~ / rigs / rse / claude-code-setup

rse/claude-code-setup

Claude Code Setup

↗ GitHub ★ 17 no license updated 7mo ago personal setup Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~13 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
3/5
Protects secrets · No YOLO mode · Sandbox or ask-first rules · details

Copy this rig

# review before running: this installs third-party code
$ npx degit rse/claude-code-setup/.claude ./rig-claude-code-setup  # 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/llm.md https://raw.githubusercontent.com/rse/claude-code-setup/master/.claude/agents/llm.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "permissions": {
    "deny": [
      "Read(./.env)"
    ],
    "ask": [
      "Write",
      "Edit",
      "MultiEdit"
    ]
  }
}

Subagents (1)

LLM
model: haiku
Query Foreign LLM

Slash commands (22)

/brave/changes/craft/exa/explain/github/hint/lint/lint/complete/lint/explain/lint/nope/lint/reassess/lint/recheck/lint/refine/llm/meta/prolog/prime/quorum/ref/refactor/suck/why

Permissions

deny (1)
Read(./.env)
ask (3)
Write
Edit
MultiEdit
allow (28)
Bash(ls:*)
Bash(find:*)
Bash(date:*)
Bash(git diff:*)
Bash(git log:*)
Bash(git tag:list:*)
Bash(npm install)
Bash(npm start lint)
Bash(npm start build)
Bash(npm start test)
Bash(npm test)
Bash(npm show)
Bash(npm view)
Read(./dst*)
Bash(curl:*)
Bash(wget:*)
WebFetch
WebSearch
mcp__chat-openai-chatgpt
mcp__chat-google-gemini
mcp__chat-alibaba-qwen
mcp__chat-deepseek
mcp__chat-microsoft-phi
mcp__chat-xai-grok
mcp__github
mcp__ref
mcp__exa
mcp__brave

Similar rigs

copied ✓