alexeygrigorev/.agents
my configs for Claude Code and Codex
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit alexeygrigorev/.agents/skills ./rig-.agents/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 alexeygrigorev/.agents/skills/a2a-communication .claude/skills/a2a-communication $ npx degit alexeygrigorev/.agents/skills/adversarial-design-review .claude/skills/adversarial-design-review $ npx degit alexeygrigorev/.agents/skills/adversarial-redesign .claude/skills/adversarial-redesign $ npx degit alexeygrigorev/.agents/skills/aplexer-handoff .claude/skills/aplexer-handoff $ npx degit alexeygrigorev/.agents/skills/cleanup .claude/skills/cleanup $ npx degit alexeygrigorev/.agents/skills/codex-imagegen .claude/skills/codex-imagegen $ npx degit alexeygrigorev/.agents/skills/create-github-repo .claude/skills/create-github-repo $ npx degit alexeygrigorev/.agents/skills/diagram-creator .claude/skills/diagram-creator $ npx degit alexeygrigorev/.agents/skills/external-model-agents .claude/skills/external-model-agents $ npx degit alexeygrigorev/.agents/skills/fetch-google-recorder .claude/skills/fetch-google-recorder $ npx degit alexeygrigorev/.agents/skills/fetch-loom .claude/skills/fetch-loom $ npx degit alexeygrigorev/.agents/skills/fetch-youtube .claude/skills/fetch-youtube $ npx degit alexeygrigorev/.agents/skills/fetch-zoom .claude/skills/fetch-zoom $ npx degit alexeygrigorev/.agents/skills/init-library .claude/skills/init-library $ npx degit alexeygrigorev/.agents/skills/jina-reader .claude/skills/jina-reader $ npx degit alexeygrigorev/.agents/skills/memory-wiki .claude/skills/memory-wiki $ npx degit alexeygrigorev/.agents/skills/openai-transcribe .claude/skills/openai-transcribe $ npx degit alexeygrigorev/.agents/skills/prose-write .claude/skills/prose-write $ npx degit alexeygrigorev/.agents/skills/regular-ping .claude/skills/regular-ping $ npx degit alexeygrigorev/.agents/skills/release .claude/skills/release $ npx degit alexeygrigorev/.agents/skills/setup-pypi-ci .claude/skills/setup-pypi-ci $ npx degit alexeygrigorev/.agents/skills/stylint .claude/skills/stylint $ npx degit alexeygrigorev/.agents/skills/terminal-screenshots .claude/skills/terminal-screenshots $ npx degit alexeygrigorev/.agents/skills/youtube-manager .claude/skills/youtube-manager
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 (24)
a2a-communicationadversarial-design-reviewadversarial-redesignaplexer-handoffcleanupcodex-imagegencreate-github-repodiagram-creatorexternal-model-agentsfetch-google-recorderfetch-loomfetch-youtubefetch-zoominit-libraryjina-readermemory-wikiopenai-transcribeprose-writeregular-pingreleasesetup-pypi-cistylintterminal-screenshotsyoutube-manager
Similar rigs
cmgmyr/hive
Run a crew of Claude Code and Codex workers from one lead session: visible tmux panes, exact state from hooks, one local SQLite store.
Pragmatist 6.0k tok ·
eugene1g/agent-safehouse
Sandbox your local AI agents so they can read/write only what they need
Minimalist 1.5k tok ·
jgravelle/jdocmunch-mcp
The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing
Pragmatist 18.0k tok ·
movieclaw/MovieClaw
Next-gen AI media server. One container replaces Sonarr, Radarr, Prowlarr, Bazarr, Jellyseerr and Jellyfin, with a web app, a native iPhone app, and an AI agent that gets things done. Free for personal use.
Minimalist 305 tok ·