How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Pantheon-SecurityCLAUDE.mdPantheon-Security/medusa/CLAUDE.md
medusa - MEDUSA Security Scanning ## CRITICAL: Release Gate — DO NOT SKIP **Unit tests ALONE are not sufficient.** Before any `git push`, `git tag`, `gh release create`, or `twine upload` — all four
dotCMSCLAUDE.mddotCMS/core/CLAUDE.md
targets whatever `maven.compiler.release` is set to in its own `pom.xml`, historically lower for portability. - **Security**: No hardcoded secrets, validate all input, never log sensitive data - **REST @Schema**: Must match actual
MeisnerDanCLAUDE.mdMeisnerDan/mission-control/CLAUDE.md
Start/stop controls, config summary, schedule display - Auto-refreshes every 5 seconds via `useDaemon()` hook ### Security Model - **No network listener** — pure local process, zero network attack surface - **Credential scrubbing** — all stdout/stderr
toonightCLAUDE.mdtoonight/get-shit-done-for-antigravity/adapters/CLAUDE.md
extended thinking for: | Task Type | Recommended | |-----------|-------------| | Architecture planning | ✅ High effort | | Complex debugging | ✅ High effort | | Security analysis | ✅ High effort | | Simple edits | ❌ Not needed | | Quick iterations | ❌ Overhead too high | ### Effort Levels
ApicurioCLAUDE.mdApicurio/apicurio-registry/CLAUDE.md
labels follow `.claude/rules/labels.md` (reserved `apicurio. .*` key namespace; labels are user-editable, so never store security-relevant state in one). - [ ] Non-variant-specific changes under `storage/impl/` must work across
bonfire-networksCLAUDE.mdbonfire-networks/bonfire-app/.claude/CLAUDE.md
core principles, project structure, coding style, naming, error handling, data/database, UI, testing, security, and Elixir/Phoenix guidelines.** Those apply here in full and supersede anything else. This file only adds usage
MicrosoftCLAUDE.mdmicrosoft/fabric-toolbox/tools/MicrosoftFabricMgmt/CLAUDE.md
Level Warning } ``` **Example output** for a 400 with `moreDetails[0] = { errorCode: "UniversalSecurityFeatureDisabledForWorkspace", message: "Universal security feature is disabled for the workspace" }`: - **Debug**: `Failed to retrieve... Full error: API request failed
MicrosoftCLAUDE.mdmicrosoft/fabric-toolbox/tools/MicrosoftFabricMgmtMCPServer/CLAUDE.md
catch` block in the sentinel wrapper as `"error_type"` = PS exception class name) --- ## Security Constraints - **Never use `shell=True`** in `subprocess.Popen` — use a list of arguments. - **App secrets** passed
janregesCLAUDE.mdjanreges/siteone-crawler/CLAUDE.md
analyzer instances (Accessibility, BestPractice, BrowserConsole, Caching, ContentType, DNS, ExternalLinks, Fastest, Headers, Page404, Redirects, Security, SeoAndOpenGraph, SkippedUrls, Slowest, SourceDomains, SslTls, Technologies) and registers them with `AnalysisManager`. Some analyzers receive config from
ListenarrsCLAUDE.mdListenarrs/Listenarr/.github/CLAUDE.md
markdown # Secure Code Generation Rules for .NET/ASP.NET Core ## Required Repository Context Before making code, dependency, workflow, or documentation changes, review and follow: - `CONTRIBUTING.md` - `BACKEND_ARCHITECTURE.md` - `.github/RULES.md` - `.github/copilot-instructions.md` - `.github/.cursorrules` Repository-specific guidance
s0ld13rrCLAUDE.mds0ld13rr/pentestcode/CLAUDE.md
positives, validates evidence. Read-only. | | **webapp** | subagent | Web application specialist. OWASP Top 10, API security, XSS, SQLi, SSRF. | | **reflector** | subagent | Post-engagement reflection. Analyzes outcomes, generates learned skills, records knowledge
janosmikoCLAUDE.mdjanosmiko/lfk/CLAUDE.md
complex tasks. **Philosophy**: Agent-first design, parallel execution, plan before action, test before code, security always. **Key Principles:** 1. **Agent-First**: Delegate to specialized agents for complex work 2. **Parallel
pocketpawCLAUDE.mdpocketpaw/pocketpaw/docs/CLAUDE.md
start, config, project structure ├── concepts/ # 6 pages — architecture, message bus, agent loop, memory, tools, security ├── channels/ # 10 pages — overview + 9 channel guides ├── backends/ # 8 pages — overview + 6 backend guides + Ollama
ecubusCLAUDE.mdecubus/EcuBus-Pro/CLAUDE.md
after any changes to `src/main/worker/`** | | `npm run worker` | Build worker bundle including native secure-access addon | | `npm run native` | Build all native modules (docan, dolin, someip) | | `npm run docan` / `dolin
always-furtherCLAUDE.mdalways-further/deepfabric/CLAUDE.md
code with black and ruff auto-fix - `make lint` - Run ruff linting checks - `make security` - Run bandit security analysis on deepfabric/ directory ### Testing - `make test` - Run pytest test suite
zentralopensourceCLAUDE.mdzentralopensource/zentral/CLAUDE.md
github/workflows/release-archive.yml](.github/workflows/release-archive.yml) publishes it, for a release tag or for a build of a `security/` branch, so that a fix can be deployed before it is public. Keep these properties
m3ueCLAUDE.mdm3ue/m3u-editor/CLAUDE.md
pull request in `m3u-editor`, both of the following are **required**, not optional: 1. **Security scan** — run `composer security:scan` (runs `composer audit`, `vendor/bin/vet`, `npm audit --audit-level=high
duriantacoCLAUDE.mdduriantaco/skylos/CLAUDE.md
Python, TS/JS, Java, Go, PHP, Rust, and Dart. It detects dead code, security flaws, secrets, dependency CVEs, quality regressions, and AI-generated-code mistakes. The CLI entry point is `skylos.cli
LegacyLandsCLAUDE.mdLegacyLands/legacy-lands-library/CLAUDE.md
login page to complete the login process. // This step is necessary to ensure the security and validity of subsequent API calls. ` ### 9.3 回答语言规范（即你与用户交流时） 1. 你在与用户交互时必须全程使用中文； 2. 若希望临时切换语言，可以明确告知，否则始终保持中文为默认沟通语言
alirezarezvaniCLAUDE.mdalirezarezvani/claude-code-skill-factory/documentation/CLAUDE.md
agent types **Example Agents**: - Code reviewer - Frontend developer - Backend developer - Test automation specialist - Security engineer --- ### PROMPTS_FACTORY_PROMPT.md **Purpose**: Generate domain-specific prompt builders (complete prompt generation systems) **Use for**: Creating specialized
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.
