agentleFS
HippocampusEvolveHippocampusEvolve/universal-agent-seed/.cursor/rules/00-defer-to-agents-md.mdc

universal-agent-seed / rules

Cursor rule0 starsChanged 4 months agoMITView on GitHub

Single source of truth — defer to AGENTS.md

  • Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.

    Of the Cursor rule files we read, the 4,181 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 repository8 other files it gives its agents.

The file

We split this 00-defer-to-agents-md.mdc into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read and follow AGENTS.md at the repository root.

    line 8
  2. Very specific:

    Do not duplicate that content here.

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule 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
00-defer-to-agents-md.mdc
---
description: Single source of truth — defer to AGENTS.md
alwaysApply: true
---

# Source of truth

Read and follow **`AGENTS.md`** at the repository root. It holds the project overview,
commands, structure, code style, testing, git workflow, and the Always / Ask-first / Never
boundaries.

Do not duplicate that content here. Add a Cursor-specific `.mdc` rule only for genuinely
glob-scoped behavior that AGENTS.md can't express (e.g. a rule that should auto-attach when
editing files matching a specific path), and keep it minimal.

This project also has a self-improvement loop (see the "Self-improvement loop" section of
`AGENTS.md`): durable learnings belong in `.claude/knowledge/`, behavior rules in
`.claude/rules/core-rules.md`, and reusable procedures in `.claude/skills/`.

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.