mark-hallam/mstack
Agent skills that take you out of every job you do not need to be in. I use them every day. Any agent, free, MIT.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit mark-hallam/mstack/skills ./rig-mstack/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.
$ npx degit mark-hallam/mstack/skills/away-mode .claude/skills/away-mode $ npx degit mark-hallam/mstack/skills/crew .claude/skills/crew $ npx degit mark-hallam/mstack/skills/design-direction .claude/skills/design-direction $ npx degit mark-hallam/mstack/skills/mstack .claude/skills/mstack $ npx degit mark-hallam/mstack/skills/multi-evaluator .claude/skills/multi-evaluator $ npx degit mark-hallam/mstack/skills/outcome-first .claude/skills/outcome-first $ npx degit mark-hallam/mstack/skills/ping-me .claude/skills/ping-me
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 (7)
Similar rigs
sashabogi/trantor
The hub-world for AI agent crews — orchestrate Claude Code, Codex, Gemini, Kimi & DeepSeek as live crews with a plan-aware Advisor, a Kanban/flow command center, a testing gate, and an economics brain (Scrooge).
Pragmatist 2.6k tok · · Q0
FurlanLuka/crew
Talk to your coding agents. A voice and web cockpit for running many Claude Code sessions at once, each in its own worktree with its own dev servers, on one machine or several.
Pragmatist 13.1k tok · · Q8
givepro91/nova
Nova — a compounding-agent nervous system for Claude Code. Modular plugin marketplace: rules/learning (claude-md), continuity (handoff), completion-honesty gate (nova-gate), session worklog (worklog).
Skill Collector 5.7k tok · · Q5
w2ur/claude-code-setup
Claude Code hooks, agents and commands for running 10+ personal apps without babysitting every diff — MIT, hooks included.
Orchestrator 7.1k tok · · Q10