yzhao062/anywhere-agents
One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).
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 yzhao062/anywhere-agents/.claude ./rig-anywhere-agents # inspect, then merge into .claude/ 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 yzhao062/anywhere-agents/packages/pypi/anywhere_agents/composer/skills/ci-mockup-figure .claude/skills/ci-mockup-figure $ npx degit yzhao062/anywhere-agents/packages/pypi/anywhere_agents/composer/skills/editable-figure .claude/skills/editable-figure $ npx degit yzhao062/anywhere-agents/packages/pypi/anywhere_agents/composer/skills/implement-review .claude/skills/implement-review $ npx degit yzhao062/anywhere-agents/packages/pypi/anywhere_agents/composer/skills/my-router .claude/skills/my-router $ npx degit yzhao062/anywhere-agents/packages/pypi/anywhere_agents/composer/skills/prun .claude/skills/prun $ npx degit yzhao062/anywhere-agents/packages/pypi/anywhere_agents/composer/skills/readme-polish .claude/skills/readme-polish
$ curl -fsSL --create-dirs -o .claude/agents/codex.md https://raw.githubusercontent.com/yzhao062/anywhere-agents/main/agents/codex.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 (1)
| codex | — |
Slash commands (14)
/ci-mockup-figure/editable-figure/implement-review/my-router/prun/readme-polish/vet/ci-mockup-figure/editable-figure/implement-review/my-router/prun/readme-polish/vet
Permissions
deny (0)
—
ask (0)
—
allow (22)
Bash(git:*)
Bash(gh:*)
Bash(python:*)
Bash(ls:*)
Bash(cd:*)
Bash(export PATH=*)
Edit
Write
Read
Grep
Glob
Skill
WebFetch
WebSearch
Bash(pip:*)
Bash(pytest:*)
Bash(conda:*)
Bash(mamba:*)
Bash(mkdir:*)
Bash(cp:*)
Bash(mv:*)
Bash(curl:*)
Similar rigs
yzhao062/agent-config
Personal agent configuration for Codex and Claude Code. Not intended for general use.
Pragmatist 7.5k tok ·
Mic92/dotfiles
My NixOS dotfiles
Pragmatist 913 tok ·
muhamadjawdatsalemalakoum/aifinetuner
Interactive visual fine-tuning plugin for AI coding agents. Generates bespoke HTML pages with sliders, infinite canvas, and live preview. Shadows, animations, colors, typography — anything visual. Works with Claude Code, Codex, Cursor, Wind
Pragmatist 5.7k tok ·
smartmemory/stratum
State machine dispatch server for AI agent workflows. Typed YAML specs, MCP server (stratum-mcp), and Python library (stratum-py) — postconditions, retries, gates, and auditable execution traces for Claude Code and Codex.
MCP Hoarder 22.5k tok ·