What is gradio AGENTS.md?

A set of instructions for AI coding agents contributing to the Gradio Python library. It describes the repository layout and rules for preparing pull requests.

Use it when modifying Gradio, running or adding tests, working on demos or guides, or preparing a contribution for review.

It helps agents find the right source, test, demo, and documentation files. It also reduces the chance of submitting changes without the project's required issue and review details.

How gradio-app/gradio configures Codex and OpenCode

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 · 44,010 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.md

Clone the repo

git clone --depth 1 https://github.com/gradio-app/gradio

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gradio-app/gradio/agents-md/github.svg)](https://agentmods.dev/instructions/gradio-app/gradio/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/gradio-app/gradio/agents-md"><img src="https://agentmods.dev/badge/instructions/gradio-app/gradio/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gradio-app/gradio/agents-md"><img src="https://agentmods.dev/badge/instructions/gradio-app/gradio/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 893 This file is loaded in full into every session.

When invoked 893 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00893	$0.00893
Opus 5.5	$0.00357	$0.00357
Sonnet 5.5	$0.00179	$0.00179
Haiku 4.5	$0.00089	$0.00089

Measured 1mo ago against content hash ea492860c394, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gradio AGENTS.md 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 1mo 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.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI coding agents working on this repository.

Repository Structure

gradio/ — Python source for the Gradio library (backend)
- gradio/components/ — all Gradio components
- gradio/cli/ — CLI commands (gradio, gradio cc, gradio skills, etc.)
client/python/ — the gradio_client Python client library
client/js/ — the @gradio/client JavaScript client library
js/ — frontend code (Svelte/TypeScript), with each component in its own subdirectory
test/ — Python backend tests (pytest)
js/spa/test/ — browser/Playwright tests (*.spec.ts)
demo/ — example Gradio apps
guides/ — written guides and tutorials for the website

Pull Request Rules

Follow these rules when creating or contributing to pull requests:

Target an issue. Every non-trivial PR should reference an existing GitHub issue. If one doesn't exist, create it first. PRs without a linked issue may be closed.
Use the PR template. Fill out every section of .github/PULL_REQUEST_TEMPLATE.md, including:
- A clear description of the change
- The AI disclosure checkbox (see below)
- The linked issue (Closes: #NNN)
AI disclosure is mandatory. If AI was used in any non-trivial way (drafting code, writing the PR description, etc.), you must disclose this in the PR template. Trivial autocomplete does not need to be disclosed. All AI-generated code must be self-reviewed.
Format your code before pushing.
- Backend: bash scripts/format_backend.sh
- Frontend: bash scripts/format_frontend.sh
Tests must pass. PRs are only merged when CI is green. Run backend tests locally with bash scripts/run_backend_tests.sh.
PR title and description should be clear and written in English. The title should concisely describe what the PR does. The description should explain why.
Don't write changeset files. A GitHub Action (committing as gradio-pr-bot) adds .changeset/*.md to your branch from the PR title, so a good title is all that's needed. The bot leaves an existing changeset alone, so a hand-written one silently replaces your title in the changelog.
- Reviewers (human or AI): a .changeset/*.md file in a PR is expected, because the CI adds one to every PR. Don't flag it or ask for it to be removed. This rule is about what authors should do, not something to check in review.

Read the full file on GitHub · 74 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.

1mo ago Changed · +1 lines · +72 tokens per session ea492860c394
2mo ago First seen · 73 lines · 821 tokens per session scan A 975541e72c77

Subscribe to this mod's changes

gradio AGENTS.md is an instructions file published in the GitHub repository gradio-app/gradio (44,010 stars, last pushed yesterday), licensed Apache-2.0. It adds 893 tokens to every session, about $0.0036 per session on Opus 5.5. 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.

Python interface machine-learning models ui ui-components

gradio AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gradio AGENTS.mdgradio-app/gradio	Instructions file	44k	yesterday	Apache-2.0	A	893	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

gradio: Instructions file for Codex