AndreAlbuquerque/claude-config
Personal Claude Code config — global CLAUDE.md, agents (@pm, @visionary, @discovery, @designer, @engineer, @implementer, @researcher, @reviewer, @qa), and skills, synced across machines.
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 AndreAlbuquerque/claude-config/agents ./rig-claude-config/agents $ npx degit AndreAlbuquerque/claude-config/skills ./rig-claude-config/skills
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 AndreAlbuquerque/claude-config/skills/bootstrap .claude/skills/bootstrap $ npx degit AndreAlbuquerque/claude-config/skills/deep-review .claude/skills/deep-review $ npx degit AndreAlbuquerque/claude-config/skills/deploy .claude/skills/deploy $ npx degit AndreAlbuquerque/claude-config/skills/fix .claude/skills/fix $ npx degit AndreAlbuquerque/claude-config/skills/improve .claude/skills/improve $ npx degit AndreAlbuquerque/claude-config/skills/jtbd .claude/skills/jtbd $ npx degit AndreAlbuquerque/claude-config/skills/merge .claude/skills/merge $ npx degit AndreAlbuquerque/claude-config/skills/moscow .claude/skills/moscow $ npx degit AndreAlbuquerque/claude-config/skills/ost .claude/skills/ost $ npx degit AndreAlbuquerque/claude-config/skills/plan .claude/skills/plan $ npx degit AndreAlbuquerque/claude-config/skills/pm .claude/skills/pm $ npx degit AndreAlbuquerque/claude-config/skills/qa .claude/skills/qa $ npx degit AndreAlbuquerque/claude-config/skills/recap .claude/skills/recap $ npx degit AndreAlbuquerque/claude-config/skills/research .claude/skills/research
$ curl -fsSL --create-dirs -o .claude/agents/designer.md https://raw.githubusercontent.com/AndreAlbuquerque/claude-config/main/agents/designer.md $ curl -fsSL --create-dirs -o .claude/agents/discovery.md https://raw.githubusercontent.com/AndreAlbuquerque/claude-config/main/agents/discovery.md $ curl -fsSL --create-dirs -o .claude/agents/engineer.md https://raw.githubusercontent.com/AndreAlbuquerque/claude-config/main/agents/engineer.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/AndreAlbuquerque/claude-config/main/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/pm.md https://raw.githubusercontent.com/AndreAlbuquerque/claude-config/main/agents/pm.md $ curl -fsSL --create-dirs -o .claude/agents/qa.md https://raw.githubusercontent.com/AndreAlbuquerque/claude-config/main/agents/qa.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/AndreAlbuquerque/claude-config/main/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/AndreAlbuquerque/claude-config/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/visionary.md https://raw.githubusercontent.com/AndreAlbuquerque/claude-config/main/agents/visionary.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,413 rigs:
{
"permissions": {
"deny": [
"Read(~/.ssh/**)",
"Read(**/.env)",
"Bash(rm -rf *)",
"Read(./.env)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(**/*.pem)",
"Bash(rm -rf /*)",
"Read(~/.aws/**)",
"Bash(rm -rf:*)",
"Read(.env)",
"Bash(git push --force*)",
"Read(**/*.key)",
"Read(./.env.*)",
"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(wget *)",
"Bash(npm publish:*)",
"Bash(gh pr merge *)",
"Bash(chown *)",
"Bash(docker *)"
]
}
} Skills (14)
Subagents (9)
| designer model: sonnet | Strategic design specialist. Use when a feature introduces a net-new UI surface, changes a user flow, touches IA/navigation, lacks a fitting design-system pattern, or has material accessibility concer |
| discovery model: sonnet | Discovery specialist. Use when a feature idea needs to be shaped before implementation — runs JTBD → OST → MoSCoW skills in sequence and writes the canvases to a local markdown file. Invoked by @pm wh |
| engineer model: sonnet | Strategic engineering specialist. Use when a feature introduces a new module/service, is cross-cutting, performance-sensitive, requires a new dependency, establishes a new pattern, or raises a real bu |
| implementer model: sonnet | Safe implementation specialist. Use for bounded changes, bug fixes, minimal safe patches, small feature work, and concrete implementation steps after requirements are clear. |
| pm model: sonnet | Product orchestrator for Builders Camp Claude OS. Use for every incoming task to classify the request, choose the minimum correct workflow, decide whether to delegate to specialist agents, and define |
| qa model: sonnet | Product QA and release-safety specialist. Use for acceptance criteria, user journeys, regression risk, functional and non-functional checks, release readiness, and validating whether work is truly don |
| researcher model: sonnet | Research and discovery specialist. Use for concept research, codebase discovery, option analysis, best practices, tradeoffs, unclear requirements, and decision framing before planning or implementatio |
| reviewer model: sonnet | Deep technical review specialist. Use for architecture review, large changes, refactors, performance or security concerns, code-quality audits, and identifying structural risks before or after impleme |
| visionary model: sonnet | Visionary/strategy specialist. Rare — sits optionally above @discovery. Use only when the request is about product or company direction itself (not a scoped feature), uses explicit strategy vocabulary |
Similar rigs
chrille0313/agentic-monorepo-template
Stack-agnostic monorepo template where agents are the workflow: PM → implementer → fresh-context reviewer loops via Claude Code subagents, skills, and GitHub Actions
Pragmatist 1.5k tok ·
sohaibdevv/Claude-Starter-Kit
A pre-built configuration that gives Claude Code persistent memory, security guardrails, and structured workflows. Clone, run setup.sh, and your next session picks up where the last one left off.
Pragmatist 435 tok ·
zeuikli/claude-code-workspace
—
Orchestrator 3.3k tok ·
Markuysa/vibe-coding-template
Claude Code project template: five agent roles with tool-level permission boundaries, four workflow commands, and a permission baseline that keeps secrets and build noise out of context. Built on native worktrees and subagents — no third-pa
Fort Knox 1.2k tok ·