theishandubey/claude-config
A complete Claude Code setup. An agent roster, an orchestration playbook, safe defaults and curated skills, installed with one command.
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 theishandubey/claude-config/agents ./rig-claude-config/agents $ npx degit theishandubey/claude-config/skills ./rig-claude-config/skills $ npx degit theishandubey/claude-config/hooks ./rig-claude-config/hooks
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 theishandubey/claude-config/skills/parallel-build .claude/skills/parallel-build $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/theishandubey/claude-config/main/agents/advisors/architect.md $ curl -fsSL --create-dirs -o .claude/agents/backend-engineer.md https://raw.githubusercontent.com/theishandubey/claude-config/main/agents/advisors/backend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/theishandubey/claude-config/main/agents/advisors/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-engineer.md https://raw.githubusercontent.com/theishandubey/claude-config/main/agents/advisors/frontend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/qa-lead.md https://raw.githubusercontent.com/theishandubey/claude-config/main/agents/advisors/qa-lead.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/theishandubey/claude-config/main/agents/advisors/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/sre.md https://raw.githubusercontent.com/theishandubey/claude-config/main/agents/advisors/sre.md $ curl -fsSL --create-dirs -o .claude/agents/explorer.md https://raw.githubusercontent.com/theishandubey/claude-config/main/agents/explorers/explorer.md $ curl -fsSL --create-dirs -o .claude/agents/web-researcher.md https://raw.githubusercontent.com/theishandubey/claude-config/main/agents/explorers/web-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/doc-writer.md https://raw.githubusercontent.com/theishandubey/claude-config/main/agents/workers/doc-writer.md $ curl -fsSL --create-dirs -o .claude/agents/fixer.md https://raw.githubusercontent.com/theishandubey/claude-config/main/agents/workers/fixer.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/theishandubey/claude-config/main/agents/workers/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/parallel-implementer.md https://raw.githubusercontent.com/theishandubey/claude-config/main/agents/workers/parallel-implementer.md $ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/theishandubey/claude-config/main/agents/workers/test-writer.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 (1)
Subagents (14)
| architect model: opus | Principal software architect advisor. Use PROACTIVELY before any non-trivial feature, refactor, or design decision. Produces designs, ADRs, trade-off analyses, and implementation plans. Advisory only |
| backend-engineer model: opus | Staff backend engineering advisor for APIs, services, databases, queues, caching, auth, and data modeling. Use PROACTIVELY when designing endpoints, schemas, migrations, or debugging complex server-si |
| code-reviewer model: opus | Senior code review advisor for quality, correctness, and maintainability. Use PROACTIVELY after any worker agent finishes implementing, and before commits. Read-only; never modifies code. |
| frontend-engineer model: opus | Staff frontend engineering advisor for component architecture, state management, rendering performance, accessibility, and design-system consistency. Use PROACTIVELY when designing UI features or revi |
| qa-lead model: opus | QA lead advisor for end-to-end test strategy, coverage analysis, and risk-based verification planning. Plans end-to-end tests only, never unit tests. Use PROACTIVELY after a feature is planned (to def |
| security-reviewer model: opus | Application security advisor for auth, sessions, user input, file handling, secrets, dependencies, SQL, and network boundaries. Dispatch ONLY when the user explicitly asks for a security review - neve |
| sre model: opus | Site Reliability Engineering advisor for infrastructure, CI/CD, observability, incident response, capacity, and deployment safety. Use PROACTIVELY before deploys, infra changes, or when diagnosing pro |
| explorer model: sonnet | Fast, cheap, read-only codebase scout. Use PROACTIVELY for any search, discovery, or "how does X work / where is Y defined / what would Z touch" question, so verbose exploration output never pollutes |
| web-researcher model: sonnet | Cheap, read-only web research scout. Use for looking up library docs, API references, error messages, changelogs, and best practices online - keeping noisy web content out of the main context. Cannot |
| doc-writer model: sonnet | Documentation worker. Writes and updates READMEs, API docs, and other standalone doc files after code changes. External docs only - never adds docstrings or inline comments to code files. |
| fixer model: sonnet | Debugging and remediation worker. Fixes failing tests, build breaks, lint errors, bugs with reproductions, and findings from the code-reviewer or security-reviewer advisors. Use proactively whenever s |
| implementer model: sonnet | General-purpose implementation worker. Executes well-specified coding tasks - writing features, endpoints, components, and modules from a plan. Use for any execution work after an advisor or the main |
| parallel-implementer model: sonnet | Isolated implementation worker that runs in its own temporary git worktree. Use when spawning MULTIPLE implementers in parallel on the same repo so their edits cannot collide. Each instance gets a cle |
| test-writer model: sonnet | Test implementation worker. Writes and fixes end-to-end tests, never unit tests, from a test plan (typically produced by the qa-lead advisor) or for a specified feature. Use whenever tests need to be |
Similar rigs
Dipen-Dedania/agent-pulse
Know what your agents are doing
Orchestrator 1.7k tok ·
ameya-vichare/claude-sdd-starter
A platform-agnostic Claude Code setup for engineering teams, using an interactive setup wizard that tailors everything to your project and provides a spec-driven feature development workflow.
Orchestrator 2.3k tok ·
roadhero/claude-code-setup
My actual Claude Code setup: a stack-agnostic engineering spine, auto-activating rule packs, 50 scoped subagents across web/Android/iOS/compute, safety hooks, and a repo scaffolder. From the book "42: The AI Builder's Stack."
Orchestrator 7.3k tok ·
Yuutokata/claude-code-setup
🔄 One Claude Code setup for my desktop and MacBook, synced through git, with guardrails that keep secrets out.
Fort Knox 1.1k tok ·