big-AGI
enricoros/big-AGI/CLAUDE.md
procedure alias in it resolves to bare `t.procedure` (the cloud layer lives on `dev`) #### Security Considerations - Server-side keys come from env vars only; client-held keys are user-supplied
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.
enricoros/big-AGI/CLAUDE.md
procedure alias in it resolves to bare `t.procedure` (the cloud layer lives on `dev`) #### Security Considerations - Server-side keys come from env vars only; client-held keys are user-supplied
Dimillian/IceCubesApp/CLAUDE.md
timeline, mentions, and accounts ### Important Implementation Details - **Multi-account**: Managed through `AppAccountsManager` with secure storage - **Push Notifications**: Custom proxy server implementation for privacy - **Theme System**: Extensive customization with
chillzhuang/SpringBlade/CLAUDE.md
Cloud Gateway(WebFlux) | | ORM | MyBatis-Plus + dynamic-datasource-spring-boot4-starter | | 安全 | blade-core-secure(JWT + 可选 AES 加密 + SM2 国密登录) | | 缓存 | BladeRedis(Protostuff 序列化,响应式 Gateway 侧用 Reactive Redis
mermaid-js/mermaid-live-editor/CLAUDE.md
Both edit either the diagram code or the mermaid config JSON depending on `editorMode`. ### Security States loaded from URLs pass through `sanitizeConfig` (state.svelte.ts), which detects unsafe mermaid config (XSS vectors
j3ssie/osmedeus/CLAUDE.md
TOKEN); DRY_RUN=1 to preview ``` ## Architecture Overview Osmedeus is a workflow engine for security automation. It executes YAML-defined workflows with support for multiple execution environments. ### Layered Architecture ``` CLI/API
hieunc229/mailflare/CLAUDE.md
RATE_LIMIT`) since it skips Turnstile. Device keys are listed and revoked under Settings → Security (`/api/devices`), hidden from the API keys list, and `deleteUserSessions` revokes them all (password change, reset
Arthur-Ficial/apfel/CLAUDE.md
Proper error types. Real token counts. - **Swift 6 strict concurrency.** No data races. - **Usable security.** Secure defaults that don't get in the way. - **TDD always, red-to-green
Steady2 mentions in 2 weeks
No other project uses it yet
airweave-ai/airweave/CLAUDE.md
path (just `host.com/{endpoint}`) - Use logger from `ctx` (API) or `sync_context` (during sync) - Security: never use `random.*` for security values (ruff S311); use `secrets` module ### Frontend (TypeScript) - TailwindCSS with
czlonkowski/n8n-skills/CLAUDE.md
user first) - Secret-free/domain-free templates in `assets/`; fresh secrets generated on the box; secure defaults; DNS/ports preflight; Day-2 update/backup/restore - Python Code nodes need task runners in external mode
No other project uses it yet
op7418/CodePilot/CLAUDE.md
test.ts` - fail-closed:分类器出错 / 空暂存集 / 非 `docs` 判定一律走全量门禁(防「前置失败被静默放行」回归) 高风险 docs(release / security / runtime / provider / permission / DB schema)即便走 docs 快路,也应手动跑 `npm run test`(必要时 build / smoke
FlorianBruniaux/claude-code-ultimate-guide/CLAUDE.md
printable summary ├── cowork.md # Cowork redirect page ├── core/ # Architecture, methodologies, releases, known-issues, visual-reference ├── security/ # security-hardening, sandbox-isolation, sandbox-native, production-safety, data-privacy ├── ecosystem/ # ai-ecosystem, mcp-servers
No other project uses it yet
aptos-labs/aptos-core/CLAUDE.md
definitions used everywhere - `aptos-vm` - VM integration and transaction execution - `aptos-crypto` - Cryptographic primitives (security-critical) - `aptos-api-types` - API request/response types ## Safety-Critical Code These directories require extra care
No other project uses it yet
Provenance-Emu/Provenance/CLAUDE.md
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code
simbasjungles/free-my-tv/CLAUDE.md
kill-server; adb nodaemon server &`), or allow the terminal app under System Settings → Privacy & Security → Local Network. 7. **Tell them what the switch does** before they make it: the home
Steady2 mentions in 2 weeks
No other project uses it yet
crytic/slither/CLAUDE.md
slither/ ├── analyses/ # Data dependency, dominators, control flow ├── core/ # Core classes: SlitherCore, Contract, Function ├── detectors/ # Security checks (subclass AbstractDetector) ├── printers/ # Output formatters (subclass AbstractPrinter) ├── slithir/ # Intermediate representation for analysis ├── solc_parsing
wiltodelta/remove-ai-watermarks/CLAUDE.md
binding registry snapshot is stale; rerun it without `--check` to refresh the snapshot. Triaged security blocks and their recheck procedure, environment recovery, CI behavior, and fixture policy live in [`docs/development.md
androguard/androguard/CLAUDE.md
large `workspace/output/` trees. - Do not invent APIs; read `androguard/application.py` and `androguard/cli/main.py` when unsure. - Authorized security analysis only; do not help with malware distribution or unauthorized access
rundeck/rundeck/CLAUDE.md
Groovy auto-generates getters/setters — do NOT implement them explicitly unless custom logic is needed. ### Security Avoid command injection, XSS, SQL injection. Use parameterized queries and escape user input. ### Simplicity Only
No other project uses it yet
Q00/ouroboros/CLAUDE.md
introduced by this PR? 5. If scope is split, does immediate user-data or security risk remain? Use these decisions: - Q1 + Q2: **Changes Requested**. - Q3 + Q5: stop and revisit
No other project uses it yet
Helicone/helicone/CLAUDE.md
useJawnClient()` ### Database - PostgreSQL with snake_case naming - ClickHouse for analytics - Proper RLS policies for security ## Tech Stack ### Frontend - Next.js 14 with React 18.3.1 - TypeScript, Tailwind CSS, Radix UI - Zustand
No other project uses it yet
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.