Home › Rules › Python automation script
Python automation script rules: AGENTS.md, CLAUDE.md & Cursor rules
Automation scripts touch real files and real accounts. These rules give every script a dry-run mode and make it ask before it deletes anything.
Stack these rules assume: Python 3, a virtual environment, standard library first. Different stack? Customize it in the generator.
Quick start
- Copy the
AGENTS.mdbelow into your project's root folder. - Fill in the three
[bracketed]lines under "Project". Delete any rule that doesn't fit. - Start your first chat with: "Read AGENTS.md and follow it for this whole session."
AGENTS.md (works across tools)
Read by OpenAI Codex, Cursor, GitHub Copilot, Claude Code (when there's no CLAUDE.md) and many other agents.
# AGENTS.md: Python automation script
Instructions for AI coding agents working on this project. Replace anything in [brackets].
## Project
- What it is: [one sentence: what you are building and who it is for]
- Stack: Python 3, a virtual environment, standard library first
- Version 1 only needs to: [the ONE thing it must do]
## Commands
- Create a virtual environment: `python3 -m venv .venv && source .venv/bin/activate`
- Install: `pip install -r requirements.txt`
- Try it safely first: `python main.py --dry-run`
## Project rules
- Every script that changes files, sends anything, or calls a paid API has a --dry-run flag that prints what it would do.
- Never delete or overwrite files without an explicit flag. Prefer moving to a backup folder.
- Use the standard library first. Ask before adding a dependency, and pin versions in requirements.txt.
- Settings (paths, limits, account names) go in a config section or .env, not scattered through the code.
- Log what happened (counts, skipped items, errors) at the end of every run.
- Handle one failing item without stopping the whole run. Report failures at the end.
## How to work
- Do one task per request. If my request is really several tasks, list them and do only the first.
- Before writing code, give a 3-line plan: what you'll change, which files, and how I'll test it.
- Make the smallest change that works. Don't refactor, rename, or reformat code I didn't ask about.
- Ask before adding a dependency, deleting or moving files, changing the data/database structure, or touching more than 3 files.
- If you're not sure a library, API, or setting exists in the version we use, say so and check the installed package or the docs instead of guessing.
- Never say something works unless you ran it or I confirmed it. Report errors exactly.
- Secrets (API keys, tokens, passwords) live only in environment variables or a .env file listed in .gitignore. Never print, hardcode, or commit them.
- Never run destructive commands (rm -rf, git reset --hard, force-push, dropping tables) without asking first.
## Finish every task with
1. What changed (list the files).
2. How to run or test it in under a minute, and what I should see.
3. A suggested git commit message.
Want a step-by-step kit?
Our paid templates ($6 to $9) add a full prompt sequence and a worked example on top of rules like these, for games, Discord bots, email triage, MVPs and fixing messy code.
Why each rule exists
- Python automation script ruleEvery script that changes files, sends anything, or calls a paid API has a --dry-run flag that prints what it would do.Why: You get to see the plan before the script renames 2,000 files.
- Python automation script ruleNever delete or overwrite files without an explicit flag. Prefer moving to a backup folder.Why: Scripts run fast and don't ask "are you sure?". Unless you tell them to.
- Python automation script ruleUse the standard library first. Ask before adding a dependency, and pin versions in requirements.txt.Why: Fewer dependencies means the script still runs a year from now.
- Python automation script ruleSettings (paths, limits, account names) go in a config section or .env, not scattered through the code.Why: Next month you'll want to point it at a different folder without reading the whole script.
- Python automation script ruleLog what happened (counts, skipped items, errors) at the end of every run.Why: "Did it work?" should be answered by the script, not by you checking by hand.
- Python automation script ruleHandle one failing item without stopping the whole run. Report failures at the end.Why: One weird file shouldn't stop the other 999 from being processed.
- How to workDo one task per request. If my request is really several tasks, list them and do only the first.Why: Big multi-part requests are where AI tools change 12 files and you can't tell which change broke things.
- How to workBefore writing code, give a 3-line plan: what you'll change, which files, and how I'll test it.Why: A plan you can read in 10 seconds catches the wrong approach before it costs you an hour or a pile of credits.
- How to workMake the smallest change that works. Don't refactor, rename, or reformat code I didn't ask about.Why: Drive-by "cleanups" are the #1 cause of "it was working yesterday".
- How to workAsk before adding a dependency, deleting or moving files, changing the data/database structure, or touching more than 3 files.Why: These are the changes that are hard to undo. One quick question is cheaper than a rollback.
- How to workIf you're not sure a library, API, or setting exists in the version we use, say so and check the installed package or the docs instead of guessing.Why: AI tools confidently invent functions and config options. Making it check is the cure.
- How to workNever say something works unless you ran it or I confirmed it. Report errors exactly.Why: "Should work now" isn't a test result. You want facts, not optimism.
- How to workSecrets (API keys, tokens, passwords) live only in environment variables or a .env file listed in .gitignore. Never print, hardcode, or commit them.Why: Leaked keys get found by bots within minutes of a public push. This rule is the cheapest insurance you'll ever buy.
- How to workNever run destructive commands (rm -rf, git reset --hard, force-push, dropping tables) without asking first.Why: One bad command can delete the only copy of your work.
- Finish every task withWhat changed, how to test it, and a commit message.Why: This turns every task into a checkpoint: you test it, you commit it, and you always have a last good version to go back to.
Use it as CLAUDE.md (Claude Code)
Pick one:
- Do nothing. Current Claude Code versions read
AGENTS.mdwhen the project has noCLAUDE.md. Run/memoryin a session to check it loaded. - Import it (best if you want Claude-only extras, or you're on an older Claude Code). Create
CLAUDE.mdnext toAGENTS.md:
@AGENTS.md
## Claude Code
- Use plan mode before any change that touches more than 3 files.
- Claude only? Save the same AGENTS.md text as
CLAUDE.mdinstead. Don't keep two separate copies; they drift apart.
Heads-up: if a project has both files and CLAUDE.md doesn't import AGENTS.md, Claude Code reads only CLAUDE.md by default. More in AGENTS.md vs CLAUDE.md.
Use it as Cursor rules (.cursor/rules/*.mdc)
Cursor reads AGENTS.md too, so the file above already works. If you prefer Cursor's own Project Rules, split it into two .mdc files. The .mdc extension and frontmatter are required; Cursor ignores plain .md files in .cursor/rules.
---
description: Project overview and working rules for Python automation script
alwaysApply: true
---
# Python automation script
Instructions for AI coding agents working on this project. Replace anything in [brackets].
## Project
- What it is: [one sentence: what you are building and who it is for]
- Stack: Python 3, a virtual environment, standard library first
- Version 1 only needs to: [the ONE thing it must do]
## Commands
- Create a virtual environment: `python3 -m venv .venv && source .venv/bin/activate`
- Install: `pip install -r requirements.txt`
- Try it safely first: `python main.py --dry-run`
## How to work
- Do one task per request. If my request is really several tasks, list them and do only the first.
- Before writing code, give a 3-line plan: what you'll change, which files, and how I'll test it.
- Make the smallest change that works. Don't refactor, rename, or reformat code I didn't ask about.
- Ask before adding a dependency, deleting or moving files, changing the data/database structure, or touching more than 3 files.
- If you're not sure a library, API, or setting exists in the version we use, say so and check the installed package or the docs instead of guessing.
- Never say something works unless you ran it or I confirmed it. Report errors exactly.
- Secrets (API keys, tokens, passwords) live only in environment variables or a .env file listed in .gitignore. Never print, hardcode, or commit them.
- Never run destructive commands (rm -rf, git reset --hard, force-push, dropping tables) without asking first.
## Finish every task with
1. What changed (list the files).
2. How to run or test it in under a minute, and what I should see.
3. A suggested git commit message.
The project rules only attach when a matching file is in the chat (globs with alwaysApply: false). Want them on all the time? Change it to alwaysApply: true.
---
globs: **/*.py
alwaysApply: false
---
# Project rules: Python automation script
- Every script that changes files, sends anything, or calls a paid API has a --dry-run flag that prints what it would do.
- Never delete or overwrite files without an explicit flag. Prefer moving to a backup folder.
- Use the standard library first. Ask before adding a dependency, and pin versions in requirements.txt.
- Settings (paths, limits, account names) go in a config section or .env, not scattered through the code.
- Log what happened (counts, skipped items, errors) at the end of every run.
- Handle one failing item without stopping the whole run. Report failures at the end.
Use either AGENTS.md or these .mdc files, not both, so you don't send the same rules twice. See Cursor rules vs AGENTS.md.