What is AutoGLM-GUI AGENTS.md?

Project instructions for AutoGLM-GUI, an Android automation application with a Python backend, web interface, and desktop Electron app.

Use them when setting up, building, linting, testing, or changing the backend, frontend, Electron app, or Android automation code.

They collect the required versions, dependencies, setup commands, development commands, and code locations in one place.

How suyiiyii/AutoGLM-GUI configures Codex and OpenCode

About the project

AutoGLM-GUI is a web interface that lets an AI operate Android devices through chat, live screen control, and Android Debug Bridge connections. It is intended for personal automation and scheduled tasks across one or more phones or emulators, and can be deployed remotely. The catalogue add-ons provide agent instructions and commands for using the tool.

suyiiyii/AutoGLM-GUI · 1,136 stars · on GitHub · autoglm-gui.vercel.app

Reuse

Borrowing it

Nothing to install: this file belongs to suyiiyii/AutoGLM-GUI. 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/suyiiyii/AutoGLM-GUI/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/suyiiyii/AutoGLM-GUI

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/suyiiyii/autoglm-gui/agents-md/github.svg)](https://agentmods.dev/instructions/suyiiyii/autoglm-gui/agents-md)

Your own site

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

Per session 1,591 This file is loaded in full into every session.

When invoked 1,591 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	$0.01591	$0.01591
Opus 5.5	$0.00636	$0.00636
Sonnet 5.5	$0.00318	$0.00318
Haiku 4.5	$0.00159	$0.00159

Measured 14d ago against content hash 73cfdd86a82c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AutoGLM-GUI 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 14d 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 · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project context

AutoGLM-GUI is an AI-driven Android automation project with a Python backend and separate frontend/electron apps.
Backend code lives in AutoGLM_GUI/ (API entrypoint examples: AutoGLM_GUI/api/__init__.py, CLI entry: AutoGLM_GUI/__main__.py).
Web frontend lives in frontend/ (entry: frontend/src/main.tsx), desktop packaging lives in electron/.
Build/lint orchestration scripts are in scripts/ (scripts/lint.py, scripts/build.py, scripts/build_electron.py).
Tests are in tests/ and tests/e2e/ (example: tests/test_metrics.py, tests/e2e/test_local_e2e.py).

Setup

Required Python: >=3.11 (from pyproject.toml).
Node/pnpm: Node.js 24 LTS and pnpm are recommended, matching lint/E2E CI. Desktop development and packaging require Node.js >=22.12 because of @electron/rebuild (see CONTRIBUTING.md).
Required tools: uv (dependency sync and task runner), adb in PATH (from CONTRIBUTING.md).
Install backend dependencies (repo root): uv sync
Install frontend dependencies: cd frontend && pnpm install
Optional Electron dependencies (when working on desktop app): cd electron && pnpm install
Start backend dev server: uv run autoglm-gui --base-url http://localhost:8080/v1 --reload
Start frontend dev server: cd frontend && pnpm dev

Commands

Lint

Quick (backend only, check mode): uv run python scripts/lint.py --backend --check-only
Quick (frontend only, check mode): uv run python scripts/lint.py --frontend --check-only
Full (check mode): uv run python scripts/lint.py --check-only

Format

Full auto-fix (backend + frontend): uv run python scripts/lint.py
Backend format check: uv run ruff format --check --diff
Backend format apply: uv run ruff format
Frontend format check: cd frontend && pnpm format:check
Frontend format apply: cd frontend && pnpm format

Typecheck

Backend typecheck: uv run pyright AutoGLM_GUI/
Frontend typecheck: cd frontend && pnpm type-check

Read the full file on GitHub · 106 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.

14d ago Changed · +12 tokens per session 73cfdd86a82c
2mo ago First seen · 106 lines · 1,579 tokens per session scan A a1826dc524f9

Subscribe to this mod's changes

AutoGLM-GUI AGENTS.md is an instructions file published in the GitHub repository suyiiyii/AutoGLM-GUI (1,136 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,591 tokens to every session, about $0.0064 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.

AutoGLM-GUI AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
AutoGLM-GUI AGENTS.mdsuyiiyii/AutoGLM-GUI	Instructions file	1.1k	yesterday	Apache-2.0	A	1,591	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

AutoGLM-GUI: Instructions file for Codex