Gemini CLI vs Claude Code: which do top repos set up for?
Claude Code averages higher: 63.5 for Gemini CLI and 71.9 for Claude Code, across 402 repos. Gemini CLI scores higher on 4, Claude Code on 396, 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
- Gemini CLI:
GEMINI.md.agents/skills/ - Claude Code:
CLAUDE.md.claude/CLAUDE.md.claude/rules/CLAUDE.local.mdAGENTS.md.claude/AGENTS.md - Reads AGENTS.md
- Gemini CLI: Only when configured to
- Claude Code: Only when there is no CLAUDE.md
- Reads CLAUDE.md
- Gemini CLI: No
- Claude Code: Yes
- From its docs
- Gemini CLI: Reads GEMINI.md from the global file, the workspace and its parent directories, and one per subdirectory once a tool reaches it. AGENTS.md loads once listed in the
context.fileNamesetting. - 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.
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 | Gemini CLI | Claude Code |
|---|---|---|
| GEMINI.md | 11% | 0% |
| AGENTS.md / CLAUDE.md | 8% | 13% |
| Skills (.agents/skills) | 4% | 0% |
| Reproducible dev env | 8% | 12% |
| Test suite | 10% | 13% |
| Type configuration | 10% | 8% |
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 Gemini CLI than Claude Code?
- google-gemini/gemini-cli82.4 vs 79.6 for Claude Code
- symfony/symfony45.7 vs 43.4 for Claude Code
- discourse/discourse93.4 vs 91.2 for Claude Code
- apache/seatunnel71.4 vs 70.8 for Claude Code
Which repos are set up better for Claude Code than Gemini CLI?
- calcom/cal.diy86.8 vs 70.7 for Gemini CLI
- prisma/orm78.9 vs 63.0 for Gemini CLI
- scikit-learn/scikit-learn86.8 vs 71.0 for Gemini CLI
- directus/directus83.6 vs 67.9 for Gemini CLI
- github/spec-kit87.2 vs 71.6 for Gemini CLI
Which one leads in each language?
| Language | Repos | Gemini CLI | Claude Code |
|---|---|---|---|
| TypeScript | 83 | 67.6 | 77.0 |
| Python | 56 | 66.9 | 75.6 |
| Rust | 45 | 67.5 | 74.9 |
| Go | 40 | 67.6 | 76.7 |
| Java | 28 | 58.8 | 66.9 |
| C++ | 21 | 55.5 | 64.0 |
| JavaScript | 15 | 69.6 | 79.2 |
What if I use both?
- Write the shared instructions once, in AGENTS.md at the repo root. What to put in it.
- Gemini CLI: list AGENTS.md in the
context.fileNamesetting, or keep a GEMINI.md. - Claude Code: import
@AGENTS.mdin a CLAUDE.md; without that, a CLAUDE.md hides AGENTS.md from it.
AGENTS.md vs CLAUDE.md · Which files each agent reads · Make a repo agent-ready
From the docs: geminicli.com/gemini-md (new tab) · geminicli.com/skills (new tab) · code.claude.com/memory (new tab) · code.claude.com/skills (new tab)
Boards: best set up for Gemini CLI · best set up for Claude Code
More comparisons: Claude Code vs Cursor · Claude Code vs Codex · 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