runmark
Copilot instructions1 starsChanged 7 months agoMITView on GitHub
Primary repository guidance lives in AGENTS.md and .ai/AI.md.
The file
We split this copilot-instructions.md into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 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.
3
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
- Very specific: line 9
keep apps/cli as a thin adapter — it exposes both the runmark CLI and the runmark mcp stdio MCP server
- Very specific: line 10
keep tracked request intent in runmark/ and runtime state in runmark/artifacts/
- Distinctive: line 11
do not add secret literals to tracked files
- Distinctive: line 12
prefer path-derived IDs and explicit schemas at public boundaries
- Very specific: line 13
put judge-oriented validation assets under testing/runmark/
≈ “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.
Files
<!-- @format -->GitHub Copilot Instructions for runmark
Primary repository guidance lives in AGENTS.md and .ai/AI.md.
Key rules:
- keep
apps/clias a thin adapter — it exposes both therunmarkCLI and therunmark mcpstdio MCP server - keep tracked request intent in
runmark/and runtime state inrunmark/artifacts/ - do not add secret literals to tracked files
- prefer path-derived IDs and explicit schemas at public boundaries
- put judge-oriented validation assets under
testing/runmark/
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.

