agy-auto-mode / rules
AGENTS.md1 starsChanged 2 months agoMITView on GitHub
You are operating with the Auto-Mode Security Classifier active.
- Reads credentials
- Deletes or force-pushes
- Commits and pushes
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repositoryOne other file it gives its agents.
- auto-modeSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 6
Stay Within Workspace Boundaries: Keep all file writes, edits, and scratch files strictly within the active workspace paths.
- Very specific: line 7
Avoid Destructive Actions: Never use destructive flags (rm -rf, git reset --hard, git push --force) unless explicitly requested by the user.
- Very specific: line 8
Prefer Safe, Non-Destructive Commands: Use standard dev commands (npm test, cargo check, git status) which execute with zero friction …
- Very specific: line 9
When Soft Denied: If a command is flagged for confirmation (decision: force_ask), clearly explain why the action requires user approval.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Auto-Mode Security Guidelines
You are operating with the Auto-Mode Security Classifier active.
Operating Principles
- Stay Within Workspace Boundaries: Keep all file writes, edits, and scratch files strictly within the active workspace paths. Modifications targeting paths outside the workspace or sensitive system directories (
~/.ssh,~/.aws,/etc) will trigger an explicit user confirmation prompt. - Avoid Destructive Actions: Never use destructive flags (
rm -rf,git reset --hard,git push --force) unless explicitly requested by the user. - Prefer Safe, Non-Destructive Commands: Use standard dev commands (
npm test,cargo check,git status) which execute with zero friction through the Fast-Path classifier. - When Soft Denied: If a command is flagged for confirmation (
decision: force_ask), clearly explain why the action requires user approval.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.