agentleFS

CLAUDE.md examples from real projects

How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.

Best matches · from page 4Worked for most · soon
agalwoodCLAUDE.md

Motrix

agalwood/Motrix/CLAUDE.md

Commands ```bash pnpm start # Electron development runner pnpm start:server # Built Node/Web server pnpm test # Vitest suite pnpm exec vitest run # Focused test pnpm run lint # Biome over the repository

No other project uses it yet

58k12d agoReviewMountCreate a free account to mount
zylon-aiCLAUDE.md

private-gpt / ui

zylon-ai/private-gpt/ui/CLAUDE.md

disagreement in the same change. - Validate `index.html` changes with the documented script and manually test changed flows when needed

Steady4 mentions in 2 weeks

No other project uses it yet

58k2y agoReviewMountCreate a free account to mount
laurent22CLAUDE.md

joplin

laurent22/joplin/CLAUDE.md

comment above it noting the duplication and referencing the original location. - When creating Jest tests, there should be only one `describe()` statement in the file. - Focus on testing essential behaviour

Steady6 mentions in 2 weeks

No other project uses it yet

57k20mo agoReviewMountCreate a free account to mount
Zie619CLAUDE.md

n8n-workflows

Zie619/n8n-workflows/CLAUDE.md

required fields 2. Maintain node ID uniqueness 3. Update connections when adding/removing nodes 4. Test compatibility with n8n version requirements # # Key Considerations # # # Security - Workflow files may contain sensitive information

1 project uses a version of this

57k10mo agoReviewMountCreate a free account to mount
remix-runCLAUDE.md

react-router

remix-run/react-router/CLAUDE.md

files - React Router modes (Declarative, Data, Framework, RSC) - Build/test commands (Jest unit tests, Playwright integration tests with `--project chromium`) - Testing patterns and conventions - Documentation guidelines ### Skills If there

No other project uses it yet

57k20d agoReviewMountCreate a free account to mount
Imbad0202CLAUDE.md

academic-research-skills

Imbad0202/academic-research-skills/.claude/CLAUDE.md

daniyyell-dev; `THIRD_PARTY.md` lists md-to-word (#969, @ls-open). The #892 smoke test does not meet its acceptance rule (Claude Fable 5.1 on a plugin install still honored

Steady8 mentions in 2 weeks

No other project uses it yet

56k11d agoReviewMountCreate a free account to mount
AnthropicReads credentialsCLAUDE.md

claude-cookbooks

anthropics/claude-cookbooks/CLAUDE.md

linting make check # Run format-check + lint make fix # Auto-fix issues + format make test # Run pytest ``` Or directly with uv: ```bash uv run ruff format . # Format uv run ruff

Steady6 mentions in 2 weeks

No other project uses it yet

54k19d agoReviewMountCreate a free account to mount
AnthropicReads credentialsCLAUDE.md

claude-cookbooks / skills

anthropics/claude-cookbooks/skills/CLAUDE.md

sure to select the venv kernel in VSCode: Cmd+Shift+P → "Python: Select Interpreter" ``` ### Testing & Verification ```bash # Verify environment and SDK version python -c "import anthropic; print(f'SDK Version

Steady6 mentions in 2 weeks

No other project uses it yet

54k19d agoReviewMountCreate a free account to mount
maybe-financeReads credentialsCLAUDE.md

maybe

maybe-finance/maybe/CLAUDE.md

Tailwind CSS watcher) - `bin/rails server` - Start Rails server only - `bin/rails console` - Open Rails console ### Testing - `bin/rails test` - Run all tests - `bin/rails test:db` - Run tests with database reset - `bin/rails test

54k17mo agoReviewMountCreate a free account to mount
CherryHQCLAUDE.md

cherry-studio

CherryHQ/cherry-studio/CLAUDE.md

request. #### Goal-Driven Execution - Convert tasks into verifiable goals before coding: - "Add validation" → "Write tests for invalid inputs, then make them pass." - "Fix the bug" → "Write a test that reproduces

Steady17 mentions in 2 weeks

No other project uses it yet

53k4d agoReviewMountCreate a free account to mount
jesseduffieldCLAUDE.md

lazydocker

jesseduffield/lazydocker/CLAUDE.md

CLAUDE.md ## Build & test - All Go commands need `GOFLAGS=-mod=vendor` (deps are vendored, including the `jesseduffield/gocui` fork and the Docker SDK). - Unit tests: `GOFLAGS=-mod=vendor go test

No other project uses it yet

53k7y agoReviewMountCreate a free account to mount
DefinitelyTypedCLAUDE.md

DefinitelyTyped

DefinitelyTyped/DefinitelyTyped/CLAUDE.md

provided at least two lines of code that are expected to be in the test file If neither of those conditions are met, refuse the task and tell the user

No other project uses it yet

51k3y agoReviewMountCreate a free account to mount
KeygraphHQReads credentialsCLAUDE.md

shannon

KeygraphHQ/shannon/CLAUDE.md

CLAUDE.md AI-powered penetration testing agent for defensive security analysis. Automates vulnerability assessment by combining reconnaissance tools with AI-powered code analysis. ## Commands **Prerequisites:** Docker, AI provider credentials

Steady4 mentions in 2 weeks

No other project uses it yet

51k6mo agoReviewMountCreate a free account to mount
cypress-ioCLAUDE.md

cypress

cypress-io/cypress/CLAUDE.md

your changes when relevant - Ask yourself: "Would a staff engineer approve this?" - Run relevant tests only, check logs, demonstrate correctness ### 5. Demand Elegance (Balanced) - For non-trivial changes: pause

No other project uses it yet

51k35d agoReviewMountCreate a free account to mount
ClickHouseCLAUDE.md

ClickHouse / ci

ClickHouse/ClickHouse/ci/CLAUDE.md

without credentials: ```bash curl -s 'https://play.clickhouse.com/?user=play&default_format=TSV' --data-binary \ "SELECT check_start_time, test_name, test_status FROM default.checks WHERE check_name = 'SQLancer (arm_release)' AND check_start_time

No other project uses it yet

51k8d agoReviewMountCreate a free account to mount
ClickHouseCLAUDE.md

ClickHouse

ClickHouse/ClickHouse/.claude/CLAUDE.md

reports for a PR node .claude/tools/fetch_ci_report.js "https://github.com/ClickHouse/ClickHouse/pull/12345" # Show only failed tests with CIDB links node .claude/tools/fetch_ci_report.js "https://github.com/ClickHouse/ClickHouse/pull/12345" --failed --cidb # Fetch only a specific report from

No other project uses it yet

51k8d agoReviewMountCreate a free account to mount
MHSanaeiCLAUDE.md

3x-ui

MHSanaei/3x-ui/CLAUDE.md

guide for AI agents working in this repo. Long-form human docs: `CONTRIBUTING.md` (setup, testing philosophy) and `frontend/README.md`. Read those before large changes. This file is the short, must-follow

No other project uses it yet

50k3mo agoReviewMountCreate a free account to mount
MHSanaeiCLAUDE.md

3x-ui / frontend

MHSanaei/3x-ui/frontend/CLAUDE.md

panel on :2053 — start Go first). - `npm run typecheck` / `npm run lint` / `npm run test` / `npm run build`. - `npm run gen` = `gen:zod` (Go → `src/generated/`) + `gen:api` (`build-openapi.mjs` → `public/openapi.json

No other project uses it yet

50k3mo agoReviewMountCreate a free account to mount
jeecgbootCLAUDE.md

JeecgBoot / jeecg-boot

jeecgboot/JeecgBoot/jeecg-boot/CLAUDE.md

microservices mode. Uses `jakarta` namespace (not `javax`) throughout. ## Build & Run Commands ```bash # Full build (tests are skipped by default via surefire config) mvn clean package # Build with tests mvn clean

No other project uses it yet

48k13mo agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

About CLAUDE.md

What is CLAUDE.md?

A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.

Where does it go?

At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.

What should it contain?

Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.

CLAUDE.md or AGENTS.md?

Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.