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 leandronsp/dotfiles/claude/.claude ./rig-dotfiles # 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 leandronsp/dotfiles/claude/.claude/skills/browser .claude/skills/browser $ npx degit leandronsp/dotfiles/claude/.claude/skills/bugfix .claude/skills/bugfix $ npx degit leandronsp/dotfiles/claude/.claude/skills/cms .claude/skills/cms $ npx degit leandronsp/dotfiles/claude/.claude/skills/commit .claude/skills/commit $ npx degit leandronsp/dotfiles/claude/.claude/skills/crew .claude/skills/crew $ npx degit leandronsp/dotfiles/claude/.claude/skills/dev .claude/skills/dev $ npx degit leandronsp/dotfiles/claude/.claude/skills/explainer .claude/skills/explainer $ npx degit leandronsp/dotfiles/claude/.claude/skills/ffmpeg-video-editing .claude/skills/ffmpeg-video-editing $ npx degit leandronsp/dotfiles/claude/.claude/skills/finance-ask .claude/skills/finance-ask $ npx degit leandronsp/dotfiles/claude/.claude/skills/finance-update .claude/skills/finance-update $ npx degit leandronsp/dotfiles/claude/.claude/skills/ghostwriter .claude/skills/ghostwriter $ npx degit leandronsp/dotfiles/claude/.claude/skills/handoff .claude/skills/handoff $ npx degit leandronsp/dotfiles/claude/.claude/skills/note .claude/skills/note $ npx degit leandronsp/dotfiles/claude/.claude/skills/ocr .claude/skills/ocr $ npx degit leandronsp/dotfiles/claude/.claude/skills/pagespeed .claude/skills/pagespeed $ npx degit leandronsp/dotfiles/claude/.claude/skills/pair .claude/skills/pair $ npx degit leandronsp/dotfiles/claude/.claude/skills/pentest .claude/skills/pentest $ npx degit leandronsp/dotfiles/claude/.claude/skills/po .claude/skills/po $ npx degit leandronsp/dotfiles/claude/.claude/skills/procs .claude/skills/procs $ npx degit leandronsp/dotfiles/claude/.claude/skills/qa .claude/skills/qa $ npx degit leandronsp/dotfiles/claude/.claude/skills/recap .claude/skills/recap $ npx degit leandronsp/dotfiles/claude/.claude/skills/review .claude/skills/review $ npx degit leandronsp/dotfiles/claude/.claude/skills/skill-creator .claude/skills/skill-creator $ npx degit leandronsp/dotfiles/claude/.claude/skills/smoke .claude/skills/smoke $ npx degit leandronsp/dotfiles/claude/.claude/skills/step .claude/skills/step $ npx degit leandronsp/dotfiles/claude/.claude/skills/sync .claude/skills/sync $ npx degit leandronsp/dotfiles/claude/.claude/skills/tui-test .claude/skills/tui-test $ npx degit leandronsp/dotfiles/claude/.claude/skills/vault .claude/skills/vault $ npx degit leandronsp/dotfiles/claude/.claude/skills/walk .claude/skills/walk $ npx degit leandronsp/dotfiles/claude/.claude/skills/wtf .claude/skills/wtf
$ curl -fsSL --create-dirs -o .claude/agents/performance-reviewer.md https://raw.githubusercontent.com/leandronsp/dotfiles/main/claude/.claude/agents/performance-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/quality-reviewer.md https://raw.githubusercontent.com/leandronsp/dotfiles/main/claude/.claude/agents/quality-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/review-auditor.md https://raw.githubusercontent.com/leandronsp/dotfiles/main/claude/.claude/agents/review-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/scout.md https://raw.githubusercontent.com/leandronsp/dotfiles/main/claude/.claude/agents/scout.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/leandronsp/dotfiles/main/claude/.claude/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-driver.md https://raw.githubusercontent.com/leandronsp/dotfiles/main/claude/.claude/agents/tdd-driver.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-navigator.md https://raw.githubusercontent.com/leandronsp/dotfiles/main/claude/.claude/agents/tdd-navigator.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 *)"
]
}
} Skills (30)
browserbugfixcmscommitcrewdevexplainerffmpeg-video-editingfinance-askfinance-updateghostwriterhandoffnoteocrpagespeedpairpentestpoprocsqarecapreviewskill-creatorsmokestepsynctui-testvaultwalkwtf
Subagents (7)
| performance-reviewer model: claude-sonnet-5 | Performance-focused code reviewer. Finds N+1 queries, missing indexes, memory leaks, hot loops, cache misses, blocking I/O, unnecessary allocations. |
| quality-reviewer model: claude-sonnet-5 | Code quality reviewer. Design, architecture, testing, naming, SOLID, DDD, clean code, error handling, modularity, readability. |
| review-auditor model: claude-opus-5 | Red team auditor. Reviews the reviewers. Finds blind spots, false positives, contradictions, missed context, severity miscalibration. |
| scout model: claude-haiku-4-5 | Fast codebase recon. Maps architecture, patterns, conventions, test structure, error handling. Returns compressed context for downstream agents. |
| security-reviewer model: claude-sonnet-5 | Security-focused code reviewer. Finds auth bypasses, injection, secrets, unsafe deserialization, SSRF, path traversal, timing attacks, race conditions. |
| tdd-driver model: claude-sonnet-5 | TDD driver in adversarial pair programming. Proposes one test idea at a time with single assertion and minimal setup, writes failing test, then minimum code to pass. Baby steps enforced. Used by /dev |
| tdd-navigator model: claude-sonnet-5 | TDD navigator in adversarial pair programming. Gates each driver turn: test-idea size, RED-for-right-reason, minimum-code discipline, baby-step slippage. Adversarial, not rubber-stamp. Used by /dev Mo |
Similar rigs
heliohq/ship
An agentic development harness for Claude Code, Codex & Cursor: gated pipeline from spec to green checks.
Skill Collector 3.7k tok ·
haacked/dotfiles
My dotfiles and scripts I use on dev machines
Skill Collector 4.1k tok ·
lwalden/AIAgentMinder
Project governance for AI-assisted development. Structured planning, sprint workflows, decision tracking, and scope enforcement — built as plain markdown files and slash commands on top of Claude Code.
Orchestrator 2.8k tok ·
bkrishnamachari/claude-elements
Claude Code configuration: CLAUDE.md guidelines, skills, hooks, and settings
Minimalist 967 tok ·