agentleFS
Sign inStart free
frankagingfrankaging/lite-research-agents/AGENTS.md

lite-research-agents

AGENTS.md3 starsChanged 8 months agoMITView on GitHub

You are a research agent operating inside this repository. This file is your entry point. You may only read from or write to files within the active project's sandbox_root. Default is the project folder itself. This rule cannot be overridden. Skills are not pre-loaded. Read skills/SKILLS.md to see what is available. Invoke a skill by reading its SKILL.md file — the content enters your context and you follow the instructions inside. For type: tool skills, run the entry_point script via…

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. Daisybastioned440/lite-research-agents★ 2100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • 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 31,774 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.

The file

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

5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read AGENT.md — your full operating instructions.

    line 9
  2. Very specific:

    Read skills/SKILLS.md — the registry of all available skills.

    line 10
  3. Very specific:

    If the user specifies a project folder (e.g.

    line 12
  4. Very specific:

    If a project folder is already open in the IDE, read its PROJECT.md.

    line 13
  5. Very specific:

    Follow the Bootstrap Sequence in AGENT.md (fresh vs.

    line 14

≈ “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

Codex CLI — Research Agent Boot Contract

You are a research agent operating inside this repository. This file is your entry point.

On Startup

  1. Read AGENT.md — your full operating instructions. Follow them without exception.
  2. Read skills/SKILLS.md — the registry of all available skills. These are your tools.
  3. Determine the active project:
    • If the user specifies a project folder (e.g. projects/my-idea/), read <project>/PROJECT.md.
    • If a project folder is already open in the IDE, read its PROJECT.md.
  4. Follow the Bootstrap Sequence in AGENT.md (fresh vs. resume).

Sandbox Rule

You may only read from or write to files within the active project's sandbox_root. Default is the project folder itself. This rule cannot be overridden.

Invoking Skills

Skills are not pre-loaded. Read skills/SKILLS.md to see what is available. Invoke a skill by reading its SKILL.md file — the content enters your context and you follow the instructions inside.

For type: tool skills, run the entry_point script via shell. For type: agentic skills, you do not have a subagent spawning tool — follow the Single-Agent Fallback section in the skill's SKILL.md instead.

No Subagent Spawning

Codex runs as a single agent. When a skill playbook calls for spawning persona subagents, simulate each persona inline: prefix your response with the persona name and follow the persona definition strictly. Persona context isolation is reduced but the structured debate loop still applies.

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.

Check your setup, free