axrmxv/claude-config
Portable, layered .claude configuration for Claude Code — reusable dev standards, specialized review agents, and an extension model you can drop into any project.
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 axrmxv/claude-config/.claude ./rig-claude-config # 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.
$ npx degit axrmxv/claude-config/skills/add-agent .claude/skills/add-agent $ npx degit axrmxv/claude-config/skills/add-standards-layer .claude/skills/add-standards-layer $ npx degit axrmxv/claude-config/skills/audit-config .claude/skills/audit-config $ npx degit axrmxv/claude-config/skills/plan-feature .claude/skills/plan-feature $ npx degit axrmxv/claude-config/skills/research-reuse .claude/skills/research-reuse $ npx degit axrmxv/claude-config/skills/review-changes .claude/skills/review-changes $ npx degit axrmxv/claude-config/skills/ship .claude/skills/ship $ npx degit axrmxv/claude-config/skills/standards-fastapi .claude/skills/standards-fastapi $ npx degit axrmxv/claude-config/skills/standards-python .claude/skills/standards-python $ npx degit axrmxv/claude-config/skills/standards-typescript .claude/skills/standards-typescript $ npx degit axrmxv/claude-config/skills/tdd .claude/skills/tdd
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/axrmxv/claude-config/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/build-error-resolver.md https://raw.githubusercontent.com/axrmxv/claude-config/main/agents/build-error-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/axrmxv/claude-config/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/doc-updater.md https://raw.githubusercontent.com/axrmxv/claude-config/main/agents/doc-updater.md $ curl -fsSL --create-dirs -o .claude/agents/e2e-runner.md https://raw.githubusercontent.com/axrmxv/claude-config/main/agents/e2e-runner.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/axrmxv/claude-config/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/refactor-cleaner.md https://raw.githubusercontent.com/axrmxv/claude-config/main/agents/refactor-cleaner.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/axrmxv/claude-config/main/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-guide.md https://raw.githubusercontent.com/axrmxv/claude-config/main/agents/tdd-guide.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 (11)
add-agentadd-standards-layeraudit-configplan-featureresearch-reusereview-changesshipstandards-fastapistandards-pythonstandards-typescripttdd
Subagents (9)
| architect model: opus | Use for system-design and architectural decisions — module boundaries, data flow, technology trade-offs, scaling. Produces a design, not code. |
| build-error-resolver model: sonnet | Use when a build, compile, or type-check fails. Diagnoses the root cause and fixes errors incrementally, verifying after each fix. |
| code-reviewer model: sonnet | Use immediately after writing or modifying code. Reviews quality, patterns, and best practices and reports findings by severity. Read-only — does not edit. |
| doc-updater model: haiku | Use to update documentation (README, docstrings, comments, changelogs) after behavior or interface changes. Keeps docs in sync with code. |
| e2e-runner model: sonnet | Use to run and triage end-to-end tests for critical user flows. Reports failures with reproduction context. |
| planner model: opus | Use PROACTIVELY before writing code for complex features, multi-step changes, or refactoring. Produces a phased implementation plan with dependencies and risks. Does not write code. |
| refactor-cleaner model: sonnet | Use for dead-code removal and structural cleanup. Preserves behavior and relies on tests to confirm no regressions. |
| security-reviewer model: opus | Use before commits and whenever authentication, authorization, user input, database queries, file/system operations, cryptography, or payment code changes. OWASP-focused. Read-only. |
| tdd-guide model: sonnet | Use PROACTIVELY for new features and bug fixes. Enforces test-first development (RED → GREEN → refactor) and the 80% coverage minimum. |
Permissions
deny (0)
—
ask (0)
—
allow (17)
Bash(black:*)
Bash(isort:*)
Bash(ruff:*)
Bash(mypy:*)
Bash(pyright:*)
Bash(bandit:*)
Bash(pytest:*)
Bash(prettier:*)
Bash(eslint:*)
Bash(tsc:*)
Bash(vitest:*)
Bash(jest:*)
Bash(npm test:*)
Bash(git status)
Bash(git diff:*)
Bash(git log:*)
Bash(gh search:*)
Similar rigs
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 ·
cfrs2005/claude-init
Claude Code 中文开发套件 - 为中国开发者定制的零门槛 AI 编程环境。一键安装完整中文化体验，集成 MCP 服务器、智能上下文管理、安全扫描，支持免翻墙访问。让 AI 编程更简单。
Orchestrator 1.5k tok ·
mh2-lee/everything-claude-code
Complete Claude Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.
Orchestrator 1.2k tok ·
hirokami3/everything-claude-code
Claude Code configs collection - agents, skills, hooks, commands, rules, and MCP configurations
Orchestrator 1.2k tok ·