yeyo11/claudio
Run Claude Code as a service: a REST API, a web UI, a Linux desktop app and parallel agents on a project's board, all through the Claude Code CLI.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
up to ~6.0k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add pando -- pando mcp-server --no-http $ npx degit yeyo11/claudio/.claude ./rig-claudio # 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.
$ claude mcp add pando -- pando mcp-server --no-http $ npx degit yeyo11/claudio/.claude/skills/add-rest-route .claude/skills/add-rest-route $ npx degit yeyo11/claudio/.claude/skills/claudio-ui .claude/skills/claudio-ui $ npx degit yeyo11/claudio/.claude/skills/run-e2e .claude/skills/run-e2e
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/yeyo11/claudio/main/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/developer.md https://raw.githubusercontent.com/yeyo11/claudio/main/.claude/agents/developer.md $ curl -fsSL --create-dirs -o .claude/agents/ia-auditor.md https://raw.githubusercontent.com/yeyo11/claudio/main/.claude/agents/ia-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/product-owner.md https://raw.githubusercontent.com/yeyo11/claudio/main/.claude/agents/product-owner.md $ curl -fsSL --create-dirs -o .claude/agents/qa.md https://raw.githubusercontent.com/yeyo11/claudio/main/.claude/agents/qa.md $ curl -fsSL --create-dirs -o .claude/agents/ui-explorer.md https://raw.githubusercontent.com/yeyo11/claudio/main/.claude/agents/ui-explorer.md $ curl -fsSL --create-dirs -o .claude/agents/ui-reviewer.md https://raw.githubusercontent.com/yeyo11/claudio/main/.claude/agents/ui-reviewer.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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| pando | binary | 2.5k |
Skills (3)
Subagents (7)
| architect model: opus | Decides the design of a change and reviews it against the codebase, the one rule and the persistence conventions. |
| developer model: sonnet | Implements work items in their own worktree, following CONTRIBUTING and the design system, with tests. |
| ia-auditor model: opus | Audits the information architecture of Claudio's settings and navigation. Read only. Use it before redesigning any part of Settings, or when asked to simplify settings, cut scrolling or reduce section |
| product-owner model: opus | Refines backlog items into specifications with checkable acceptance criteria, grounded in the docs and the design system. |
| qa model: sonnet | Verifies each item against its acceptance criteria by running the project's checks and reading the change, and writes tests for gaps. |
| ui-explorer model: opus | Builds ONE design variant of a Claudio screen under one extreme, explicit constraint, in an isolated git worktree. Launched in parallel (3–5 at once) by /ui-explore. Not for the final implementation. |
| ui-reviewer model: opus | Reviews a Claudio screen against the rubric and the invariants, with real screenshots and a clean context. Use it after any UI change and before calling a UI task done. Does not edit code. |
Hooks (4)
| event | matcher | runs |
|---|---|---|
| UserPromptSubmit | * | echo '{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"Project rule (CLAUDE.md > Knowledge): if this prompt asks anything about this project - what it does, how it works, where it stands, why something was deci |
| PostToolUse | Edit|Write|MultiEdit | node "$CLAUDE_PROJECT_DIR/.claude/hooks/design-lint.mjs" |
| PostToolUse | Edit|Write|MultiEdit | node "$CLAUDE_PROJECT_DIR/.claude/hooks/ui-invariants-fast.mjs" |
| Stop | * | node "$CLAUDE_PROJECT_DIR/.claude/hooks/require-review.mjs" |
Slash commands (3)
/ui-audit/ui-explore/ui-review
Plugins (1)
infra@yeyo11
Similar rigs
yeyo11/agentry
Run Claude Code as a service: REST API, web UI and multi-agent orchestration in one container
Pragmatist 5.2k tok · · Q18
vannt-dev/governed-agent-sdlc
Ship with agents. Keep humans in control. Cross-platform governance toolkit for AI coding agents.
Fort Knox 632 tok · · Q24
ThinhHoang1/claude-code-agent-team
An AI dev team for Claude Code agent teams: 8 role agents, a HANDOFF protocol and 3 hook quality gates — with the TeammateIdle infinite-loop bug fixed and regression-tested.
Orchestrator 1.6k tok · · Q15
danielfarnose/claude-code-dev-loop
A multi-agent development loop for Claude Code: five specialized subagents plan, implement, verify and merge — with a QA gate that cannot edit the code it judges.
Orchestrator 1.2k tok · · Q0