rcrdk/agent-kit
Cursor rules, agent commands, and bundled skills — one submodule for consistent AI coding across rcrdk projects Agent config for rcrdk: .mdc rules, slash commands, Karpathy skills, and DX bootstrap templates
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ claude mcp add codebase-memory -- npx -y codebase-memory-mcp@0.9.0 $ npx degit rcrdk/agent-kit/commands ./rig-agent-kit/commands $ npx degit rcrdk/agent-kit/skills ./rig-agent-kit/skills
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.
$ claude mcp add codebase-memory -- npx -y codebase-memory-mcp@0.9.0 $ npx degit rcrdk/agent-kit/skills/clean .claude/skills/clean $ npx degit rcrdk/agent-kit/skills/code-reviewer .claude/skills/code-reviewer $ npx degit rcrdk/agent-kit/skills/debugger .claude/skills/debugger $ npx degit rcrdk/agent-kit/skills/evidence-verifier .claude/skills/evidence-verifier $ npx degit rcrdk/agent-kit/skills/interviewer .claude/skills/interviewer $ npx degit rcrdk/agent-kit/skills/karpathy-guidelines .claude/skills/karpathy-guidelines $ npx degit rcrdk/agent-kit/skills/logic-reviewer .claude/skills/logic-reviewer $ npx degit rcrdk/agent-kit/skills/performance .claude/skills/performance $ npx degit rcrdk/agent-kit/skills/security-reviewer .claude/skills/security-reviewer $ npx degit rcrdk/agent-kit/skills/tdd .claude/skills/tdd
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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| codebase-memory-mcp · "codebase-memory" | npm | 2.5k |
Skills (10)
cleancode-reviewerdebuggerevidence-verifierinterviewerkarpathy-guidelineslogic-reviewerperformancesecurity-reviewertdd
Slash commands (14)
/rcrdk-commit-unstaged/rcrdk-debug-and-fix/rcrdk-document-commit/rcrdk-dual-review/rcrdk-fix-tests/rcrdk-full-delivery/rcrdk-honest-close/rcrdk-hotfix/rcrdk-index-codebase/rcrdk-platform-pipeline/rcrdk-prod-incident/rcrdk-review-rules/rcrdk-setup-agent-kit/rcrdk-setup-dx
Similar rigs
Anmolnoor/claude-dotfiles
Portable Claude Code setup — clone on a new machine, run ./install.sh, done.
Pragmatist 1.3k tok ·
antonbabenko/deliberation
Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures the models' usefulness, too.
Pragmatist 4.2k tok ·
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Minimalist 723 tok ·
wbern/agent-instructions
Claude Instructions Repository
Pragmatist 2.0k tok ·