How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
affaan-mCLAUDE.mdaffaan-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-mCLAUDE.mdaffaan-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.mdn8n-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-GravitasCLAUDE.mdSignificant-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
garrytanCLAUDE.mdgarrytan/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
browser-useCLAUDE.mdbrowser-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
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/CLAUDE.md
until changed or session ends. ### Auto-clarity rule Caveman drops to normal prose for: security warnings, irreversible action confirmations, multi-step sequences where fragment ambiguity risks misread, user confused
addyosmaniCLAUDE.mdaddyosmani/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
ruvnetCLAUDE.mdruvnet/RuView/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
Model Context ProtocolCLAUDE.mdmodelcontextprotocol/servers/CLAUDE.md
reviewed against the [PR template](.github/pull_request_template.md) checklist -- ensure MCP docs are read, security best practices followed, and changes tested with an LLM client
ruvnetCLAUDE.mdruvnet/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
ruvnetCLAUDE.mdruvnet/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
CherryHQCLAUDE.mdCherryHQ/cherry-studio/CLAUDE.md
MUST READ**: [docs/references/ipc/README.md](docs/references/ipc/README.md) — paradigm boundary (RPC vs REST), schema/router/preload/facade layering, `IpcContext`, error model, security. Non-data command IPC (window/system/shell/notification/external/file) goes through **IpcApi** — the fifth subsystem alongside BootConfig/Cache/Preference/DataApi, RPC-over
Imbad0202CLAUDE.mdImbad0202/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
luongnv89CLAUDE.mdluongnv89/claude-howto/uk/CLAUDE.md
Якість коду ```bash # Lint and format Python code ruff check scripts/ ruff format scripts/ # Security scan bandit -c scripts/pyproject.toml -r scripts/ --exclude scripts/tests/ # Type checking mypy scripts/ --ignore-missing-imports
luongnv89CLAUDE.mdluongnv89/claude-howto/vi/CLAUDE.md
Lượng Code ```bash # Lint và format Python code ruff check scripts/ ruff format scripts/ # Security scan bandit -c scripts/pyproject.toml -r scripts/ --exclude scripts/tests/ # Type checking mypy scripts/ --ignore-missing-imports
AnthropicCLAUDE.mdanthropics/financial-services/CLAUDE.md
named agent) │ └── / │ ├── agent.yaml # system + skills → ../../plugins/agent-plugins/ /... │ ├── subagents/*.yaml # depth-1 leaf workers │ ├── steering-examples.json │ └── README.md # security tier + handoff notes ├── claude-for-msft-365-install/ # admin tooling for the Microsoft
davila7CLAUDE.mddavila7/claude-code-templates/CLAUDE.md
push to `main` > (changes in `dashboard/**`). Manual deploy uses `wrangler pages deploy`, not Vercel. ## Security Guidelines ### ⛔ CRITICAL: NEVER Hardcode Secrets or IDs **NEVER write API keys, tokens, passwords, project
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
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
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.
