John99101/claude-code-project-template
Self-configuring Claude Code setup: install into a project or onto your machine, and Claude detects your stack, asks about your preferences, and writes CLAUDE.md, rules, commands, skills, agents, hooks and MCP config.
field: Developer tools workflow: Testing & TDDCI/CD & deployPR / code reviewGit & commitsSecurity review runs claude in CI
stack: Python
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 John99101/claude-code-project-template/agents ./rig-claude-code-project-template/agents $ npx degit John99101/claude-code-project-template/skills ./rig-claude-code-project-template/skills $ npx degit John99101/claude-code-project-template/hooks ./rig-claude-code-project-template/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 John99101/claude-code-project-template/skills/check .claude/skills/check $ npx degit John99101/claude-code-project-template/skills/commit .claude/skills/commit $ npx degit John99101/claude-code-project-template/skills/debug-issue .claude/skills/debug-issue $ npx degit John99101/claude-code-project-template/skills/release-notes .claude/skills/release-notes $ npx degit John99101/claude-code-project-template/skills/remember-preference .claude/skills/remember-preference $ npx degit John99101/claude-code-project-template/skills/review-changes .claude/skills/review-changes $ npx degit John99101/claude-code-project-template/skills/setup .claude/skills/setup $ npx degit John99101/claude-code-project-template/skills/template-update .claude/skills/template-update $ npx degit John99101/claude-code-project-template/skills/write-tests .claude/skills/write-tests
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/John99101/claude-code-project-template/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/John99101/claude-code-project-template/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-auditor.md https://raw.githubusercontent.com/John99101/claude-code-project-template/main/agents/security-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/John99101/claude-code-project-template/main/agents/test-writer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (9)
Subagents (4)
| planner model: opus | Read-only planner for larger features or refactors. Explores the codebase and returns a step-by-step implementation plan with files to change, risks and open questions. Use before multi-file changes. |
| reviewer model: inherit | Reviews recent code changes for bugs, edge cases, readability and convention violations. Use after making changes and before committing. |
| security-auditor model: inherit | Read-only security review of code changes or a module. Use when changes touch authentication, authorisation, user input, file or shell access, SQL, secrets, crypto or dependencies. |
| test-writer model: sonnet | Writes and fixes tests in the project's framework and style. Use for adding test coverage to a module, writing regression tests for a bug, or fixing a broken test suite. |
Similar rigs
kevingo710/dota2App
React Native app built and verified by a team of AI agents: deterministic gate, evals, hybrid Claude/local routing, live Neo4j agent graph
Fort Knox 3.9k tok · · Q60
Yassinekrn/claude-setup
Personal Claude Code setup — orchestrator/subagent delegation policy, custom agents, and a colored PowerShell statusline (git branch, model+effort, tokens, cost, rate limits).
Orchestrator 1.2k tok · · Q15
Windy3f3f3f3f/claude-code-from-scratch
Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码,读不动?用 ~5000 行 TypeScript / Python 从零复现核心架构,11 章分步教程带你理解 coding agent 精髓
Pragmatist 2.6k tok · · Q0
OlegTestov/prove-it-mini
A pytest Stop hook for Claude Code: two repair attempts, then an explicit unverified result. No model calls, MIT.
Minimalist 332 tok · · Q3