OM1
Copilot instructions2.9k starsChanged 4 months agoMITView on GitHub
We split this copilot-instructions.md into the rules it gives an agent
17 rules. About 1 is common, 11 are distinctive, and 5 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 6
Use these make commands:
- Very specific: line 9
Test with coverage: make test-coverage
- Very specific: line 14
Check all: make check (runs fmt, vet, lint, and test)
- Very specific: line 16
When adding a new dependency, use go get <package> and run make deps to tidy.
- Distinctive: line 17
Keep the dependency list minimal and prefer well-maintained packages.
- Distinctive: line 21
Follow Go conventions and idiomatic patterns
- Common: line 22
Use proper error handling (never ignore errors)
- Distinctive: line 23
Follow the standard Go project layout
- Very specific: line 24
Use gofmt for formatting (enforced by make fmt)
- Distinctive: line 29
Keep business logic out of HTTP handlers
- Distinctive: line 30
Use interfaces for abstractions
- Distinctive: line 33
Use Go's built-in testing framework
- Distinctive: line 34
Add unit tests for all new functions
- Very specific: line 36
Run tests with race detector: make test
- Distinctive: line 37
Use table-driven tests where appropriate
- Distinctive: line 41
Write clear package documentation
- Distinctive: line 42
Document exported functions and types
≈ “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.
Files
Copilot Instructions
Tooling / Dependencies
- We use Make for building, testing, and running the project.
- Dependencies are managed via Go modules (
go.modandgo.sum). - Use these make commands:
- Build:
make build - Test:
make test - Test with coverage:
make test-coverage - Run:
make run CONFIG=<config_name> - Dev mode:
make dev CONFIG=<config_name> - Lint:
make lint - Format:
make fmt - Check all:
make check(runs fmt, vet, lint, and test) - Clean:
make clean
- Build:
- When adding a new dependency, use
go get <package>and runmake depsto tidy. - Keep the dependency list minimal and prefer well-maintained packages.
Coding Style
- Use Go 1.21+
- Follow Go conventions and idiomatic patterns
- Use proper error handling (never ignore errors)
- Follow the standard Go project layout
- Use
gofmtfor formatting (enforced bymake fmt)
Architecture
- Use modular design
- Separate concerns: inputs, actions, backgrounds, LLM providers
- Keep business logic out of HTTP handlers
- Use interfaces for abstractions
Testing
- Use Go's built-in testing framework
- Add unit tests for all new functions
- Aim for 90% code coverage
- Run tests with race detector:
make test - Use table-driven tests where appropriate
- Mock external dependencies using interfaces
Comments
- Write clear package documentation
- Document exported functions and types
- Avoid obvious comments
- Use godoc conventions
Trending
Quiet since July.thin dataabout the whole repository
Who's talking about OpenMind/OM1
- OpenMind/OM1-telemetry“Complementary tool: OTel-GenAI trace export + behavioral-regression gate for OM1 (Plumbline)”GitHub · Jul 13, 2026
- githubevents/open-source-friday“Open Source Friday - OpenMind - 5-22-2026 1PM”GitHub · Apr 8, 2026
- githubevents/open-source-friday“Open Source Friday - OM1 - 05-08-2026”GitHub · Apr 7, 2026
- ScapeXYZ/OM1“Fix /status Endpoint to Return Live OpenMind API Data”GitHub · Aug 9, 2025
The biggest 4 of 4 mentions linking to the repository that our crawl found. Each line is their own headline.
Where files are headingNew Copilot instructions files have more rules about branches and pull requests, and fewer about code style.
Of the Copilot instructions files we read, the 2,297 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.
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
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.

