~ / rigs / skateddu / claude-code-python-setup

skateddu/claude-code-python-setup

Ready-to-use .claude configuration for Python projects: agents, skills, commands, rules, and MCP server templates for Claude Code.

↗ GitHub ★ 28 MIT updated 2d ago personal setup Claude Code

share on X

ARCHETYPE

Fort Knox

Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.

CONTEXT TAX · EVERY TURN

~7.9k tokens

Heavy · median rig: 2.3k · breakdown

GUARDRAILS

4/5

Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit skateddu/claude-code-python-setup/.claude ./rig-claude-code-python-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.

$ npx degit skateddu/claude-code-python-setup/.claude/skills/api-design .claude/skills/api-design
$ npx degit skateddu/claude-code-python-setup/.claude/skills/claude-api .claude/skills/claude-api
$ npx degit skateddu/claude-code-python-setup/.claude/skills/claude-automation-recommender .claude/skills/claude-automation-recommender
$ npx degit skateddu/claude-code-python-setup/.claude/skills/claude-md-improver .claude/skills/claude-md-improver
$ npx degit skateddu/claude-code-python-setup/.claude/skills/database-migrations .claude/skills/database-migrations
$ npx degit skateddu/claude-code-python-setup/.claude/skills/deployment-patterns .claude/skills/deployment-patterns
$ npx degit skateddu/claude-code-python-setup/.claude/skills/django-patterns .claude/skills/django-patterns
$ npx degit skateddu/claude-code-python-setup/.claude/skills/django-security .claude/skills/django-security
$ npx degit skateddu/claude-code-python-setup/.claude/skills/django-tdd .claude/skills/django-tdd
$ npx degit skateddu/claude-code-python-setup/.claude/skills/django-verification .claude/skills/django-verification
$ npx degit skateddu/claude-code-python-setup/.claude/skills/doc-coauthoring .claude/skills/doc-coauthoring
$ npx degit skateddu/claude-code-python-setup/.claude/skills/docker-patterns .claude/skills/docker-patterns
$ npx degit skateddu/claude-code-python-setup/.claude/skills/docx .claude/skills/docx
$ npx degit skateddu/claude-code-python-setup/.claude/skills/frontend-design .claude/skills/frontend-design
$ npx degit skateddu/claude-code-python-setup/.claude/skills/mcp-builder .claude/skills/mcp-builder
$ npx degit skateddu/claude-code-python-setup/.claude/skills/pdf .claude/skills/pdf
$ npx degit skateddu/claude-code-python-setup/.claude/skills/playground .claude/skills/playground
$ npx degit skateddu/claude-code-python-setup/.claude/skills/postgres-patterns .claude/skills/postgres-patterns
$ npx degit skateddu/claude-code-python-setup/.claude/skills/pptx .claude/skills/pptx
$ npx degit skateddu/claude-code-python-setup/.claude/skills/skill-creator .claude/skills/skill-creator
$ npx degit skateddu/claude-code-python-setup/.claude/skills/webapp-testing .claude/skills/webapp-testing
$ npx degit skateddu/claude-code-python-setup/.claude/skills/xlsx .claude/skills/xlsx

$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/skateddu/claude-code-python-setup/main/.claude/agents/architect.md
$ curl -fsSL --create-dirs -o .claude/agents/code-architect.md https://raw.githubusercontent.com/skateddu/claude-code-python-setup/main/.claude/agents/code-architect.md
$ curl -fsSL --create-dirs -o .claude/agents/code-explorer.md https://raw.githubusercontent.com/skateddu/claude-code-python-setup/main/.claude/agents/code-explorer.md
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/skateddu/claude-code-python-setup/main/.claude/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/comment-analyzer.md https://raw.githubusercontent.com/skateddu/claude-code-python-setup/main/.claude/agents/comment-analyzer.md
$ curl -fsSL --create-dirs -o .claude/agents/database-reviewer.md https://raw.githubusercontent.com/skateddu/claude-code-python-setup/main/.claude/agents/database-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/skateddu/claude-code-python-setup/main/.claude/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/pr-test-analyzer.md https://raw.githubusercontent.com/skateddu/claude-code-python-setup/main/.claude/agents/pr-test-analyzer.md
$ curl -fsSL --create-dirs -o .claude/agents/refactor-cleaner.md https://raw.githubusercontent.com/skateddu/claude-code-python-setup/main/.claude/agents/refactor-cleaner.md
$ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/skateddu/claude-code-python-setup/main/.claude/agents/security-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/silent-failure-hunter.md https://raw.githubusercontent.com/skateddu/claude-code-python-setup/main/.claude/agents/silent-failure-hunter.md
$ curl -fsSL --create-dirs -o .claude/agents/tdd-guide.md https://raw.githubusercontent.com/skateddu/claude-code-python-setup/main/.claude/agents/tdd-guide.md
$ curl -fsSL --create-dirs -o .claude/agents/type-design-analyzer.md https://raw.githubusercontent.com/skateddu/claude-code-python-setup/main/.claude/agents/type-design-analyzer.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)",
      "Read(./.env.local)",
      "Read(./.env.development)",
      "Read(./.env.staging)",
      "Read(./.env.production)",
      "Read(./.env.test)",
      "Read(./.envrc)",
      "Read(./secrets/**)",
      "Read(./**/credentials*)",
      "Read(./**/secret*)",
      "Read(./**/*.pem)",
      "Read(./**/*.key)",
      "Read(./**/*.p12)",
      "Read(./**/*.pfx)",
      "Read(./**/*.jks)",
      "Read(./**/*token*)",
      "Read(~/.ssh/**)",
      "Read(./**/*id_rsa*)",
      "Read(./**/*id_ed25519*)",
      "Read(./**/*id_ecdsa*)",
      "Read(./**/*id_dsa*)"
    ]
  },
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "bash .claude/hooks/enforce-uv.sh"
          },
          {
            "type": "command",
            "command": "bash .claude/hooks/enforce-uv.sh"
          },
          {
            "type": "command",
            "command": "bash .claude/hooks/enforce-uv.sh"
          },
          {
            "type": "command",
            "command": "bash .claude/hooks/enforce-uv.sh"
          },
          {
            "type": "command",
            "command": "bash .claude/hooks/enforce-uv.sh"
          },
          {
            "type": "command",
            "command": "bash .claude/hooks/enforce-uv.sh"
          },
          {
            "type": "command",
            "command": "bash .claude/hooks/enforce-uv.sh"
          },
          {
            "type": "command",
            "command": "bash .claude/hooks/enforce-uv.sh"
          },
          {
            "type": "command",
            "command": "bash .claude/hooks/protect-main.sh"
          },
          {
            "type": "command",
            "command": "bash .claude/hooks/protect-main.sh"
          }
        ]
      }
    ]
  }
}

Skills (22)

Subagents (13)

architect model: opus	Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when a decision changes the system's structure — new services or data stores, integratio
code-architect model: sonnet	Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, d
code-explorer model: sonnet	Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development
code-reviewer model: sonnet	Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use after writing or modifying non-trivial code, before it is committed.
comment-analyzer model: inherit	Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes (1) after generating large documentation comments or docstrings, (2) befo
database-reviewer model: sonnet	PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database p
planner model: opus	Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation or complex refactoring that needs a step-by-step implementation plan. For dec
pr-test-analyzer model: inherit	Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new fun
refactor-cleaner model: sonnet	Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (vulture, ruff, autoflake) to identify dead code and safely r
security-reviewer model: sonnet	Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injectio
silent-failure-hunter model: inherit	Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. This agent should be invoked proactively after
tdd-guide model: sonnet	Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.
type-design-analyzer model: inherit	Use this agent when you need expert analysis of type design in your codebase. Specifically use it (1) when introducing a new type to ensure it follows best practices for encapsulation and invariant ex

Hooks (14)

event	matcher	runs
SessionStart	*	bash .claude/hooks/session-start.sh
UserPromptSubmit	*	bash .claude/hooks/guard-secrets.sh
PreToolUse	Bash	bash .claude/hooks/enforce-uv.sh
PreToolUse	Bash	bash .claude/hooks/enforce-uv.sh
PreToolUse	Bash	bash .claude/hooks/enforce-uv.sh
PreToolUse	Bash	bash .claude/hooks/enforce-uv.sh
PreToolUse	Bash	bash .claude/hooks/enforce-uv.sh
PreToolUse	Bash	bash .claude/hooks/enforce-uv.sh
PreToolUse	Bash	bash .claude/hooks/enforce-uv.sh
PreToolUse	Bash	bash .claude/hooks/enforce-uv.sh
PreToolUse	Bash	bash .claude/hooks/protect-main.sh
PreToolUse	Bash	bash .claude/hooks/protect-main.sh
PostToolUse	Edit\|Write	bash .claude/hooks/auto-lint.sh
Stop	*	bash .claude/hooks/verify.sh

Slash commands (10)

/build-fix/clean-gone/commit-push-pr/commit/feature-dev/notebook-review/orchestrate/review-pr/revise-claude-md/test-coverage

Permissions

deny (21)

Read(./.env)

Read(./.env.local)

Read(./.env.development)

Read(./.env.staging)

Read(./.env.production)

Read(./.env.test)

Read(./.envrc)

Read(./secrets/**)

Read(./**/credentials*)

Read(./**/secret*)

Read(./**/*.pem)

Read(./**/*.key)

Read(./**/*.p12)

Read(./**/*.pfx)

Read(./**/*.jks)

Read(./**/*token*)

Read(~/.ssh/**)

Read(./**/*id_rsa*)

Read(./**/*id_ed25519*)

Read(./**/*id_ecdsa*)

Read(./**/*id_dsa*)

ask (0)

—

allow (6)

Bash(uv sync *)

Bash(uv run pytest *)

Bash(uv run ruff *)

Bash(uv add *)

Bash(uv remove *)

Bash(uv run python *)

Context tax

Instructions: 5.5kMCP tool schemas (est.): 0Skill metadata: 1.4kSubagent metadata: 962

ALWAYS-LOADED FILES (claude-code)

≡

CLAUDE.md · 105 lines · ~994 tok · 10 @import (+4.5k)

Estimate: characters ÷ 4 for instruction files and skill/subagent descriptions; MCP schema sizes from typical tool counts. Harnesses with deferred tool loading pay less. Method

Guardrails 4/5

✓

Blocks destructive commands

PreToolUse hook screens Bash: bash .claude/hooks/enforce-uv.sh

✓

Protects secrets

Denies reads like Read(./.env)

✓

Pre-tool screening hook

10 PreToolUse hook(s)

✓

No YOLO mode

Permission prompts stay on

✗

Sandbox or ask-first rules

No sandbox and no ask-first rules

Badge

Add to your README:

[![AgentRigs](https://agentrigs.dev/badge/rig/skateddu/claude-code-python-setup.svg)](https://agentrigs.dev/r/skateddu/claude-code-python-setup)

Indexed from commit cb69b3288bcd on 2026-10-09. Data is structure only — env values and anything secret-looking are stripped.

Similar rigs

anthropics/skills

Public repository for Agent Skills

★ 180k collection Claude Code 19 skills 4d ago

Skill Collector 1.3k tok ·

LeastBit/Claude_skills_zh-CN

Anthropics/skills中文学习版本来自：https://github.com/anthropics/skills

★ 589 project Claude Code 16 skills 9mo ago

Skill Collector 608 tok ·

TsinHzl/claude-code-config

—

★ 1 setup Claude CodeCodexGemini CLI 2 mcp 121 skills 14 agents 17 hooks 5d ago

YOLO Cowboy 9.8k tok ·

Cyvid7-Darus10/claude-code-config

My Claude Code configuration: 29 agents, 60 commands, 60 skills, 65 rules. Built on everything-claude-code + obra/superpowers.

★ 2 setup Claude CodeCodex 2 mcp 18 skills 12 agents 2 hooks 3mo ago

Fort Knox 10.7k tok ·