compozy
compozy/compozy/CLAUDE.md
most 500 lines; extract before growing an oversized file. - Before changing a test, identify its invariant, owning layer, and existing suite. Reuse that suite and suitable utilities. Add coverage
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
compozy/compozy/CLAUDE.md
most 500 lines; extract before growing an oversized file. - Before changing a test, identify its invariant, owning layer, and existing suite. Reuse that suite and suitable utilities. Add coverage
compozy/compozy/internal/CLAUDE.md
Runtime Applies to `internal/` and `cmd/compozy`. Root `CLAUDE.md` owns compatibility, delivery, and test placement. Use `eng-code-guidelines` for project Go conventions and `eng-test-conventions` when editing Go tests
compozy/compozy/web/CLAUDE.md
tone. A generic need with no primitive goes to `packages/ui` with story and test, callsites migrated in the same change; a domain composite stays in `src/systems/ /components/`. `compozy-ui-reuse
anthropics/claude-agent-sdk-demos/excel-demo/agent/CLAUDE.MD
formatting when modifying spreadsheets - Provide clear explanations of any formulas or calculations you create - Test formulas to ensure they produce correct results - When creating new spreadsheets, use clear headers
marketcalls/openalgo/CLAUDE.md
trough persisted as zero on most stop paths. Each is pinned by a test marked `PORTED DEFECT`. Full reference: [`docs/prompt/strategy_rms_documentation.md`](docs/prompt/strategy_rms_documentation.md). ### An order path decides once, under the lock
stellarlinkco/myclaude/memorys/CLAUDE.md
Contract: Claude Code performs intake, context gathering, planning, and verification only; every edit or test must be executed via skill(`codeagent`). 3. Tooling & Safety Rules: - Capture errors, retry once
microsoft/clarity/CLAUDE.md
Every byte matters. ## Build & Development Commands ### Installation **ALWAYS run `yarn install` before building or testing.** (~25s, peer dependency warnings are normal) ### Building ```bash yarn build # All packages (~45s, Lerna parallel
addyosmani/web-quality-skills/CLAUDE.md
lines 3. Move detailed content to `references/` 4. Update version in frontmatter ### Running tests ```bash # Validate skill format for skill in skills/*/; do npx skills-ref validate "$skill" || exit
jeremylongshore/tons-of-skills-marketplace/CLAUDE.md
enforced). **Contributor guidelines live in `AGENTS.md`** — project structure, build/test/dev commands, style and naming, test conventions, commit/PR expectations, and the merge gates. Read it before starting work. (Session protocol lives
cocoindex-io/cocoindex-code/CLAUDE.md
code search tool built on top of [CocoIndex v1](https://cocoindex.io/docs-v1/llms.txt). ## Build and Test Commands This project uses [uv](https://docs.astral.sh/uv/) for project management. ```bash uv sync # Install
jgravelle/jcodemunch-mcp/CLAUDE.md
main` by name; `enforce_admins` and `strict` ON; `release.yml` dispatched with a version, Test PyPI first, trusted publishing). ⚠⚠ The gate caught its own author four times before it merged
zilliztech/memsearch/CLAUDE.md
guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Build & Test Commands ```bash # Install in development mode uv sync --all-extras # Run all tests (use python
centminmod/my-claude-code-setup/CLAUDE.md
lines) | | memory/patterns.md | CLAUDE-patterns.md | Survives CLAUDE.md reset | | memory/architecture.md | CLAUDE-decisions.md | Survives CLAUDE.md reset | | memory/build.md | Build, Test & Verify section | Survives CLAUDE.md reset | All optional — check existence first. Exclude CLAUDE.md and CLAUDE-*.md from
BytePioneer-AI/codex-host/CLAUDE.md
conflate Harness, Model, Provider, Account, or Billing Source. ## Implementation Principles - Inspect related implementations, tests, contracts, and documentation before making changes. Prefer established repository patterns and public APIs over parallel implementations
stripe/stripe-go/.claude/CLAUDE.md
stripe-go ## Testing - Run all tests: `just test` - Run tests for a single package: `just test ./invoice` - Lint: `just lint` (uses go vet + staticcheck) - Benchmarks: `just bench` ## Formatting - Format: `just
Windy3f3f3f3f/claude-code-from-scratch/CLAUDE.md
Test Project Rules @./.claude/rules/chinese-greeting.md This is a test project for mini-claude feature validation
huggingface/OpenEnv/CLAUDE.md
principles, trade-off decisions 2. **Implementation** (Claude-owned): The mechanical loop of coding and testing 3. **Review** (collaborative): Claude catches bugs, flags alignment questions for humans ### Getting Started Skills
chrisryugj/korean-law-mcp/CLAUDE.md
뒤에 만든다 — 워크플로는 같은 버전이 이미 레지스트리에 있으면 게시를 건너뛰고 검증(typecheck·test·build·verify:package·audit)만 릴리스 시점에 재확인한다. > - **🚫 이 레포에서 `fly deploy` 직접 실행 절대 금지** — 통합
Natively-AI-assistant/natively-cluely-ai-assistant/CLAUDE.md
faster, cheaper, and provides structural context such as callers, dependents, affected flows, and test coverage that direct file scanning cannot provide. ### When to use graph tools first * **Exploring code
kayba-ai/agentic-context-engine/CLAUDE.md
that `ace` is built on (see `docs/design/PIPELINE_DESIGN.md`) - `ace-eval/` — evaluation framework (submodule, separate repo) - `tests/` — unit/integration tests (pytest) - `examples/` — runnable demos grouped by integration - `agent-guides/` — internal development guides
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
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 Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.