agentleFS
Sign inStart free
EpicGamesEpicGames/lore/AGENTS.md

lore

AGENTS.md9.1k starsChanged 9 days agoMITView on GitHub

Guidance for AI agents working in this repository. You must load the lore-development skill (.claude/skills/lore-development/SKILL.md) at the start of every session in this repository, before any other work, and follow it. This applies to every task: designing, writing, reviewing, building or testing code, and answering questions about it. Load it again whenever the conversation is compacted or resumed, and tell every subagent you brief to load it too. The skill routes to the decisions and code standards that govern the…

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 EpicGames/lore

The biggest 5 of 39 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 39

Talked about on GitHub, Bluesky and Hacker News (39 times).

On GitHub · 26

21 more on GitHub

On Bluesky · 12

7 more on Bluesky

On Hacker News · 1

  • 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 repository5 other files it gives its agents.

The file

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

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

  • 2

    Very specific

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

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

    When context/team-workspace.md exists, read it before non-trivial work and follow it.

    line 25
  2. Very specific:

    If you are about to write code in one of those four classes, the proposal comes first — not afterwards to describe what was built.

    line 44

≈ “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

AGENTS.md

Guidance for AI agents working in this repository.

Development workflow

You must load the lore-development skill (.claude/skills/lore-development/SKILL.md) at the start of every session in this repository, before any other work, and follow it. This applies to every task: designing, writing, reviewing, building or testing code, and answering questions about it. Load it again whenever the conversation is compacted or resumed, and tell every subagent you brief to load it too.

The skill routes to the decisions and code standards that govern the change, and defines the validation, review and submission steps. Work done without it doesn't meet this repository's standards.

You must review every change with the review-change skill (.claude/skills/review-change/SKILL.md) before you submit it. The review runs in a fresh session, from the code, so it finds what the author's own reading misses. Performance and allocations come first, and a fix must come with a test that fails without it.

Team workspace

When context/team-workspace.md exists, read it before non-trivial work and follow it. It names the team's workspace for specs, plans, work items and decisions, and how to reach it. Without it, work proceeds normally, and specs and plans stay in context/.

Where design decisions go

A spec plus plan is the whole design record for ordinary work. This project does not generally use RFCs.

Four classes are different. A larger architectural change, anything touching a data format or a protocol, and any substantial new capability are designed in this repo, in public:

  • LEPs — docs/proposals/YYYY-MM-DD-<slug>.md. Required per GOVERNANCE.md; minimum two-week discussion, and accepted before implementation begins.
  • ADRs — docs/developing/decisions/<NNNNN>-<slug>.md, for rulings below the LEP bar.

If you are about to write code in one of those four classes, the proposal comes first — not afterwards to describe what was built. The LEP bar is in GOVERNANCE.md and CONTRIBUTING.md.

Governance sign-off is a GitHub gate

The issue → PR → two-Maintainer-approval flow in GOVERNANCE.md and CONTRIBUTING.md governs public contributions arriving through GitHub. It is not a per-revision gate on work in Lore — a Lore branch is reviewed through its change request.

Binding either way: an accepted LEP before implementation for the four classes above, the Code of Conduct, and the security policy.

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