claytoncasey01/conn
A local dashboard for Claude Code: live sessions and agents, a searchable archive, PR reviews and fixes, and themes. Runs on your machine only.
field: Data & analytics
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
Copy this rig
# review before running: this installs third-party code $ npx degit claytoncasey01/conn/agents ./rig-conn/agents $ npx degit claytoncasey01/conn/skills ./rig-conn/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 claytoncasey01/conn/skills/deep-code-review .claude/skills/deep-code-review $ curl -fsSL --create-dirs -o .claude/agents/docs.md https://raw.githubusercontent.com/claytoncasey01/conn/main/agents/docs.md $ curl -fsSL --create-dirs -o .claude/agents/grep.md https://raw.githubusercontent.com/claytoncasey01/conn/main/agents/grep.md $ curl -fsSL --create-dirs -o .claude/agents/search.md https://raw.githubusercontent.com/claytoncasey01/conn/main/agents/search.md
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 (1)
Subagents (3)
| docs model: haiku | Pulls API reference for a library, framework, or service at the version this project uses. Use before writing code against an API you haven't verified. Read-only; returns signatures, params, and minim |
| grep model: haiku | Finds every call site, reference, or usage of a symbol, string, config key, or pattern. Use before renaming, changing a signature, or deleting code. Read-only; returns an exhaustive path:line list. |
| search model: haiku | Maps a repo or directory before work starts — layout, entry points, build/test commands, and the files relevant to the goal. Read-only; returns a concise map, not file dumps. |
Similar rigs
agentlogbooks/logbooks
Structured state for agent skills
Minimalist 180 tok · · Q0
towerforge/claude-agents
Lists the Claude Code subagents on disk and shows which ones are running, what they were asked to do, how long they worked and the tokens they used.
Orchestrator 1.3k tok · · Q0
tavriq/claude-setup
Готовое окружение Claude Code: правила, субагенты, скиллы, хук контекста. Ставится одной командой
Orchestrator 2.5k tok · · Q15
utkudarilmaz/claude-code-setup
My personal Claude Code Configuration
YOLO Cowboy 3.4k tok · · Q3