KonixDev/claude-code-guardrails
Architecture rules your AI coding agent can't skip: CLAUDE.md/AGENTS.md, Claude Code hooks, ESLint boundaries, Cursor rules. Copy-in kit.
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
Copy this rig
# review before running: this installs third-party code
$ npx degit KonixDev/claude-code-guardrails/templates/.claude ./rig-claude-code-guardrails # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit KonixDev/claude-code-guardrails/templates/.claude/skills/new-module .claude/skills/new-module $ curl -fsSL --create-dirs -o .claude/agents/architecture-reviewer.md https://raw.githubusercontent.com/KonixDev/claude-code-guardrails/main/templates/.claude/agents/architecture-reviewer.md This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (1)
Subagents (1)
| architecture-reviewer | Reviews a diff against the layered architecture in AGENTS.md (inward dependencies, framework-free core, type-only cross-module imports). Use before reporting a non-trivial change as done. |
Hooks (2)
| event | matcher | runs |
|---|---|---|
| PostToolUse | Edit|Write|MultiEdit | node "$CLAUDE_PROJECT_DIR/.claude/hooks/lint-edited-file.mjs" |
| Stop | * | node "$CLAUDE_PROJECT_DIR/.claude/hooks/verify-before-stop.mjs" |
Cursor rules (1)
architecture
Similar rigs
etu/nixconfig
My NixOS config
Pragmatist 9.8k tok · · Q18
emeraldleaf/okl
Lessons your coding agent can trust: briefed before every task, proven by checks, and flagged when the code they cover changes. Works with Claude Code and any MCP agent.
Pragmatist 4.0k tok · · Q15
TbusOS/android-llm-bridge
让 LLM Agent 直接在线调试安卓设备 —— 抽象 adb / ssh / UART 多种传输,通过 MCP / CLI / Web API 三层接入大模型。
Orchestrator 2.6k tok · · Q0
norton77930/Provost
Classify every request, let cheaper models do the typing, review only on risk: orchestration policy, roles and handoff runtime for Claude Code
Orchestrator 886 tok · · Q0