helmor
dohooo/helmor/CLAUDE.md
Bump cadence: every release cycle if upstream has shipped a notable fix; immediately on security advisories. Pin so the auth-status JSON shape Helmor parses doesn't drift unexpectedly. - **Bundled
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
dohooo/helmor/CLAUDE.md
Bump cadence: every release cycle if upstream has shipped a notable fix; immediately on security advisories. Pin so the auth-status JSON shape Helmor parses doesn't drift unexpectedly. - **Bundled
Taewan-P/gpt_mobile/CLAUDE.md
/gradlew connectedAndroidTest # Instrumented tests ``` ### Code Quality - **Linting**: Handled by GitHub Actions with ktlint 1.3.1 - **Security**: CodeQL analysis runs automatically on main branch changes ## Architecture ### Core Structure - **MVVM Pattern**: ViewModels handle
modu-ai/moai-adk/CLAUDE.md
reduction. **Use for**: implementation-heavy SPECs (run phase), code/test/doc generation. **Avoid**: planning/architecture (needs Opus), security, complex debugging. Routing: `glm-web-tooling.md` § CG Mode. Dynamic Workflows + `/effort ultracode`: `dynamic-workflows.md` + `goal-directive.md` (workflow subagents cannot
affaan-m/agentshield/CLAUDE.md
AgentShield Security auditor for AI agent configurations (Claude Code, MCP servers, hooks, agents). ## Build & Test ```bash npm run build # tsc + tsup → dist/ npm test # vitest (912 tests
RchGrav/claudebox/claude/CLAUDE.md
Final review** - Check `git diff --staged` to review what will be committed 8. **Security check** - Verify no sensitive information (keys, tokens, passwords) is included ### Test Requirements **All tests must pass
RchGrav/claudebox/CLAUDE.md
string comparisons - Docker containerization specialist understanding multi-stage builds, layer optimization, and security - Familiar with ClaudeBox architecture: project isolation, profile system, security model ## Code Analysis Approach 1. **READ** the entire
AltanS/collie/CLAUDE.md
keeps the daily cadence.** A patch the operator must take today, data loss, a security fix, a broken update path, may carry ONE line directly under the release heading
beizhu-1209/AIHelms/apps/CLAUDE.md
async. One file per resource. Returns ORM model instances or lists. - **Core layer**: Config, security, database session management — infrastructure concerns. No cross-layer calls: Router must not operate database directly
jezweb/claude-skills/CLAUDE.md
tree in this file and the table in README.md **Categories**: `development`, `design`, `productivity`, `testing`, `security`, `database`, `monitoring`, `deployment` ## Creating a Skill See [`SKILL_SHAPE.md`](SKILL_SHAPE.md) for the canonical authoring guide — frontmatter
chamilo/chamilo-lms/CLAUDE.md
were skipped. Default to surfacing uncertainty, not hiding it. ### Rule 13 - OWASP security review Review **every** new and modified file (controller, Vue component, updated legacy links) for common vulnerabilities. This
bytechefhq/bytechef/CLAUDE.md
token validity and expiration - Verify user roles and permissions in database - Review Spring Security filter chain execution - Check CORS configuration for client-server communication ## Troubleshooting **Database schema issues** - Reset database
MadAppGang/claudish/CLAUDE.md
pinning - `keychain.md` — the macOS Keychain backend: enumerate-for-presence vs read-for-value, the `security` traps, the Providers-tab write/delete - `mcp-channel.md` — MCP tool surface, channel wire format, progress keepalive - `team-capture.md
autonomous-ai/autonomous-harness/desktop/CLAUDE.md
pumpAndSettle` that never settles and these sources would otherwise shell out to `security` and open real sockets. - **The token ledger is the OTHER usage feature, and the two must
jarrodwatts/claude-delegator/CLAUDE.md
experts that can advise OR implement: Architect, Plan Reviewer, Scope Analyst, Code Reviewer, and Security Analyst. ## Development Commands ```bash # Test plugin locally (loads from working directory) claude --plugin-dir /path/to/claude-delegator
microsoft/AIOpsLab/CLAUDE.md
Wrong home base for cloud | Set `user_home_base: /home` in inventory | ### NSG (Network Security Group) Rules The Terraform config creates NSG rules for: - **SSH (22)**: Open
NVIDIA/NVFlare/CLAUDE.md
federated learning. It allows ML/DL workflows to be adapted to a federated paradigm, enabling secure, privacy-preserving distributed multi-party collaboration. **Key capabilities:** PyTorch/TensorFlow/Scikit-learn/XGBoost support, horizontal and vertical FL, built
Pantheon-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
zeenie-ai/OpenCompany/CLAUDE.md
# OpenCompany - Claude Documentation ## Project Overview This is a React Flow-based workflow automation platform
rohitg00/kubectl-mcp-server/CLAUDE.md
Workloads** | k8s-deploy, k8s-operations, k8s-helm | | **Observability** | k8s-diagnostics, k8s-troubleshoot, k8s-incident | | **Security** | k8s-security, k8s-policy, k8s-certs | | **GitOps** | k8s-gitops, k8s-rollouts | | **Scaling** | k8s-autoscaling
LING71671/Open-ClaudeCode/CLAUDE.md
typecheck:loop-tests` + `test:loop` + chaîne desktop | | `npm --prefix desktop run verify:ci` | `audit:security` (npm audit --audit-level=moderate --omit=optional) + `typecheck:refactor` + `test` (node --test test/*.test.cjs
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.