MaceGrim/claude-code-config
My Claude Code configuration - commands, skills, hooks, and settings
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 MaceGrim/claude-code-config/agents ./rig-claude-code-config/agents $ npx degit MaceGrim/claude-code-config/commands ./rig-claude-code-config/commands $ npx degit MaceGrim/claude-code-config/skills ./rig-claude-code-config/skills $ npx degit MaceGrim/claude-code-config/hooks ./rig-claude-code-config/hooks
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 MaceGrim/claude-code-config/skills/codex .claude/skills/codex $ npx degit MaceGrim/claude-code-config/skills/converge .claude/skills/converge $ npx degit MaceGrim/claude-code-config/skills/frontend-slides .claude/skills/frontend-slides $ npx degit MaceGrim/claude-code-config/skills/gemini-image .claude/skills/gemini-image $ npx degit MaceGrim/claude-code-config/skills/sentinel-hero .claude/skills/sentinel-hero $ npx degit MaceGrim/claude-code-config/skills/spawn .claude/skills/spawn
$ curl -fsSL --create-dirs -o .claude/agents/codex-code-reviewer.md https://raw.githubusercontent.com/MaceGrim/claude-code-config/main/agents/codex-code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/codex-runner.md https://raw.githubusercontent.com/MaceGrim/claude-code-config/main/agents/codex-runner.md
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 (6)
Subagents (2)
| codex-code-reviewer model: opus | Use this agent when you want an external AI perspective on recently written code, when you need a second opinion on code quality or implementation approach, or when reviewing pull requests and changes |
| codex-runner model: opus | Use this agent whenever you need an independent second opinion from the OpenAI Codex CLI — code review, design critique, fact-checking, plan sanity-checks, architecture opinions, verdicts. The agent o |
Slash commands (20)
/adversarial-spec/atomic-commit/codex-review/council/dayprep/decompose/done/double-check/implement-spec/log-failure/open/prep-for-commit/profile-data/ralph/rundown/seed/studio-draft/studio-ideate/studio-publish/studio-review
Similar rigs
bingran-you/bingran-you
Home workspace for Bingran's AI agents army.
Pragmatist 3.5k tok ·
rnijhara/claude-code-toolkit
Personal Claude Code utilities, configs, and customizations
Pragmatist 206 tok ·
kato-yoshiharu/dotfiles
—
Skill Collector 681 tok ·
Nowely/agent-skills
Run Codex as a Claude Code subagent with rights declared per call — read-only analysis, or writing and running tests inside a git worktree — and an exit code that reflects what actually ran.
Skill Collector 110 tok ·