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.
nicolargoCLAUDE.mdnicolargo/glances/CLAUDE.md
strict confinement blocks host file access at the open stage, not the read stage. ### Security Glances runs unauthenticated by default — this is intentional and documented. Most users deploy on private
No other project uses it yet
surrealdbCLAUDE.mdsurrealdb/surrealdb/CLAUDE.md
execution, storage keys, or import/export, consult `SECURITY_GUIDE.md` and confirm the relevant invariants still hold. - Security model and review invariants: `SECURITY_GUIDE.md` - General code review checklist: `REVIEW.md` - Architecture decision records: `doc/adr/` - SurrealQL
Steady2 mentions in 2 weeks
No other project uses it yet
surrealdbCLAUDE.mdsurrealdb/surrealdb/surrealism/CLAUDE.md
wasm32-wasip2`, optimizes with wasm-opt, pre-initialises it by snapshotting `init` (see Security Model), packs into a `.surli` archive. - **Run:** `surreal ext run [--fn ] [args...]` — loads the archive, invokes
No other project uses it yet
davila7CLAUDE.mddavila7/claude-code-templates/docs/CLAUDE.md
type has specific structure: **Agents** (162 total) - AI specialists organized by category (Development, Data/AI, Security, Business, etc.) - Stored in `cli-tool/components/agents/{category}/{name}.md` - Installation: `--agent ` **Commands** (210 total
Steady15 mentions in 2 weeks
No other project uses it yet
projectdiscoveryCLAUDE.mdprojectdiscovery/nuclei/CLAUDE.md
repo's known vulnerabilities and recurring weak spots. Check it before writing or reviewing security-sensitive code
No other project uses it yet
tirth8205CLAUDE.mdtirth8205/code-review-graph/CLAUDE.md
clients. - File reads: read the bytes once, hash them, then parse the same bytes. ## Security Invariants - No `eval()`, `exec()`, `pickle` or `yaml.unsafe_load()`. - No `shell=True` in subprocess calls. - `_validate
Steady6 mentions in 2 weeks
No other project uses it yet
Zackriya-SolutionsCLAUDE.mdZackriya-Solutions/meetily/CLAUDE.md
reintroduce the archived FastAPI backend as a supported requirement. 5. **Legacy FastAPI Security Context**: The archived FastAPI/CORS behavior is unsupported legacy code and must not be treated as a supported
Steady3 mentions in 2 weeks
1 project uses a version of this
garrytanCLAUDE.mdgarrytan/gbrain/CLAUDE.md
false` set by `src/cli.ts`) from untrusted agent-facing callers (`remote: true` set by `src/mcp/server.ts`). Security-sensitive operations like `file_upload` tighten filesystem confinement when `remote=true` and default to strict
Steady42 mentions in 2 weeks
No other project uses it yet
supermemoryaiCLAUDE.mdsupermemoryai/supermemory/CLAUDE.md
shared packages - Database migrations handled through Drizzle Kit - Schema types automatically generated and shared ## Security & Best Practices ### Authentication - Better Auth handles user authentication and organization management - API key authentication
No other project uses it yet
simstudioaiCLAUDE.mdsimstudioai/sim/CLAUDE.md
generateShortId()` from `@sim/utils/id`, never `randomUUID`, `nanoid`, or `uuid`: the helpers also work in non-secure (HTTP) browsers. `check:utils` bans the inline forms and names the replacement. It cannot catch
Steady47 mentions in 2 weeks
No other project uses it yet
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/engineering-team/CLAUDE.md
frontend, senior-backend, senior-fullstack - senior-qa, senior-devops, senior-secops - code-reviewer, senior-security - aws-solution-architect, ms365-tenant-manager, google-workspace-cli, tdd-guide, tech-stack-evaluator, epic
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/project-management/CLAUDE.md
atlassian-admin/`) **Focus:** Suite administration, user management, integrations **Scripts:** - `scripts/permission_audit_tool.py` — Analyzes permission schemes for security gaps **Key Workflows:** - User provisioning and permissions - SSO/SAML configuration - App marketplace management - Performance monitoring ### Atlassian
Steady28 mentions in 2 weeks
No other project uses it yet
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/ra-qm-team/CLAUDE.md
CAPA system management, root cause analysis - quality-documentation-manager - DHF, DMR, DHR management **Risk & Security (2 skills):** - risk-management-specialist - ISO 14971 compliance, risk analysis - information-security-manager-iso27001
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/standards/CLAUDE.md
workflow, conventional commits, branching strategy 4. **documentation/** - Markdown quality, structure consistency, living docs 5. **security/** - Secret detection, dependency security, input validation ## When to Reference Standards ### Communication Standards **Reference when:** - Writing
swagger-apiCLAUDE.mdswagger-api/swagger-ui/CLAUDE.md
swagger-client 3.36.0 - OpenAPI client - js-yaml 4.1.1 - YAML parsing - remarkable 2.0.1 - Markdown rendering **Security:** - DOMPurify 3.2.6 - HTML sanitization (CRITICAL for XSS prevention) - serialize-error 8.1.0 - Error serialization **Build Tools
No other project uses it yet
DonchitosCLAUDE.mdDonchitos/Claude-Code-Game-Studios/studio-tests/CLAUDE.md
check, content-audit, code-review, tech-debt, scope-check, estimate, perf-profile, asset-audit, security-audit, test-evidence-review, test-flakiness team → team-combat, team-narrative, team-audio, team-level
Steady8 mentions in 2 weeks
No other project uses it yet
OpenZeppelinCLAUDE.mdOpenZeppelin/openzeppelin-contracts/CLAUDE.md
deciding whether a feature belongs in the library — open an issue first. - Security assessments or audit opinions. - New ERC interfaces or standards without explicit direction. - Restructuring tests without a corresponding
1 project uses a version of this
VoltAgentCLAUDE.mdVoltAgent/awesome-claude-code-subagents/CLAUDE.md
specialists/ # Language/framework experts (TypeScript, Python, etc.) 03-infrastructure/ # DevOps, cloud, Kubernetes, etc. 04-quality-security/ # Testing, security auditing, code review 05-data-ai/ # ML, data engineering, AI specialists 06-developer
Surging3 mentions in 2 weeks
1 project uses a version of this
apacheCLAUDE.mdapache/skywalking/CLAUDE.md
Rare exceptions: propagating OpenTelemetry context where the whole industry has standardised on `ThreadLocal`, or security principals enforced by a framework. In all other cases, prefer an explicit API extension, even
No other project uses it yet
plotlyCLAUDE.mdplotly/dash/CLAUDE.md
front: - `COMMANDS.md` - build, test, lint commands - `ARCHITECTURE.md` - backend, callbacks, pages, background callbacks, stores, async, security - `RENDERER.md` - frontend, crawlLayout, Redux store, clientside API - `COMPONENTS.md` - component system, generation, resources - `TESTING.md` - test framework
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.
