andrewchoi-hds/claude-code-config
Claude Code custom agents and slash commands for optimized development workflow
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit andrewchoi-hds/claude-code-config/.claude ./rig-claude-code-config # 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/documenter.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/base/documenter.md $ curl -fsSL --create-dirs -o .claude/agents/e2e-tester.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/base/e2e-tester.md $ curl -fsSL --create-dirs -o .claude/agents/explorer.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/base/explorer.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/base/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tester.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/base/tester.md $ curl -fsSL --create-dirs -o .claude/agents/backend.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/domain/backend.md $ curl -fsSL --create-dirs -o .claude/agents/bm-master.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/domain/bm-master.md $ curl -fsSL --create-dirs -o .claude/agents/data-ml.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/domain/data-ml.md $ curl -fsSL --create-dirs -o .claude/agents/design.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/domain/design.md $ curl -fsSL --create-dirs -o .claude/agents/devops.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/domain/devops.md $ curl -fsSL --create-dirs -o .claude/agents/evil-user.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/domain/evil-user.md $ curl -fsSL --create-dirs -o .claude/agents/frontend.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/domain/frontend.md $ curl -fsSL --create-dirs -o .claude/agents/mcp-design.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/domain/mcp-design.md $ curl -fsSL --create-dirs -o .claude/agents/mcp-github.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/domain/mcp-github.md $ curl -fsSL --create-dirs -o .claude/agents/mcp-notify.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/domain/mcp-notify.md $ curl -fsSL --create-dirs -o .claude/agents/mobile.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/domain/mobile.md $ curl -fsSL --create-dirs -o .claude/agents/pm.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/domain/pm.md $ curl -fsSL --create-dirs -o .claude/agents/product-planner.md https://raw.githubusercontent.com/andrewchoi-hds/claude-code-config/main/.claude/agents/domain/product-planner.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Subagents (18)
| documenter | — |
| e2e-tester | — |
| explorer | — |
| reviewer | — |
| tester | — |
| backend | — |
| bm-master | — |
| data-ml | — |
| design | — |
| devops | — |
| evil-user | — |
| frontend | — |
| mcp-design | — |
| mcp-github | — |
| mcp-notify | — |
| mobile | — |
| pm | — |
| product-planner | — |
Slash commands (12)
/analyze/deploy/doc/init/map/metrics/optimize/review/tdd/test/todo/wrap
Similar rigs
BillDX/spicy-to-dark-factory-starter
Workshop starter for 'From Spicy Autocomplete to Dark Factory: Agentic Coding in Practice' — a FastAPI mini-app with a full Claude Code harness (agents, slash commands, hooks, sandbox settings) and self-paced exercises.
Orchestrator 706 tok ·
eugeek/claude-config-tdd
Claude Code config with TDD workflow, plan -> tests -> red -> implementation -> green -> review -> shipment
Orchestrator 5.8k tok ·
YounusHussain9/claude-agent-workspace
Multi-repo workspace for Claude Code: plain-language requests, specialist AI agents, approval gates and safety hooks.
Fort Knox 2.0k tok ·
simscal/sapiens-dtj
GitHub-native, human-gated AI workflow for Claude Code: agents execute, sapiens gate every step
Pragmatist 759 tok ·