thrawn01/claude-dotfiles
Claude Configuration Repository
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 thrawn01/claude-dotfiles/agents ./rig-claude-dotfiles/agents $ npx degit thrawn01/claude-dotfiles/skills ./rig-claude-dotfiles/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 thrawn01/claude-dotfiles/skills/adr-write .claude/skills/adr-write $ npx degit thrawn01/claude-dotfiles/skills/babysit-pr .claude/skills/babysit-pr $ npx degit thrawn01/claude-dotfiles/skills/blueprint-adr-audit .claude/skills/blueprint-adr-audit $ npx degit thrawn01/claude-dotfiles/skills/blueprint-create .claude/skills/blueprint-create $ npx degit thrawn01/claude-dotfiles/skills/blueprint-review .claude/skills/blueprint-review $ npx degit thrawn01/claude-dotfiles/skills/bug-detector .claude/skills/bug-detector $ npx degit thrawn01/claude-dotfiles/skills/captain-done .claude/skills/captain-done $ npx degit thrawn01/claude-dotfiles/skills/captain .claude/skills/captain $ npx degit thrawn01/claude-dotfiles/skills/decisions-capture .claude/skills/decisions-capture $ npx degit thrawn01/claude-dotfiles/skills/deliberate .claude/skills/deliberate $ npx degit thrawn01/claude-dotfiles/skills/goal-from-spec .claude/skills/goal-from-spec $ npx degit thrawn01/claude-dotfiles/skills/grill-me .claude/skills/grill-me $ npx degit thrawn01/claude-dotfiles/skills/handoff .claude/skills/handoff $ npx degit thrawn01/claude-dotfiles/skills/html-explainer .claude/skills/html-explainer $ npx degit thrawn01/claude-dotfiles/skills/invariant-test .claude/skills/invariant-test $ npx degit thrawn01/claude-dotfiles/skills/lazy .claude/skills/lazy $ npx degit thrawn01/claude-dotfiles/skills/linear-handoff .claude/skills/linear-handoff $ npx degit thrawn01/claude-dotfiles/skills/linear-resume .claude/skills/linear-resume $ npx degit thrawn01/claude-dotfiles/skills/linear-start .claude/skills/linear-start $ npx degit thrawn01/claude-dotfiles/skills/no-ai-slop .claude/skills/no-ai-slop $ npx degit thrawn01/claude-dotfiles/skills/pr-github-review .claude/skills/pr-github-review $ npx degit thrawn01/claude-dotfiles/skills/review-behavior-change .claude/skills/review-behavior-change $ npx degit thrawn01/claude-dotfiles/skills/review-captain .claude/skills/review-captain $ npx degit thrawn01/claude-dotfiles/skills/review-comments .claude/skills/review-comments $ npx degit thrawn01/claude-dotfiles/skills/review-for-reader .claude/skills/review-for-reader $ npx degit thrawn01/claude-dotfiles/skills/review-guidelines .claude/skills/review-guidelines $ npx degit thrawn01/claude-dotfiles/skills/review-openapi .claude/skills/review-openapi $ npx degit thrawn01/claude-dotfiles/skills/review-status .claude/skills/review-status $ npx degit thrawn01/claude-dotfiles/skills/review-suite .claude/skills/review-suite $ npx degit thrawn01/claude-dotfiles/skills/review-tests .claude/skills/review-tests $ npx degit thrawn01/claude-dotfiles/skills/review-validate .claude/skills/review-validate $ npx degit thrawn01/claude-dotfiles/skills/review-worker-start .claude/skills/review-worker-start $ npx degit thrawn01/claude-dotfiles/skills/show-work .claude/skills/show-work $ npx degit thrawn01/claude-dotfiles/skills/spec-to-comms .claude/skills/spec-to-comms $ npx degit thrawn01/claude-dotfiles/skills/surface-testing .claude/skills/surface-testing $ npx degit thrawn01/claude-dotfiles/skills/writing-prose .claude/skills/writing-prose $ npx degit thrawn01/claude-dotfiles/skills/writing-style .claude/skills/writing-style
$ curl -fsSL --create-dirs -o .claude/agents/codebase-analyzer.md https://raw.githubusercontent.com/thrawn01/claude-dotfiles/main/agents/codebase-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/codebase-guidelines-validator.md https://raw.githubusercontent.com/thrawn01/claude-dotfiles/main/agents/codebase-guidelines-validator.md $ curl -fsSL --create-dirs -o .claude/agents/codebase-locator.md https://raw.githubusercontent.com/thrawn01/claude-dotfiles/main/agents/codebase-locator.md $ curl -fsSL --create-dirs -o .claude/agents/codebase-pattern-finder.md https://raw.githubusercontent.com/thrawn01/claude-dotfiles/main/agents/codebase-pattern-finder.md $ curl -fsSL --create-dirs -o .claude/agents/codebase-review-critical.md https://raw.githubusercontent.com/thrawn01/claude-dotfiles/main/agents/codebase-review-critical.md $ curl -fsSL --create-dirs -o .claude/agents/phase-implementer.md https://raw.githubusercontent.com/thrawn01/claude-dotfiles/main/agents/phase-implementer.md $ curl -fsSL --create-dirs -o .claude/agents/thoughts-analyzer.md https://raw.githubusercontent.com/thrawn01/claude-dotfiles/main/agents/thoughts-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/thoughts-locator.md https://raw.githubusercontent.com/thrawn01/claude-dotfiles/main/agents/thoughts-locator.md $ curl -fsSL --create-dirs -o .claude/agents/web-search-researcher.md https://raw.githubusercontent.com/thrawn01/claude-dotfiles/main/agents/web-search-researcher.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 (37)
adr-writebabysit-prblueprint-adr-auditblueprint-createblueprint-reviewbug-detectorcaptain-donecaptaindecisions-capturedeliberategoal-from-specgrill-mehandoffhtml-explainerinvariant-testlazylinear-handofflinear-resumelinear-startno-ai-sloppr-github-reviewreview-behavior-changereview-captainreview-commentsreview-for-readerreview-guidelinesreview-openapireview-statusreview-suitereview-testsreview-validatereview-worker-startshow-workspec-to-commssurface-testingwriting-prosewriting-style
Subagents (9)
| codebase-analyzer model: sonnet | Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the b |
| codebase-guidelines-validator model: sonnet | Use this agent when you need to validate that code follows the CLAUDE.md guidelines and coding standards. This includes checking for proper test patterns, code formatting, struct field ordering, varia |
| codebase-locator model: haiku | Locates files, directories, and components relevant to a feature or task. Call `codebase-locator` with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — |
| codebase-pattern-finder model: haiku | codebase-pattern-finder is a useful subagent_type for finding similar implementations, usage examples, or existing patterns that can be modeled after. It will give you concrete code examples based on |
| code-review-critical model: sonnet | Use this agent when you need to review recently written or modified code for critical issues that could impact production. This agent focuses exclusively on bugs, performance problems, security vulner |
| phase-implementer model: sonnet | Implements a single phase from a multi-phase technical plan with testing and verification |
| thoughts-analyzer model: sonnet | The research equivalent of codebase-analyzer. Use this subagent_type when wanting to deep dive on a research topic. Not commonly needed otherwise. |
| thoughts-locator model: haiku | Discovers relevant documents in thoughts/ directory (We use this for all sorts of metadata storage!). This is really only relevant/needed when you're in a reseaching mood and need to figure out if we |
| web-search-researcher model: sonnet | Do you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the web-search-researcher |
Similar rigs
humanlayer/humanlayer
The best way to get AI coding agents to solve hard problems in complex codebases.
Orchestrator 2.7k tok ·
jeffersonBastos/precis
A comprehensive template for Claude Code projects with pre-configured commands, agents, and workflows.
Orchestrator 982 tok ·
luke-kerwin/claude-code-setup
Personal setup for claude code projects
Orchestrator 19.4k tok ·
medusajs/medusa
The world's most flexible commerce platform for agents and developers
Pragmatist 4.4k tok ·