User-Piotr/agent-config
Config for my AI coding agents
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
Copy this rig
$ git clone --depth 1 https://github.com/User-Piotr/agent-config 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 User-Piotr/agent-config/claude/skills/delivery .claude/skills/delivery 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 (1)
Similar rigs
ribeirogab/specwright
A multi-host plugin for Claude Code, Codex, and OpenCode. It gives a repository one explicit, change-driven engineering workflow:
Pragmatist 1.6k tok ·
Atman36/AI-First-HQ-OS
AI-first operating system for running a one-person company: Markdown source of truth, agent prompts, and an agent control plane with deny-by-default permissions, runtime governance, policy-as-code, telemetry, and a safe-delegation feedback
Skill Collector 5.5k tok ·
joaofnds/dotfiles
:octocat: + ~/. = ❤️. These are my dotfiles, feel free to hack them! 😄
Skill Collector 5.2k tok ·
wangqiqi/cursor-ai
无关用户, 无关系统, 无关项目,开箱复制即用! code faster, code better;
Skill Collector 2.8k tok ·