HRDIUtilities / instructions
Copilot instructions6 starsChanged 5 months agoMITView on GitHub
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 2,336 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.
In this repository4 other files it gives its agents.
- DQ-CoWorker/.github/instructions/copilot-instructions.mdCopilot instructions
- FabricCLI/.github/instructions/copilot-instructions.mdCopilot instructions
- MaskIQ/.github/instructions/copilot-instructions.mdCopilot instructions
- Prompt2Data/.github/instructions/copilot-instructions.mdCopilot instructions
The file
We split this copilot-instructions.md into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Very specific: line 7
Follow the stages in prompts/fabric-access-onboarding.prompt.md in order.
- Distinctive: line 9
Never guess tenant, catalog, group, access package, policy, workspace, or identity object IDs.
- Distinctive: line 11
Do not create a missing entitlement catalog directly.
- Distinctive: line 13
Never reveal or persist browser, Microsoft 365, Graph, Fabric, or Power BI access tokens.
≈ “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
Fabric access onboarding instructions
- Follow the stages in
prompts/fabric-access-onboarding.prompt.mdin order. - Resolve named people to exact Entra users; never infer email addresses from names.
- Never guess tenant, catalog, group, access package, policy, workspace, or identity object IDs.
- Reuse exact-name resources when they already exist and verify persistent state after each write.
- Do not create a missing entitlement catalog directly. Prepare the approved catalog request workflow and stop until the catalog exists.
- Show the recipient and exact email body and obtain explicit confirmation before sending outbound email.
- Never reveal or persist browser, Microsoft 365, Graph, Fabric, or Power BI access tokens.
- Distinguish the Fabric workspace ID from the workspace identity ID.
- Require explicit confirmation before destructive actions or access removal.
- Report completed, blocked, and unverifiable stages separately.
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.

