agentleFS
pnppnp/powershell/.github/copilot-instructions.md

powershell

Copilot instructions906 starsChanged 2 months agoMITView on GitHub

Repository guidance for this project lives in AGENTS.md — read it first. It is the single source shared by Copilot, Claude Code, Codex and any other agent, so that guidance never drifts between tools. Task procedures live in .agents/skills/. Add new repository guidance to AGENTS.md or a playbook, never to this file — anything written here is invisible to the other tools. Never create an issue. Never create a PR. Never comment, approve, merge, or push unbidden, and never connect…

We split this copilot-instructions.md into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Add new repository guidance to AGENTS.md or a playbook, never to this file — anything written here is invisible to the other tools.

    line 9
  2. Distinctive:

    Never create an issue. Never create a PR: Never comment, approve, merge, or push unbidden, and never connect to a Microsoft 365 tenant on …

    line 14

≈ “Common” is an estimate: at least 1 in 5 of the 3,669 Copilot instructions 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
copilot-instructions.md

GitHub Copilot instructions

Repository guidance for this project lives in AGENTS.md — read it first. It is the single source shared by Copilot, Claude Code, Codex and any other agent, so that guidance never drifts between tools.

Task procedures live in .agents/skills/.

Add new repository guidance to AGENTS.md or a playbook, never to this file — anything written here is invisible to the other tools.

Read this before touching GitHub

Never create an issue. Never create a PR. Never comment, approve, merge, or push unbidden, and never connect to a Microsoft 365 tenant on your own initiative. Draft the content, hand over the command, stop. Full rules: Human in the loop.

This is about acting unprompted. When the user asks you directly to connect to a tenant and run something, that is the authorization — see Running against a tenant.

This applies to the Copilot coding agent as well: when assigned an issue, prepare the change in the working tree and stop before publishing.

Copilot specifics

Custom agents (.github/agents/*.agent.md) — pick from the agents dropdown, or let Copilot delegate to one. Available in VS Code, Visual Studio 18.4+, JetBrains, Eclipse, Xcode, the Copilot CLI (/agents) and the cloud agent on github.com:

AgentDoes
permissions-auditorPermission attributes vs the API called vs the docs
docs-syncCmdlet parameters vs documentation/*.md
api-surface-diffPublic surface of this branch vs dev
issue-triageGitHub issue → owning cmdlet → hypothesis
cmdlet-scaffolderNew cmdlet from a sibling (produces a draft)
code-reviewReview the current change

VS Code also reads .claude/agents/ in the Claude sub-agent format, so the same set is available from there — the two use matching filenames so they deduplicate rather than appearing twice.

Custom chat modes were renamed to custom agents. .chatmode.md files are no longer recognised; this repository's have been migrated to .github/agents/*.agent.md.

For cmdlet conventions there is no agent — read .agents/skills/new-cmdlet/SKILL.md directly.

MCP servers — .vscode/mcp.json configures GitHub and Microsoft Learn. See .agents/README.md.

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.