Skip to content
Agent Friendly Code

Devin vs Claude Code: which do top repos set up for?

Claude Code averages higher: 68.0 for Devin and 71.9 for Claude Code, across 402 repos. Devin scores higher on 36, Claude Code on 361, and 5 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
Devin: AGENTS.mdCLAUDE.md.cursor/rules/*.mdc.devin/blueprint.yaml.agents/skills/
Claude Code: CLAUDE.md.claude/CLAUDE.md.claude/rules/CLAUDE.local.mdAGENTS.md.claude/AGENTS.md
Reads AGENTS.md
Devin: Always
Claude Code: Only when there is no CLAUDE.md
Reads CLAUDE.md
Devin: Yes
Claude Code: Yes
From its docs
Devin: Looks for AGENTS.md before it starts coding and includes its first 16 KiB. Pulls CLAUDE.md and Cursor rule files into its Knowledge. Setup comes from its environment snapshot, which .devin/blueprint.yaml can define.
Claude Code: Reads AGENTS.md only when no CLAUDE.md, .claude/CLAUDE.md or CLAUDE.local.md is found (v2.1.277 and later). A CLAUDE.md that imports @AGENTS.md loads both, as does a setting.
Repos with its own file
Devin: AGENTS.md: 207 of 402 (51%)
Claude Code: CLAUDE.md only: 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?

Share of each agent's score that a check carries, where Devin and Claude Code differ most
CheckDevinClaude Code
AGENTS.md / CLAUDE.md7%13%
Skills (.agents/skills)5%0%
Cursor rules (.cursor/rules)4%0%
Test suite11%13%
Linter / formatter config6%8%
Type configuration6%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 Devin than Claude Code?

Which repos are set up better for Claude Code than Devin?

Which one leads in each language?

Average Devin and Claude Code scores of the repos in each language; the higher is in bold
LanguageReposDevinClaude Code
TypeScript8373.377.0
Python5672.275.6
Rust4570.774.9
Go4071.576.7
Java2862.366.9
C++2160.164.0
JavaScript1574.379.2

What if I use both?

  1. Write the shared instructions once, in AGENTS.md at the repo root. What to put in it.
  2. Devin: includes the first 16 KiB of AGENTS.md; .devin/blueprint.yaml can define its environment.
  3. Claude Code: import @AGENTS.md in 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: docs.devin.ai/environment (new tab) · docs.devin.ai/knowledge-onboarding (new tab) · docs.devin.ai/skills (new tab) · docs.devin.ai/agents-md (new tab) · docs.devin.ai/git-backed-blueprints (new tab) · code.claude.com/memory (new tab) · code.claude.com/skills (new tab)

Boards: best set up for Devin · best set up for Claude Code

More comparisons: Claude Code vs Cursor · 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 · Codex vs Gemini CLI