CLAUDE.md examples from real projects

moltis-orgReads credentialsCLAUDE.md

moltis

moltis-org/moltis/CLAUDE.md

Moltis engineering guide for Claude/Codex agents: Rust architecture, testing, security, and release workflows

No other project uses it yet

affaan-mCLAUDE.md

ECC

affaan-m/ECC/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

affaan-mReads credentialsCLAUDE.md

ECC / examples

affaan-m/ECC/examples/CLAUDE.md

Unit tests for utilities - Integration tests for APIs - E2E tests for critical flows ### 4. Security - No hardcoded secrets - Environment variables for sensitive data - Validate all user inputs - Parameterized queries only

n8n-ioCLAUDE.md

n8n

n8n-io/n8n/.github/CLAUDE.md

visual) | | `ci-` | Continuous integration | | `util-` | Utilities (notifications) | | `build-` | Build processes | | `release-` | Release automation | | `sec-` | Security scanning | Reusable workflows: add `-reusable` or `-callable` suffix. ### Common Tasks **Add workflow:** Create in `workflows

Significant-GravitasReads credentialsCLAUDE.md

AutoGPT / classic

Significant-Gravitas/AutoGPT/classic/CLAUDE.md

agents (saves to `autogpt.yaml`) | | **Deny** | Deny this command (saves to appropriate deny list) | ### Default Security Out of the box, the following are **denied by default**: - Reading sensitive files

No other project uses it yet

AnthropicCLAUDE.md

claude-code

anthropics/claude-code/CLAUDE.md

CLAUDE.md Guidance for Claude Code and other coding agents working in this repository. ## Security hardening for GitHub Actions Workflow jobs in this repository that call Claude run with three protections

garrytanReads credentialsCLAUDE.md

gstack

garrytan/gstack/CLAUDE.md

listener rules, Unicode sanitization at egress, SSE/CDP helpers, setup symlink hardening, and the sidebar security stack all live there, each pinned by a CI tripwire. **Egress receipts at every

No other project uses it yet

electronCLAUDE.md

electron

electron/electron/CLAUDE.md

Default policy: - **Bug fixes** — backport to all active release lines _except the oldest_ - **Security fixes** — backport to all active release lines _including the oldest_ - **Features (semver/minor) and breaking changes (semver/major

No other project uses it yet

browser-useCLAUDE.md

browser-use

browser-use/browser-use/CLAUDE.md

file management - **PopupsWatchdog**: Manages JavaScript dialogs and popups - **SecurityWatchdog**: Enforces domain restrictions and security policies - **DOMWatchdog**: Processes DOM snapshots, screenshots, and element highlighting - **AboutBlankWatchdog**: Handles empty page redirects ### CDP Integration

JuliusBrusseePipes a download into a shellCLAUDE.md

caveman

JuliusBrussee/caveman/CLAUDE.md

# CLAUDE.md — caveman ## README is a product artifact README = product front door. Non-technical people

addyosmaniCLAUDE.md

agent-skills

addyosmani/agent-skills/CLAUDE.md

skills/ → Core skills (SKILL.md per directory) agents/ → Reusable agent personas (code-reviewer, test-engineer, security-auditor, web-performance-auditor) hooks/ → Session lifecycle hooks .claude/commands/ → Slash commands (/spec, /plan, /build, /test

ruvnetReads credentialsCLAUDE.md

wifi-densepose

ruvnet/wifi-densepose/CLAUDE.md

them. ## Contributor metaharness (`@ruvnet/ruview@0.4.0`) ADR-283 defines the current community metaharness. It adds secure local Claude/Codex execution, a reviewed shared brain, default-deny MCP mutation policy, and gated Darwin/Flywheel

ruvnetReads credentialsCLAUDE.md

ruflo

ruvnet/ruflo/CLAUDE.md

tasks, low complexity (<30%) | | **3** | Sonnet/Opus | 2-5s | $0.003-0.015 | Complex reasoning, architecture, security (>30%) | - Always check for `[CODEMOD_AVAILABLE]` or `[TASK_MODEL_RECOMMENDATION]` before spawning agents - When

No other project uses it yet

ruvnetCLAUDE.md

ruflo / v3

ruvnet/ruflo/v3/CLAUDE.md

/shared/` | Shared types and utilities | | `@claude-flow/security` | `@claude-flow/security/` | Input validation, path security, CVE remediation | ## Code Quality - Files under 500 lines - No hardcoded secrets - Input validation at system

ruvnetReads credentialsCLAUDE.md

claude-flow

ruvnet/claude-flow/CLAUDE.md

tasks, low complexity (<30%) | | **3** | Sonnet/Opus | 2-5s | $0.003-0.015 | Complex reasoning, architecture, security (>30%) | - Always check for `[CODEMOD_AVAILABLE]` or `[TASK_MODEL_RECOMMENDATION]` before spawning agents - When

No other project uses it yet

jgraphCLAUDE.md

drawio-desktop

jgraph/drawio-desktop/CLAUDE.md

submodule). It enables creating flowcharts, UML diagrams, and more, with a security-first design that isolates diagram data from the internet. **Repository:** https://github.com/jgraph/drawio-desktop **License:** GPL v3 only since

No other project uses it yet

zylon-aiCLAUDE.md

private-gpt / ui

zylon-ai/private-gpt/ui/CLAUDE.md

paths and document ownership. - Update the relevant docs in `docs/` whenever behavior, visuals, persistence, security posture, or API request/response handling changes. ## Claude-Specific Notes - Use the shared docs above

No other project uses it yet

Zie619CLAUDE.md

n8n-workflows

Zie619/n8n-workflows/CLAUDE.md

Update connections when adding/removing nodes 4. Test compatibility with n8n version requirements # # Key Considerations # # # Security - Workflow files may contain sensitive information in webhook URLs or API configurations - Credentials are typically

maybe-financeReads credentialsCLAUDE.md

maybe

maybe-finance/maybe/CLAUDE.md

lint:fix` - Fix JavaScript/TypeScript issues - `npm run format` - Format JavaScript/TypeScript code - `bin/brakeman` - Run security analysis ### Database - `bin/rails db:prepare` - Create and migrate database - `bin/rails db:migrate` - Run pending migrations - `bin/rails

Imbad0202CLAUDE.md

academic-research-skills

Imbad0202/academic-research-skills/.claude/CLAUDE.md

with matrix-mirrored statuses and an asserted-status ceiling). - **Governance stated, security response proceduralized.** Root `GOVERNANCE.md` records decision authority, per-operator cross-model scope (error-detection control, not organizational independence

No other project uses it yet