agentleFS
Sign inStart free
ozgurkarahanozgurkarahan/ai-agent-memory/.github/copilot-instructions.md

ai-agent-memory

Copilot instructions8 starsChanged 4 months agoMITView on GitHub

Read these files for full context: A compounding cross-project knowledge base lives at ~/projects/memory (%USERPROFILE%\projects\memory on Windows; resolve ~ to your home dir). Consult it reflexively before answering about clients, domains, patterns, tools, colleagues, or past work — do not answer from memory when the wiki has the answer. - Read the top matching page(s) in full before you answer. - Compact catalog / router: ~/projects/memory/index.md (per-category summaries in ~/projects/memory/wiki/{category}/_index.md). - When you learn something durable about this project or…

The file

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

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read these files for full context:

    line 3
  2. Very specific:

    Use @workspace to give Copilot full project context

    line 11
  3. Distinctive:

    Use Copilot Edits (Ctrl+Shift+I) for multi-file changes

    line 13
  4. Distinctive:

    Run tests manually — Copilot cannot execute them

    line 14
  5. Very specific:

    When corrected, update the project wiki page at ~/projects/memory/wiki/projects/ai-agent-memory.md

    line 15
  6. Distinctive:

    Read the top matching page(s) in full before you answer.

    line 31
  7. Very specific:

    When you learn something durable about this project or client, ask the user to run ingest in the memory repo so it compounds for future …

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 3,779 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

Copilot Instructions

Read these files for full context:

  • AGENT.md — Project instructions, workflow rules, architecture, key paths
  • ~/projects/memory/wiki/projects/ai-agent-memory.md — Project wiki page (lessons, decisions)
  • ~/projects/memory/agent-config/workflow.md — Global workflow rules

Copilot-Specific Tips

  • Use @workspace to give Copilot full project context
  • Pin AGENT.md in chat for persistent context
  • Use Copilot Edits (Ctrl+Shift+I) for multi-file changes
  • Run tests manually — Copilot cannot execute them
  • When corrected, update the project wiki page at ~/projects/memory/wiki/projects/ai-agent-memory.md

Shared knowledge base (memory wiki)

A compounding cross-project knowledge base lives at ~/projects/memory (%USERPROFILE%\projects\memory on Windows; resolve ~ to your home dir). Consult it reflexively before answering about clients, domains, patterns, tools, colleagues, or past work — do not answer from memory when the wiki has the answer.

# from ANY repo — resolves the wiki root from the script's own location
python ~/projects/memory/scripts/wiki-search.py <terms>          # ranked hits
python ~/projects/memory/scripts/wiki-search.py <terms> --full   # + Summary
  • Read the top matching page(s) in full before you answer.
  • Compact catalog / router: ~/projects/memory/index.md (per-category summaries in ~/projects/memory/wiki/{category}/_index.md).
  • When you learn something durable about this project or client, ask the user to run ingest in the memory repo so it compounds for future sessions.

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