homayoun-asghari/claude-agentic-workflow-starter-kit
A minimal Claude Code template — the workflow, CLAUDE.md, hooks, skills and review subagent I actually use. Two commands. One reviewer subagent. Zero dependencies.
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
Copy this rig
# review before running: this installs third-party code
$ npx degit homayoun-asghari/claude-agentic-workflow-starter-kit/template/.claude ./rig-claude-agentic-workflow-starter-kit # 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 homayoun-asghari/claude-agentic-workflow-starter-kit/template/.claude/skills/kickoff .claude/skills/kickoff $ npx degit homayoun-asghari/claude-agentic-workflow-starter-kit/template/.claude/skills/ship-it .claude/skills/ship-it
$ curl -fsSL --create-dirs -o .claude/agents/spec-auditor.md https://raw.githubusercontent.com/homayoun-asghari/claude-agentic-workflow-starter-kit/main/template/.claude/agents/spec-auditor.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 (2)
Subagents (1)
| spec-auditor model: sonnet | Audits a finished change against its written acceptance criteria in a fresh context. Use at the end of every feature, before opening a PR. Never let the agent that wrote the code be the only one to ju |
Similar rigs
DD-Gits/CoreVault
An Obsidian vault scaffold for AI-assisted development. Persistent project context, durable AI memory, and a kickoff/wrap-up session protocol that works across Claude Code, Codex, Cursor, and other AGENTS.md-aware agents.
Pragmatist 4.1k tok ·
globalprojectscorp/kylecorp-team
Claude Code organization: skills, design system, and config
Skill Collector 3.2k tok ·
Chillin-spree/claude-code-system-template
A lean, skills-first Claude Code template for building web apps — vanilla by default, stack-swappable, with workflow skills, agents, and a commit/push safety gate.
Fort Knox 1.5k tok ·
kotaraa09/easyClaude
A stack-agnostic harness that makes Claude Code work well on any project: persistent state, an adaptive verify gate, guardrails, and a token-frugal escape hatch.
Skill Collector 1.1k tok ·