Chan-Software-Services/agent-team
Daniel's agent team: the scripts, prompts, settings and hooks that run a coordinator and its Claude Code workers
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
up to ~26.0k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Context hog · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code
$ npx degit Chan-Software-Services/agent-team/.claude ./rig-agent-team # 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 Chan-Software-Services/agent-team/plugins/coordinator-skills/skills/handoff .claude/skills/handoff $ npx degit Chan-Software-Services/agent-team/plugins/coordinator-skills/skills/level .claude/skills/level $ npx degit Chan-Software-Services/agent-team/plugins/coordinator-skills/skills/recover-worker .claude/skills/recover-worker $ npx degit Chan-Software-Services/agent-team/plugins/coordinator-skills/skills/resume .claude/skills/resume $ npx degit Chan-Software-Services/agent-team/plugins/coordinator-skills/skills/retro .claude/skills/retro $ npx degit Chan-Software-Services/agent-team/plugins/coordinator-skills/skills/status-report .claude/skills/status-report $ npx degit Chan-Software-Services/agent-team/plugins/coordinator-skills/skills/stow .claude/skills/stow $ npx degit Chan-Software-Services/agent-team/plugins/coordinator-skills/skills/ui-intake .claude/skills/ui-intake $ npx degit Chan-Software-Services/agent-team/toolkits/browser/skills/ui-check .claude/skills/ui-check $ npx degit Chan-Software-Services/agent-team/toolkits/effect/skills/effect-v4 .claude/skills/effect-v4 $ npx degit Chan-Software-Services/agent-team/toolkits/frontend/skills/fixing-the-selected-element .claude/skills/fixing-the-selected-element $ npx degit Chan-Software-Services/agent-team/toolkits/prod-mongo/skills/backing-up-production-data .claude/skills/backing-up-production-data $ npx degit Chan-Software-Services/agent-team/toolkits/prod-mongo/skills/rehearsing-production-changes .claude/skills/rehearsing-production-changes $ npx degit Chan-Software-Services/agent-team/toolkits/prod-read/skills/querying-production-data .claude/skills/querying-production-data $ npx degit Chan-Software-Services/agent-team/toolkits/prod-write/skills/changing-production-data .claude/skills/changing-production-data $ npx degit Chan-Software-Services/agent-team/toolkits/spec-review/skills/claims-check .claude/skills/claims-check $ npx degit Chan-Software-Services/agent-team/toolkits/spec-review/skills/spec-review .claude/skills/spec-review $ npx degit Chan-Software-Services/agent-team/toolkits/vercel-read/skills/reading-vercel-deployments .claude/skills/reading-vercel-deployments
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 (5)
| server | source | est. tokens |
|---|---|---|
| foldkit-devtools env: FOLDKIT_PROJECT_ROOT | local / custom | 2.5k |
| frontend env: CHROME_DEVTOOLS_MCP_NO_UPDATE_CHECKS, CHROME_DEVTOOLS_MCP_NO_USAGE_STATISTICS | local / custom | 2.5k |
| prod-mongo | local / custom | 2.5k |
| prod-read | local / custom | 2.5k |
| prod-write | local / custom | 2.5k |
Skills (18)
Similar rigs
chanjdaniel/agent-team
Daniel's agent team: the scripts, prompts, settings and hooks that run a coordinator and its Claude Code workers
Skill Collector 21.5k tok · · Q20
holland-built/no-yolo
Rules and skills for Claude Code: it asks before guessing, answers short, and gets a second opinion before costly work.
YOLO Cowboy 3.3k tok · · Q12
Akku/agentic-coding-starter-kit
Minimal, growing starter kit for agent-driven development with Git and Backlog.md (Claude Code, Codex, Copilot)
Pragmatist 1.3k tok · · Q0
Suksan01/agent-hq
Agent HQ: a live command center for Claude Code agent teams
Pragmatist 506 tok · · Q0