multi-provider-harness / rules
Cursor rule1 starsChanged 4 months agoMITView on GitHub
Project harness entry point — always read AGENTS.md and the current execution state.
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,243 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 repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- brainstormingSkill
- checkpointing-progressSkill
- executing-plansSkill
- idea-reviewSkill
- initiating-a-projectSkill
- onboardingSkill
- <kebab-case-folder-name>Skill
- test-driven-developmentSkill
- verifySkill
The file
We split this 00-harness.mdc into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 6
Read AGENTS.md at the repository root for all project conventions, invariants, and skill routing.
- Very specific: line 8
Before starting any work, read docs/state/CURRENT.md first — it holds the active task and the exact next action.
≈ “Common” is an estimate: at least 1 in 5 of the 6,809 Cursor rule 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
--- description: Project harness entry point — always read AGENTS.md and the current execution state. alwaysApply: true --- Read `AGENTS.md` at the repository root for all project conventions, invariants, and skill routing. Before starting any work, read `docs/state/CURRENT.md` first — it holds the active task and the exact next action. This project is worked across multiple AI providers switched mid-task; on-disk state in `docs/state/` is the only source of continuity between them. This `.mdc` file is a thin pointer. All real instruction lives in `AGENTS.md` and `.agents/`. Add more scoped `.mdc` rules here (with `globs:` frontmatter) only for genuinely Cursor-specific, path-scoped guidance.
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.

