junghan0611/agent-config
Skills SSOT and proving ground for entwurf — one operator's memory, skills, and 1KB identity carried identically across pi, Claude Code, Codex, Antigravity, Copilot, OMP, and OpenClaw. Semantic memory (Qwen3-Embedding-8B + LanceDB), 43 shar
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 junghan0611/agent-config/.claude ./rig-agent-config # 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 junghan0611/agent-config/.claude/skills/agent-config .claude/skills/agent-config $ npx degit junghan0611/agent-config/skills/agenda .claude/skills/agenda $ npx degit junghan0611/agent-config/skills/autholog-mend .claude/skills/autholog-mend $ npx degit junghan0611/agent-config/skills/bibcli .claude/skills/bibcli $ npx degit junghan0611/agent-config/skills/botlog .claude/skills/botlog $ npx degit junghan0611/agent-config/skills/botment .claude/skills/botment $ npx degit junghan0611/agent-config/skills/brave-search .claude/skills/brave-search $ npx degit junghan0611/agent-config/skills/browser-tools .claude/skills/browser-tools $ npx degit junghan0611/agent-config/skills/cloudflare .claude/skills/cloudflare $ npx degit junghan0611/agent-config/skills/command-glgimage .claude/skills/command-glgimage $ npx degit junghan0611/agent-config/skills/command-recall .claude/skills/command-recall $ npx degit junghan0611/agent-config/skills/commit .claude/skills/commit $ npx degit junghan0611/agent-config/skills/day-query .claude/skills/day-query $ npx degit junghan0611/agent-config/skills/denotecli .claude/skills/denotecli $ npx degit junghan0611/agent-config/skills/dictcli .claude/skills/dictcli $ npx degit junghan0611/agent-config/skills/diskspace .claude/skills/diskspace $ npx degit junghan0611/agent-config/skills/dm .claude/skills/dm $ npx degit junghan0611/agent-config/skills/emacs .claude/skills/emacs $ npx degit junghan0611/agent-config/skills/entwurf-peek .claude/skills/entwurf-peek $ npx degit junghan0611/agent-config/skills/evidence-closure .claude/skills/evidence-closure $ npx degit junghan0611/agent-config/skills/exa-search .claude/skills/exa-search $ npx degit junghan0611/agent-config/skills/ghcli .claude/skills/ghcli $ npx degit junghan0611/agent-config/skills/gitcli .claude/skills/gitcli $ npx degit junghan0611/agent-config/skills/gogcli .claude/skills/gogcli $ npx degit junghan0611/agent-config/skills/harness-bench .claude/skills/harness-bench $ npx degit junghan0611/agent-config/skills/improve-agent .claude/skills/improve-agent $ npx degit junghan0611/agent-config/skills/jiracli .claude/skills/jiracli $ npx degit junghan0611/agent-config/skills/lifetract .claude/skills/lifetract $ npx degit junghan0611/agent-config/skills/logickocli .claude/skills/logickocli $ npx degit junghan0611/agent-config/skills/medium-extractor .claude/skills/medium-extractor $ npx degit junghan0611/agent-config/skills/memory-sync .claude/skills/memory-sync $ npx degit junghan0611/agent-config/skills/next-handoff .claude/skills/next-handoff $ npx degit junghan0611/agent-config/skills/plane .claude/skills/plane $ npx degit junghan0611/agent-config/skills/punchout .claude/skills/punchout $ npx degit junghan0611/agent-config/skills/quota .claude/skills/quota $ npx degit junghan0611/agent-config/skills/semantic-memory .claude/skills/semantic-memory $ npx degit junghan0611/agent-config/skills/session-recap .claude/skills/session-recap $ npx degit junghan0611/agent-config/skills/slack-latest .claude/skills/slack-latest $ npx degit junghan0611/agent-config/skills/subtract .claude/skills/subtract $ npx degit junghan0611/agent-config/skills/summarize .claude/skills/summarize
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 (46)
agent-configagendaautholog-mendbibclibotlogbotmentbrave-searchbrowser-toolscloudflareglg-imagerecallcommitday-querydenoteclidictclidiskspacedmemacsentwurf-peekevidence-closureexa-searchghcligitcligogcliharness-benchimprove-agentjiraclilifetractlogickoclimedium-extractormemory-syncnext-handoffplanepunchoutquotasemantic-memorysession-recapslack-latestsubtractsummarizetag-releasetelegramtimelinetmuxtranscribeyoutube-transcript
Slash commands (9)
/authologplay/boom/discuss/docplay/glg-image/metaplay/pandoc-html/recall/scaleplay
Similar rigs
dnouri/ai-config
Skills and extensions for pi-coding-agent, Claude Code, Codex CLI
Pragmatist 1.9k tok ·
lttr/dotfiles
Collection of files for configuration and installation of my development machines
Skill Collector 2.8k tok ·
jasonlong/dotfiles
Files. With dots in front of them.
Pragmatist 336 tok ·
MemTensor/memmy-agent
🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc.
Skill Collector 765 tok ·