Bewinxed/cawco
One board for every coding agent you run: a self-hosted control plane for Claude Code, OpenCode and pi across all your machines.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
up to ~5.4k 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 playwriter -e PLAYWRITER_AUTO_ENABLE=YOUR_PLAYWRITER_AUTO_ENABLE -- npx playwriter@latest 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 playwriter -e PLAYWRITER_AUTO_ENABLE=YOUR_PLAYWRITER_AUTO_ENABLE -- npx playwriter@latest $ npx degit Bewinxed/cawco/packages/hub/skills/brand-extract .claude/skills/brand-extract $ npx degit Bewinxed/cawco/packages/hub/skills/component-canvas .claude/skills/component-canvas $ npx degit Bewinxed/cawco/packages/hub/skills/decision-page .claude/skills/decision-page $ npx degit Bewinxed/cawco/packages/hub/skills/design-explore .claude/skills/design-explore $ npx degit Bewinxed/cawco/packages/hub/skills/design-system .claude/skills/design-system $ npx degit Bewinxed/cawco/packages/hub/skills/drift .claude/skills/drift $ npx degit Bewinxed/cawco/packages/hub/skills/grill .claude/skills/grill $ npx degit Bewinxed/cawco/packages/hub/skills/inline-block .claude/skills/inline-block $ npx degit Bewinxed/cawco/packages/hub/skills/launch-plan .claude/skills/launch-plan $ npx degit Bewinxed/cawco/packages/hub/skills/outreach-message .claude/skills/outreach-message $ npx degit Bewinxed/cawco/packages/hub/skills/project-attempt-judgement .claude/skills/project-attempt-judgement $ npx degit Bewinxed/cawco/packages/hub/skills/project-connection .claude/skills/project-connection $ npx degit Bewinxed/cawco/packages/hub/skills/project-decision .claude/skills/project-decision $ npx degit Bewinxed/cawco/packages/hub/skills/project-delegate-report .claude/skills/project-delegate-report $ npx degit Bewinxed/cawco/packages/hub/skills/project-fleet-watch .claude/skills/project-fleet-watch $ npx degit Bewinxed/cawco/packages/hub/skills/project-github-event .claude/skills/project-github-event $ npx degit Bewinxed/cawco/packages/hub/skills/project-inbound-event .claude/skills/project-inbound-event $ npx degit Bewinxed/cawco/packages/hub/skills/project-person-request .claude/skills/project-person-request $ npx degit Bewinxed/cawco/packages/hub/skills/project-routine-report .claude/skills/project-routine-report $ npx degit Bewinxed/cawco/packages/hub/skills/project-routine-run .claude/skills/project-routine-run $ npx degit Bewinxed/cawco/packages/hub/skills/project-setup .claude/skills/project-setup $ npx degit Bewinxed/cawco/packages/hub/skills/project-task-input .claude/skills/project-task-input $ npx degit Bewinxed/cawco/packages/hub/skills/project-task-move .claude/skills/project-task-move $ npx degit Bewinxed/cawco/packages/hub/skills/project-view .claude/skills/project-view $ npx degit Bewinxed/cawco/packages/hub/skills/restyle .claude/skills/restyle $ npx degit Bewinxed/cawco/packages/hub/skills/review-attempt .claude/skills/review-attempt $ npx degit Bewinxed/cawco/packages/hub/skills/screen .claude/skills/screen $ npx degit Bewinxed/cawco/packages/hub/skills/seo-brief .claude/skills/seo-brief $ npx degit Bewinxed/cawco/packages/hub/skills/show .claude/skills/show $ npx degit Bewinxed/cawco/packages/hub/skills/social-post .claude/skills/social-post $ npx degit Bewinxed/cawco/packages/hub/skills/to-tasks .claude/skills/to-tasks $ npx degit Bewinxed/cawco/packages/hub/skills/triage .claude/skills/triage
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 |
|---|---|---|
| playwriter env: PLAYWRITER_AUTO_ENABLE | npm | 2.5k |
Skills (32)
brand-extractcomponent-canvasdecision-pagedesign-exploredesign-systemdriftgrillinline-blocklaunch-planoutreach-messageproject-attempt-judgementproject-connectionproject-decisionproject-delegate-reportproject-fleet-watchproject-github-eventproject-inbound-eventproject-person-requestproject-routine-reportproject-routine-runproject-setupproject-task-inputproject-task-moveproject-viewrestylereview-attemptscreenseo-briefshowsocial-postto-taskstriage
Similar rigs
JoaoPeixoto72/production-quality-ready
Sistema de qualidade e auditoria com gates declarativos para Antigravity e Claude Code
Skill Collector 1.6k tok · · Q0
openwizdev/OpenWiz
An open-source software factory: you say what you want, agents plan, build, review and ship it.
Skill Collector 8.1k tok · · Q10
openwizdev/openwiz
A software factory that works out of the box. Built for fleets of agents in the cloud.
Skill Collector 8.0k tok · · Q10
halilural/imprimatur
Review your AI agent's edits like tracked changes: marked in VS Code and the Markdown preview until you accept them.
Skill Collector 1.9k tok · · Q20