agentleFS
equinorequinor/fusion-skills/AGENTS.md

fusion-skills

AGENTS.md2 starsChanged 2 months agoMITView on GitHub

Audience: GitHub Copilot / coding agents making changes in this repository. This repository is a shared catalog of Fusion GitHub Copilot Agent Skills. Treat it like a library: changes should be small, reviewable, and security-first. When creating or editing skills, follow CONTRIBUTING.md and .github/copilot-instructions.md. For local skill discovery in this repository, search skills/ first and include both skills/ and skills/.experimental/ in local .agents/skills lookup paths for this workspace.

The file

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

10 rules. About 1 is common, 8 are distinctive, and 1 is very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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:

    Prefer minimal diffs; avoid unrelated refactors.

    line 17
  2. Distinctive:

    Follow existing repository conventions.

    line 18
  3. Distinctive:

    If requirements are ambiguous, ask targeted questions.

    line 19
  4. Distinctive:

    Keep changes scoped to the request.

    line 23
  5. Distinctive:

    Avoid introducing new global governance unless explicitly requested.

    line 24
  6. Distinctive:

    Ensure Markdown docs render correctly on GitHub.

    line 25
  7. Common:

    Never request, store, or print secrets.

    line 29
  8. Distinctive:

    Prefer read-only operations by default.

    line 31
  9. Distinctive:

    Avoid risky automation patterns (for example remote-script execution).

    line 32
  10. Very specific:

    When creating or editing skills, follow CONTRIBUTING.md and .github/copilot-instructions.md.

    line 36

≈ “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

Audience: GitHub Copilot / coding agents making changes in this repository.

This repository is a shared catalog of Fusion GitHub Copilot Agent Skills. Treat it like a library: changes should be small, reviewable, and security-first.

Where to look first

  • Consumer overview: README.md
  • Maintainer workflow: CONTRIBUTING.md
  • Security policy: SECURITY.md
  • Script-specific guidance: documentation in the scripts/ directory

Operating principles

  • Optimize for safety, clarity, and maintainability over cleverness.
  • Prefer minimal diffs; avoid unrelated refactors.
  • Follow existing repository conventions.
  • If requirements are ambiguous, ask targeted questions.

Practical checklist

  • Keep changes scoped to the request.
  • Avoid introducing new global governance unless explicitly requested.
  • Ensure Markdown docs render correctly on GitHub.

Security baseline

  • Never request, store, or print secrets.
  • Redact sensitive data in examples/logs.
  • Prefer read-only operations by default.
  • Avoid risky automation patterns (for example remote-script execution).

Skills changes

When creating or editing skills, follow CONTRIBUTING.md and .github/copilot-instructions.md. For local skill discovery in this repository, search skills/ first and include both skills/ and skills/.experimental/ in local .agents/skills lookup paths for this workspace.

Custom instruction files

  • Repository-wide Copilot instructions: .github/copilot-instructions.md
  • Path-specific instructions: .github/instructions/*.instructions.md
  • Agent instructions: nearest AGENTS.md in directory tree takes precedence.

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.