sayiyla/bant-panosu
Local dashboard for Claude Code: see which files your agents read and write, subagents, models, cost, heat map, session replay, and YAML pipelines with on/off switches. Cream and neon themes. MIT.
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 sayiyla/bant-panosu/examples/demo-project/.claude ./rig-bant-panosu # 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.
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/sayiyla/bant-panosu/main/examples/demo-project/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/doc-writer.md https://raw.githubusercontent.com/sayiyla/bant-panosu/main/examples/demo-project/.claude/agents/doc-writer.md $ curl -fsSL --create-dirs -o .claude/agents/test-runner.md https://raw.githubusercontent.com/sayiyla/bant-panosu/main/examples/demo-project/.claude/agents/test-runner.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 *)"
]
}
} Subagents (3)
| code-reviewer model: sonnet | Reviews a change for correctness, hidden assumptions and missing tests. Use after a feature is written and before it is merged. |
| doc-writer | Updates README sections and usage docs after a change in behavior. |
| test-runner model: haiku | Runs the test suite, the linter and the type checker, then summarizes what failed. |
Similar rigs
ericvw/dotfiles
.files
Pragmatist 3.7k tok · · Q16
MCKRUZ/claude-code-mastery
The definitive Claude Code setup, configuration, and mastery skill — CLAUDE.md engineering, MCP servers, agent teams, hooks, CI/CD, and self-updating knowledge base
Minimalist 1.0k tok · · Q0
msiShariful/claude-code-studio
A local GUI for managing Claude Code settings — config, MCP servers, plugins, hooks, agents, skills, and CLAUDE.md. npx cc-studio
Fort Knox 2.1k tok · · Q40
Mfrostbutter/beyond-the-chatbox
A field guide for moving beyond web chat AI — Claude Desktop and Claude Code setup, context engineering, and project scaffolding for non-developers and developers alike.
Orchestrator 3.8k tok · · Q20