agentleFS
paralleldriveparalleldrive/cuid2/AGENTS.md

cuid2

AGENTS.md3.4k starsChanged 10 months agoMITView on GitHub

This project uses AI-assisted development with structured guidance in the ai/ directory. Agents should examine the ai/* directory listings to understand the available commands, rules, and workflows. Each folder in the ai/ directory contains an index.md file that describes the purpose and contents of that folder. Agents can read these index files to learn the function of files in each folder without needing to read every file. Important: The ai/**/index.md files are auto-generated from frontmatter. Do not create or edit…

Adopted by

Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Sep 13: 0 new projectsWeek of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projectsWeek of Oct 25: 0 new projectsWeek of Nov 1: 0 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 0 in all, so this is a hint, not a trend.

Who's talking about paralleldrive/cuid2

The biggest 5 of 57 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 57

Talked about on GitHub, Hacker News and Bluesky (57 times).

On GitHub · 50

45 more on GitHub

On Hacker News · 5

  • 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.

The file

We split this AGENTS.md into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the project is Python, there is no need to read JavaScript-specific folders

    line 18
  2. Distinctive:

    If working on backend logic, frontend UI folders can be skipped

    line 19
  3. Distinctive:

    Only drill into subfolders when the task requires that specific domain knowledge

    line 20
  4. Distinctive:

    If any conflicts are detected between a requested task and the vision document, agents must:

    line 37
  5. Distinctive:

    Stop and identify the specific conflict

    line 39
  6. Distinctive:

    Ask the user to clarify how to resolve the conflict before proceeding

    line 41
  7. Distinctive:

    Never proceed with a task that contradicts the vision without explicit user approval.

    line 43

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AI Agent Guidelines

This project uses AI-assisted development with structured guidance in the ai/ directory.

Directory Structure

Agents should examine the ai/* directory listings to understand the available commands, rules, and workflows.

Index Files

Each folder in the ai/ directory contains an index.md file that describes the purpose and contents of that folder. Agents can read these index files to learn the function of files in each folder without needing to read every file.

Important: The ai/**/index.md files are auto-generated from frontmatter. Do not create or edit these files manually—they will be overwritten by the pre-commit hook.

Progressive Discovery

Agents should only consume the root index until they need subfolder contents. For example:

  • If the project is Python, there is no need to read JavaScript-specific folders
  • If working on backend logic, frontend UI folders can be skipped
  • Only drill into subfolders when the task requires that specific domain knowledge

This approach minimizes context consumption and keeps agent responses focused.

Vision Document Requirement

Before creating or running any task, agents must first read the vision document (vision.md) in the project root.

The vision document serves as the source of truth for:

  • Project goals and objectives
  • Key constraints and non-negotiables
  • Architectural decisions and rationale
  • User experience principles
  • Success criteria

Conflict Resolution

If any conflicts are detected between a requested task and the vision document, agents must:

  1. Stop and identify the specific conflict
  2. Explain how the task conflicts with the stated vision
  3. Ask the user to clarify how to resolve the conflict before proceeding

Never proceed with a task that contradicts the vision without explicit user approval.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.