Claude Code vs Cursor: which do top repos set up for?
Claude Code averages higher: 71.9 for Claude Code and 63.5 for Cursor, across 402 repos. Claude Code scores higher on 388, Cursor on 12, and 2 tie.
Scores measure how well each repo is set up for an agent: instruction files, tests, CI and the other checks, weighted by what each agent's docs say it uses, not which agent writes better code.
Which files does each one read?
- Reads from the repo
- Claude Code:
CLAUDE.md.claude/CLAUDE.md.claude/rules/CLAUDE.local.mdAGENTS.md.claude/AGENTS.md - Cursor:
.cursor/rules/*.mdcAGENTS.mdCLAUDE.md.agents/skills/ - Reads AGENTS.md
- Claude Code: Only when there is no CLAUDE.md
- Cursor: Always
- Reads CLAUDE.md
- Claude Code: Yes
- Cursor: Yes
- From its docs
- Claude Code: Reads AGENTS.md only when no CLAUDE.md,
.claude/CLAUDE.mdor CLAUDE.local.md is found (v2.1.277 and later). A CLAUDE.md that imports@AGENTS.mdloads both, as does a setting. - Cursor: Project rules are
.mdcfiles in.cursor/rules/, subfolders included; a plain.mdthere is ignored. AGENTS.md is read at the root and in subdirectories, combined, the more specific winning. CLAUDE.md is read the same way; the docs describe one at the root. A root.cursorrulesis legacy and will be deprecated. - Repos with its own file
- Claude Code: CLAUDE.md only: 18 of 402 (4%)
- Cursor: .cursor/rules or .cursorrules: 18 of 402 (4%)
AGENTS.md and CLAUDE.md mean the file at the repo root; a repo with both counts under AGENTS.md, and empty files don't count. Every agent's files.
Which checks does each weigh more?
| Check | Claude Code | Cursor |
|---|---|---|
| Cursor rules (.cursor/rules) | 0% | 11% |
| Reproducible dev env | 12% | 6% |
| Test suite | 13% | 8% |
| Skills (.agents/skills) | 0% | 5% |
| AGENTS.md / CLAUDE.md | 13% | 9% |
| Type configuration | 8% | 11% |
Each figure is the check's share of the agent's total weight, from the docs linked below. A check few repos pass, such as an agent's own file, lowers that agent's scores wherever it carries weight. The methodology lists every weight.
Which repos are set up better for Claude Code than Cursor?
- prisma/orm78.9 vs 59.5 for Cursor
- calcom/cal.diy86.8 vs 68.7 for Cursor
- scikit-learn/scikit-learn86.8 vs 69.1 for Cursor
- github/spec-kit87.2 vs 69.8 for Cursor
- directus/directus83.6 vs 66.7 for Cursor
Which repos are set up better for Cursor than Claude Code?
- Shopify/cli89.5 vs 82.8 for Claude Code
- mastra-ai/mastra91.6 vs 86.1 for Claude Code
- novuhq/novu90.5 vs 86.8 for Claude Code
- symfony/symfony46.9 vs 43.4 for Claude Code
- discourse/discourse94.6 vs 91.2 for Claude Code
Which one leads in each language?
| Language | Repos | Claude Code | Cursor |
|---|---|---|---|
| TypeScript | 83 | 77.0 | 68.3 |
| Python | 56 | 75.6 | 66.9 |
| Rust | 45 | 74.9 | 67.8 |
| Go | 40 | 76.7 | 67.6 |
| Java | 28 | 66.9 | 58.4 |
| C++ | 21 | 64.0 | 54.9 |
| JavaScript | 15 | 79.2 | 69.4 |
What if I use both?
- Write the shared instructions once, in AGENTS.md at the repo root. What to put in it.
- Claude Code: import
@AGENTS.mdin a CLAUDE.md; without that, a CLAUDE.md hides AGENTS.md from it. - Cursor: put rules in
.cursor/rules/*.mdc; a plain.mdthere is ignored. It reads AGENTS.md too.
AGENTS.md vs CLAUDE.md · Which files each agent reads · Make a repo agent-ready
From the docs: code.claude.com/memory (new tab) · code.claude.com/skills (new tab) · cursor.com/docs/rules (new tab) · cursor.com/skills (new tab) · cursor.com/context/rules (new tab) · cursor.com/customization/rules (new tab) · cursor.com/using (new tab)
Boards: best set up for Claude Code · best set up for Cursor
More comparisons: Claude Code vs Codex · Gemini CLI vs Claude Code · Cursor vs Codex · Aider vs Claude Code · OpenHands vs Claude Code · Pi vs Claude Code · Kimi Code CLI vs Claude Code · Devin vs Claude Code · Codex vs Gemini CLI