AGENTS.md · zauberzeug/nicegui
AGENTS.md from zauberzeug/nicegui: 41 lines covering Pair Programming, What to Avoid, Before Claiming a Task Complete, Creating Pull Requests and more.
Template by zauberzeug
Chalk Labs
Need help deploying AGENTS.md · zauberzeug/nicegui?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code. Read the repository before you give any tool access to your data.
curl -fsSL https://raw.githubusercontent.com/zauberzeug/nicegui/main/AGENTS.md -o AGENTS.md
Read it and adapt it to your project before use.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: prompt-engineering, code-generation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
What's in it
An AGENTS.md file: instructions coding agents (Codex, Cursor, Copilot, Gemini CLI and others) read before working in a repo.
- For
- Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code
- Length
- 41 lines
- File
AGENTS.md
Sections
- Pair Programming
- What to Avoid
- Before Claiming a Task Complete
- Creating Pull Requests
- Reviewing Pull Requests
First lines (shown under the repo's MIT license)
# AI Agent Guidelines for NiceGUI This file gives AI assistants project-specific behavioral guidance. For coding standards, see [CONTRIBUTING.md](CONTRIBUTING.md). ## Pair Programming Work as a pair programmer, not a silent code generator: - **Think from first principles**: Don't settle for the first solution; question assumptions about the true nature of the problem. - **Requirements first**: Verify requirements before implementing, especially when writing or changing tests. - **Research before guessing**: Search the codebase for similar patterns; check online sources for verification. - **Discuss before deciding**: When strategy is unclear, present options and trade-offs to the user instead of choosing silently. - **Step-by-step for large changes**: Break down significant refactorings and get confirmation along the way. - **Challenge assumptions**: If the user states something untrue, correct them directly. ## What to Avoid - **Hard-wrapping prose on GitHub** — in issues, pull requests and comments, GitHub renders every line break, so keep each paragraph on a single line. - **Overwriting `.env` files** without explicit user confirmation - **Creating new files** when editing existing ones would suffice - **Global mutable state** in library code - **Unnecessary dependencies** — check if existing code suffices first - **Reflexive regression tests** — not every bug fix earns a test, and a test coupled to implementation details can be worse than none. Assert observable behavior, not internals: no private attributes, no patched machinery, no fake objects mirroring the code under test. If you catch yourself building scaffolding to observe an internal mechanism, stop — find the user-visible effect to assert on, or skip the test and give the reason in the pull request. Before writing a test, read a recent one in the same file and copy its shape. (Details in [CONTRIBUTING.md](CONTRIBUTING.md#coding-conventions).) ## Before Claiming a Task Complete Run the project's tests and linters (see [CONTRIBUTING.md](CONTRIBUTING.md)) and review your own diff for unintended scope creep. ## Creating Pull Requests Always use the repository's PR template ([`.github/PULL_REQUEST_TEMPLATE.md`](.github/PULL_REQUEST_TEMPLATE.md)) with its **Motivation**, **Implementation**, and **Progress** sections. Do not invent alternative formats like "Summary" or "Test plan". ## Reviewing Pull Requests Follow [REVIEW.md](REVIEW.md) — it lists what to look for, defines the severity vocabulary, and sets the tone for reviews.
Signals
- Stars
- 16,311
- Forks
- 964
- Open issues
- 15
- Last commit (this folder)
- Oct 12, 2026 (18 days ago)
- Last release
- Oct 7, 2026 (23 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/zauberzeug/nicegui
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get AGENTS.md · zauberzeug/nicegui running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
AGENTS.md · zauberzeug/nicegui. Agent Mart. https://agentmart.dev/templates/zauberzeug-nicegui-agents-md (last updated 2026-10-24)