~ / rigs / wanghong5233 / agent-engineering-kit

wanghong5233/agent-engineering-kit

A reusable, production-grade .cursor/ engineering package for Cursor / Claude Code / Agent IDEs. Rules, skills, commands, and deterministic safety hooks extracted from a real Agent project.

↗ GitHub ★ 0 MIT updated 5mo ago project Cursor
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~1.3k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/wanghong5233/agent-engineering-kit

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 wanghong5233/agent-engineering-kit/cursor/.cursor/skills/agent-debugging .claude/skills/agent-debugging
$ npx degit wanghong5233/agent-engineering-kit/cursor/.cursor/skills/bootstrap-cursor-package .claude/skills/bootstrap-cursor-package
$ npx degit wanghong5233/agent-engineering-kit/cursor/.cursor/skills/llm-cost-optimizer .claude/skills/llm-cost-optimizer
$ npx degit wanghong5233/agent-engineering-kit/cursor/.cursor/skills/llm-observability-and-evals .claude/skills/llm-observability-and-evals
$ npx degit wanghong5233/agent-engineering-kit/cursor/.cursor/skills/tool-and-mcp-design .claude/skills/tool-and-mcp-design
$ npx degit wanghong5233/agent-engineering-kit/cursor/.cursor/skills/writing-architecture-docs .claude/skills/writing-architecture-docs
$ npx degit wanghong5233/agent-engineering-kit/cursor/.cursor/skills/writing-engineering-playbook .claude/skills/writing-engineering-playbook
$ npx degit wanghong5233/agent-engineering-kit/cursor/.cursor/skills/writing-issue-backlog .claude/skills/writing-issue-backlog
$ npx degit wanghong5233/agent-engineering-kit/cursor/.cursor/skills/writing-pitfall-archive .claude/skills/writing-pitfall-archive
$ npx degit wanghong5233/agent-engineering-kit/cursor/.cursor/skills/writing-readme .claude/skills/writing-readme
$ npx degit wanghong5233/agent-engineering-kit/cursor/.cursor/skills/writing-skill .claude/skills/writing-skill
$ npx degit wanghong5233/agent-engineering-kit/cursor/.cursor/skills/writing-tech-article .claude/skills/writing-tech-article

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (12)

Cursor rules (4)

agent-runtime-contractsconfiguration-managementcore-principles · alwayscursor-package-boundaries

Similar rigs

copied ✓