How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
ruanrongmanCLAUDE.mdruanrongman/IntelliConnect/CLAUDE.md
infrastructure with Thing Model abstraction. ## Technology Stack - **Backend**: Java 21, Spring Boot 3.5.7, Spring Security, JWT, Maven - **Frontend**: Vue 3 (in `/web` directory) - **AI/LLM**: LangChain4j, Dashscope/Qwen3, GLM/Zhipu, DeepSeek v4, SiliconFlow
undeadlistCLAUDE.mdundeadlist/claude-code-agents/CLAUDE.md
Agents (11) - NON-OVERLAPPING SCOPE | Type | Prompt | Does | |------|--------|------| | `bug-auditor` | `agents/bug-auditor.md` | Runtime bugs (NOT security) | | `code-auditor` | `agents/code-auditor.md` | Code quality (NOT security/bugs) | | `security-auditor` | `agents/security-auditor.md` | ALL security (single authority
agentfrontCLAUDE.mdagentfront/frontmcp/CLAUDE.md
configurations ✅ **Do**: Achieve 95%+ test coverage ✅ **Do**: Use strict TypeScript settings ✅ **Do**: Write comprehensive security documentation ✅ **Do**: Use `unknown` instead of `any` for generic type defaults ✅ **Do**: Validate hooks match
GitHubCLAUDE.mdgithub/gh-aw-firewall/CLAUDE.md
README.md](README.md)** - Main project documentation and usage guide - **[docs/environment.md](docs/environment.md)** - Environment variable configuration and security best practices - **[LOGGING.md](LOGGING.md)** - Comprehensive logging documentation - **[docs/logging_quickref.md](docs/logging_quickref.md)** - Quick reference for log queries
ariel-frischerCLAUDE.mdariel-frischer/autospec/CLAUDE.md
describe user-visible behavior: CLI changes, config changes, compatibility changes, docs users rely on, security fixes, or bug fixes users can observe. Maintainer-only process, governance, prompt hygiene, test strategy
AgriciDanielCLAUDE.mdAgriciDaniel/claude-repurpose/CLAUDE.md
directories - Agents invoked via Agent tool, never via Bash - Python deps install into `~/.claude/skills/repurpose/.venv/` ## Security Rules - No hardcoded credentials or secrets - URL validation in all scripts (block private IPs, loopback
AWSCLAUDE.mdawslabs/visual-asset-management-system/backend/CLAUDE.md
# CLAUDE.md -- VAMS Python Lambda Backend > Auto-loaded when Claude Code works within `backend/`. Authoritative
AWSCLAUDE.mdawslabs/visual-asset-management-system/CLAUDE.md
explicitly overridden). --- ## 🚨 **Critical Rules** These rules apply project-wide. Violations will cause deployment failures, security issues, or runtime errors. ### **Rule 1: Never Use Pydantic v2 Syntax** The backend uses Pydantic
AWSCLAUDE.mdawslabs/visual-asset-management-system/documentation/CLAUDE.md
Core concepts: databases, assets, files, pipelines, metadata, permissions ├── architecture/ # Architecture overview, details, AWS resources, security, networking, data model ├── deployment/ # Prerequisites, deploy, config reference, external S3, update, uninstall ├── user-guide/ # Getting
AWSCLAUDE.mdawslabs/visual-asset-management-system/infra/CLAUDE.md
subnets } : undefined, environment: { /* handler-specific env vars only; resource names resolve via SSM */ }, }); ``` ### Required Security Calls (Every Lambda Builder) After creating the function, every builder MUST call these five helpers
AWSCLAUDE.mdawslabs/visual-asset-management-system/infra/lib/nestedStacks/pipelines/CLAUDE.md
output path conventions. See `infra/CLAUDE.md` for cross-stack patterns (lambda builder, service helper, security helpers). --- ## Pipeline Nested Stack Pattern Each pipeline follows a consistent structure: ``` lib/nestedStacks/pipelines/{category}/{pipelineName}/ {pipelineName}Builder-nestedStack.ts
AWSCLAUDE.mdawslabs/visual-asset-management-system/tools/VamsCLI/CLAUDE.md
value shape** — `vams_…` keys, JWTs, `Bearer …`, and presigned-URL `X-Amz-Signature` / `X-Amz-Security-Token` parameters are scrubbed even when the key name gives no hint, which covers
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.
