agentleFS
Lisa-HarnessLisa-Harness/lisa/.github/copilot-instructions.md

lisa

Copilot instructions9 starsChanged 26 days agoMITView on GitHub

Use the repository customization taxonomy in this order:

The file

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

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

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

    Use the repository customization taxonomy in this order:

    line 7
  2. Distinctive:

    Always-on project contract: this file and the package-scoped guidance below.

    line 9
  3. Distinctive:

    Prefer the smallest rule file that can explain the intent.

    line 16
  4. Distinctive:

    Treat the repository as a hard-cutover codebase.

    line 18
  5. Very specific:

    Follow the shared engineering loop: verify, review the diff, then commit.

    line 19
  6. Distinctive:

    Keep troubleshooting notes, incident logs, and one-off test workarounds out of instructions.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 3,827 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

Lisa Copilot Project Contract

Use the repository customization taxonomy in this order:

  1. Always-on project contract: this file and the package-scoped guidance below.
  2. Engineering standards: workflow, Python, content-authoring, and file-format rules.
  3. Architecture boundaries: package ownership and dependency rules for kernel, SDK, packs, MCP servers, and hosts.
  4. Customization governance: how to author instructions, agents, prompts, and skills without bloating the prompt.

Operating defaults

  • Prefer the smallest rule file that can explain the intent. Keep instructions concise and task-driven.
  • Resolve scope explicitly. A change should bind to the narrowest applyTo that still covers the relevant files.
  • Treat the repository as a hard-cutover codebase. Do not add compatibility shims or stale aliases for old patterns.
  • Follow the shared engineering loop: verify, review the diff, then commit. Land changes on main by rebase or squash — never a merge commit. If a change is already shared or pushed, prefer a fixup! commit over rewriting history.
  • Keep troubleshooting notes, incident logs, and one-off test workarounds out of instructions. Put them in docs or tests instead.

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.