How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
jens-duttkeCLAUDE.mdjens-duttke/usage-monitor-for-claude/.claude/CLAUDE.md
drop, so a "reset pending" flag cleared by a drop would never clear again ## Security & Transparency - All URLs and API endpoints as top-level constants - no dynamic URL construction
Othmane-KhadriCLAUDE.mdOthmane-Khadri/YALC-the-GTM-operating-system/CLAUDE.md
Affiliate signup if you don't have a lemlist account yet: <https://get.lemlist.com/skrtwnkxw60i> ## Security - **NEVER display API keys, tokens, or secrets from `.env.local` in chat output.** Mask all credentials
zenml-ioCLAUDE.mdzenml-io/kitaru/CLAUDE.md
changelog.d/ . .md`, where the section is one of `added`, `changed`, `deprecated`, `removed`, `fixed`, or `security` (see `changelog.d/README.md`). Any slug works in place of the number while the PR does
vizra-aiCLAUDE.mdvizra-ai/vizra-adk/CLAUDE.md
Clean old traces regularly: `php artisan vizra:trace:cleanup` - Monitor token usage in dashboard ## Security Notes - API keys stored in .env file - Session-based isolation for multi-user systems - Tool
codervisorCLAUDE.mdcodervisor/leanspec/CLAUDE.md
Split large changes into stacked PRs. - Request review from at least one team member. ## Security - Never commit secrets, tokens, or credentials. Use environment variables. - Validate all external input at system
HarmonicSecurityCLAUDE.mdHarmonicSecurity/claudit-sec/CLAUDE.md
CLAUDIT-SEC — Claude Security Audit Tool ## Project Overview CLAUDIT-SEC is a read-only, single-file security audit tool for macOS that inspects Claude Desktop and Claude Code configuration, scheduled
yonatangrossCLAUDE.mdyonatangross/orchestkit/CLAUDE.md
Overview **OrchestKit** — Claude Code plugin for AI-assisted development with built-in best practices, security patterns, and quality gates. For live component counts (skills / agents / hooks / per-session token cost
openseshCLAUDE.mdopensesh/KARIMO/CLAUDE.md
GETTING-STARTED.md](.karimo/docs/GETTING-STARTED.md) | Installation walkthrough | | [PHASES.md](.karimo/docs/PHASES.md) | Adoption phases explained | | [SAFEGUARDS.md](.karimo/docs/SAFEGUARDS.md) | Code integrity, security, Greptile | --- ## Learnings Project-specific learnings are stored in `.karimo/learnings/` (categorized directories: patterns, anti-patterns, project-notes
pavel-molyanovCLAUDE.mdpavel-molyanov/molyanov-ai-dev/CLAUDE.md
team or swarm, orchestrate bounded subagent work with the runtime's team tools. ## Security - NEVER ask user to write secrets in chat - Instead: provide instructions where to store them securely
PlamenTSVCLAUDE.mdPlamenTSV/plamen/CLAUDE.md
Plamen — Security Auditor You are **Plamen**, an autonomous Web3 security auditing agent (v2.2.4). Methodology files live under `~/.claude/rules/` and `~/.claude/prompts/` (or `~/.codex/plamen/...` on Codex) — both are install-created symlinks into
MadAppGangCLAUDE.mdMadAppGang/claude-code/CLAUDE.md
validate before save 3. **Team Ready** - Auto-install, consistent setup, no drift 4. **Security First** - No secrets in git, personal tokens, clear docs 5. **Developer Experience** - Smart defaults, clear errors
ship-studioCLAUDE.mdship-studio/ship-studio/CLAUDE.md
# Ship Studio Development Guidelines ## Feature Overview Ship Studio is a desktop app for web
DobermanCoreCLAUDE.mdDobermanCore/Doberman-Core/CLAUDE.md
every slice) **Step 1 — Read the slice.** Read its objective, files, changes, security considerations, edge cases, expected output, suggested tests, and suggested commit message (from your local development plan, with
KimYx0207CLAUDE.mdKimYx0207/Meta_Kim/CLAUDE.md
blueprint may include: - product direction - UX flow - UI system - frontend - backend - database - auth / security - motion / interaction polish - tests / QA - release / install path - feedback and evolution The blueprint does not need
RealMikeChongCLAUDE.mdRealMikeChong/ultra-mcp/CLAUDE.md
keys - View current configuration (with masked API keys) - Reset configuration - API keys are stored securely in your system's config directory ### doctor - Health Check Check installation and configuration health: ```bash
shangyankejiCLAUDE.mdshangyankeji/super-dev/CLAUDE.md
Record generation ### Quality & Review (`super_dev/reviewers/`) - `quality_gate.py` — quality threshold enforcement (default threshold: 90) - `redteam.py` — security red-team analysis - `code_review.py` — automated code review - `ui_review.py` — UI compliance review - `validation_rules.py` — configurable validation rules
loulanyueCLAUDE.mdloulanyue/awesome-claude-notes/CLAUDE.md
/e2e, etc.) - **hooks/** - Trigger-based automations (session persistence, pre/post-tool hooks) - **rules/** - Always-follow guidelines (security, coding style, testing requirements) - **mcp-configs/** - MCP server configurations for external integrations - **scripts/** - Cross-platform
8b-isCLAUDE.md8b-is/smart-tree/CLAUDE.md
args, initializes logging 2. **Exclusive modes** run locally and exit: `--mcp`, `--version`, `--completions`, `--man`, `--security-scan`, `--terminal`, `--dashboard`, `--http-daemon`, `--guardian-daemon`, daemon control flags 3. **Everything else** (the common
circuit-synthCLAUDE.mdcircuit-synth/circuit-synth/CLAUDE.md
Safety**: Type hints required for all functions - **Code Quality**: black, isort, ruff (automated linting) - **Security**: bandit, safety (automated scanning) - **CI/CD**: Automated enforcement on every PR - **Documentation**: Complete docstrings
avivlCLAUDE.mdavivl/claude-007-agents/CLAUDE.md
attribution requirements **For configuration**: Include `@team-configurator` + technical expert **For API**: Include `@api-architect` + security expert **For database**: Include `@database-admin` + performance expert --- # Claude Code - Advanced AI Agent System **Version
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.
