rosetta
Copilot instructions54 starsChanged 4 months agoMITView on GitHub
GitHub Copilot reads this file plus matching .github/instructions/*.instructions.md files. Keep this file short; put actual rules in the narrow instruction files. Prefer pointers over repetition. If you are about to add a long rule here, it probably belongs in a new scoped instruction file instead.
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 repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- matrix/CLAUDE.mdCLAUDE.md
- pick-next-taskSkill
- promote-ideaSkill
- pr-review-gateSkill
- re-extractSkill
- verify-taskSkill
The file
We split this copilot-instructions.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 35
Prefer pointers over repetition.
≈ “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
Copilot instructions for rosetta
GitHub Copilot reads this file plus matching .github/instructions/*.instructions.md files. Keep this file short; put actual rules in the narrow instruction files.
Project snapshot
- Bun + TypeScript, with Bun-native runtime APIs (
bun:sqlite,Bun.serve,bunx). - One core data model, exposed as MCP + browse TUI + glossary/command-tree surfaces.
CLAUDE.mdis now only the orientation + routing index. Rationale lives inDESIGN.md; operator/reference material lives inMANUAL.md.
Routing map
CLAUDE.md— project orientation and "where does this go?" index.AGENTS.md— Codex-specific routing note.DESIGN.md— durable rationale, data-source provenance, architecture tradeoffs.MANUAL.md— install, release/re-extraction operations, CLI/HTTP reference, schema.- GitHub Issues — the active work queue (
agent-ready/umbrella/blockedlabels).tasks/is a frozen archive;tasks/README.md/briefings/README.mdhold the directory-local rules. .github/instructions/*.instructions.md— narrow normative rules selected byapplyTo.
Start with these broad rules
where-does-this-go.instructions.mdissue-pr-linking.instructions.mdchangelog-discipline.instructions.mdcapture-undone-work.instructions.mdci-pickup-verification.instructions.mdinstruction-scopes.instructions.md
Surface-specific rules
- MCP/query/TUI/canonicalizer →
mcp-server.instructions.md - Extraction/data-shape work →
extraction.instructions.md - Database init/schema internals →
database.instructions.md
Prefer pointers over repetition. If you are about to add a long rule here, it probably belongs in a new scoped instruction file instead.
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.

