noahlz/claude-code-config
My Claude Code global config, prompt, output style and custom hooks.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ npx degit noahlz/claude-code-config/agents ./rig-claude-code-config/agents $ npx degit noahlz/claude-code-config/skills ./rig-claude-code-config/skills $ npx degit noahlz/claude-code-config/hooks ./rig-claude-code-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 noahlz/claude-code-config/skills/set-voice .claude/skills/set-voice $ curl -fsSL --create-dirs -o .claude/agents/coder-haiku.md https://raw.githubusercontent.com/noahlz/claude-code-config/main/agents/coder-haiku.md $ curl -fsSL --create-dirs -o .claude/agents/coder-opus.md https://raw.githubusercontent.com/noahlz/claude-code-config/main/agents/coder-opus.md $ curl -fsSL --create-dirs -o .claude/agents/coder-sonnet.md https://raw.githubusercontent.com/noahlz/claude-code-config/main/agents/coder-sonnet.md $ curl -fsSL --create-dirs -o .claude/agents/judge-opus.md https://raw.githubusercontent.com/noahlz/claude-code-config/main/agents/judge-opus.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 (4)
| coder-haiku model: haiku | Implementation subagent for zero-judgment coding – mechanical migrations, renames and find-replace across files, boilerplate, or logic whose exact behavior the prompt spells out (signatures, inputs, o |
| coder-opus model: opus | Implementation subagent for work that needs judgment — refactoring, non-obvious business logic, or a batch of individual decisions where a wrong call is expensive and silent. Use when the dispatch pro |
| coder-sonnet model: sonnet | Implementation subagent for mechanical, well-specified work — writing tests, applying a change described in the prompt, enumerating or transcribing from source. Use when the dispatch prompt already co |
| judge-opus model: opus | Opus subagent for high-stakes judgment batches whose failure mode is silent — triaging test coverage before a deletion, classifying cases where a wrong call still leaves a green suite, deciding what b |
Similar rigs
anomalyco/opencode
The open source coding agent.
Pragmatist 4.2k tok ·
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Pragmatist 1.6k tok ·
Shubhamsaboo/awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
Pragmatist 4.2k tok ·
garrytan/gstack
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Pragmatist 8.8k tok ·