/gradio/hf-gradio)
Your own site
<a href="https://agentmods.dev/skills/gradio-app/gradio/hf-gradio"><img src="https://agentmods.dev/badge/skills/gradio-app/gradio/hf-gradio/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.

agentmods 80×15 button for hf-gradio

Your own site · 80×15
<a href="https://agentmods.dev/skills/gradio-app/gradio/hf-gradio"><img src="https://agentmods.dev/badge/skills/gradio-app/gradio/hf-gradio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 704 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Snyk warn 7 Sept 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.00704
Opus 5 $0.00028 $0.00352
Sonnet 5 $0.00011 $0.00141
Haiku 4.5 $0.00006 $0.00070

Measured 12d ago against content hash 2be3bc11a452, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hf-gradio 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 12d 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.

.agents/skills/hf-gradio/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hf-gradio CLI Skill

The hf-gradio CLI gradio CLI includes info and predict commands for interacting with Gradio apps programmatically.

Step 1 - Verify installation

Verify that either hf-gradio or gradio are installed in the current virtual environment.

If the hf CLI app is installed. The hf-gradio extension can be installed via

hf extensions install gradio-app/hf-gradio

Step 2 - Use info to discover endpoints and payload format

gradio info <space_id_or_url>
hf-gradio info <space_id_or_url>
hf gradio info <space_id_or_url>

Returns a JSON payload describing all endpoints, their parameters (with types and defaults), and return values.

gradio info gradio/calculator
#    {
#   "/predict": {
#     "parameters": [
#       {"name": "num1", "required": true, "default": null, "type": {"type": "number"}},
#       {"name": "operation", "required": true, "default": null, "type": {"enum": ["add", "subtract", "multiply", "divide"], "type": "string"}},
#       {"name": "num2", "required": true, "default": null, "type": {"type": "number"}}
#     ],
#     "returns": [{"name": "output", "type": {"type": "number"}}],
#     "description": ""
#   }
# }

File-type parameters show "type": "filepath" with instructions to include "meta": {"_type": "gradio.FileData"} — this signals the file will be uploaded to the remote server.

Step 3 - Use predict to generate the prediction

gradio predict <space_id_or_url> <endpoint> <json_payload>
hf-gradio predict <space_id_or_url> <endpoint> <json_payload>
hf gradio predict <space_id_or_url> <endpoint> <json_payload>

Returns a JSON object with named output keys.

# Simple numeric prediction
gradio predict gradio/calculator /predict '{"num1": 5, "operation": "multiply", "num2": 3}'
# {"output": 15}

# Image generation
gradio predict black-forest-labs/FLUX.2-dev /infer '{"prompt": "A majestic dragon"}'
# {"Result": "/tmp/gradio/.../image.webp", "Seed": 1117868604}

# File upload (must include meta key)
gradio predict gradio/image_mod /predict '{"image": {"path": "/path/to/image.png", "meta": {"_type": "gradio.FileData"}}}'
# {"output": "/tmp/gradio/.../output.png"}

Read the full file on GitHub · 83 lines

Changes

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.

  1. 12d ago First seen · 83 lines · 55 tokens per session scan A 2be3bc11a452

Subscribe to this mod's changes

hf-gradio is a skill published in the GitHub repository gradio-app/gradio (43,523 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 704 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

marimo-pair

Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.

marimo-team/marimo · 57 tokens

fill-model-descriptions

Fill missing and refresh obsolete model descriptions in packages/llm-info/data/models.yml by querying OpenRouter and provider documentation. Use when the user asks to populate model descriptions, enrich the model catalog, or curate descriptions after running pnpm sync-models.

marimo-team/marimo · 58 tokens

pysr

Use when fitting equations to data with PySR or SymbolicRegression.jl, when a user wants an interpretable formula, symbolic model, scaling law, or empirical relation discovered from numeric data, or when debugging a PySR search that is slow, stuck, or giving poor equations.

astroautomata/PySR · 61 tokens

dstack-prototyping

Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final…

dstackai/dstack · 80 tokens

dstack-presets

Create and manage dstack presets: a toolkit that streamlines model inference optimization with agents, and a portable preset format. Use together with the dstack skill, and only when the user explicitly asks to create a preset or manage existing presets, not for deploying or serving a model.

dstackai/dstack · 61 tokens

perforatedai

Expert in PerforatedAI library for adding artificial dendrites to PyTorch neural networks. Triggers: 'Perforate my model' (start interactive setup), 'debug my perforated model' (debug/optimize existing integration), 'load my perforated model for inference' (deploy trained models). Also use when: debugging dendrite…

PerforatedAI/PerforatedAI · 115 tokens