saichandra1199/kickstart-with-claude-code
Smart Task Manager CLI demo showing all major Claude Code features: CLAUDE.md, Skills, Agents, Hooks, MCP, Settings, and Memory
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ claude mcp add sqlite -- uvx mcp-server-sqlite --db-path ./tasks.db $ npx degit saichandra1199/kickstart-with-claude-code/.claude ./rig-kickstart-with-claude-code # 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.
$ claude mcp add sqlite -- uvx mcp-server-sqlite --db-path ./tasks.db $ npx degit saichandra1199/kickstart-with-claude-code/.claude/skills/add-task .claude/skills/add-task $ npx degit saichandra1199/kickstart-with-claude-code/.claude/skills/run-tests .claude/skills/run-tests $ npx degit saichandra1199/kickstart-with-claude-code/.claude/skills/show-stats .claude/skills/show-stats
$ curl -fsSL --create-dirs -o .claude/agents/task-analyzer.md https://raw.githubusercontent.com/saichandra1199/kickstart-with-claude-code/master/.claude/agents/task-analyzer.md This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"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(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| mcp-server-sqlite · "sqlite" | pypi | 2.5k |
Skills (3)
Subagents (1)
| task-analyzer model: inherit | Analyzes task patterns in tasks.db. Use when the user asks to analyze tasks, show task patterns, compute completion rates, identify stale tasks, or break down tasks by priority. Returns a structured m |
Similar rigs
JSchOBL/agentic-ai-learning-journey
A hands-on lab for learning to write CLAUDE.md files and Claude Code setups — you write the context, the agent builds the code, a coach reviews your work.
Minimalist 1.3k tok ·
cbolden15/claude-code-config-manager
A powerful configuration management tool for Claude Code and Auto-Claude projects. CCM serves as the single source of truth for agent personas, MCP servers, model profiles, and project settings across multiple machines.
Pragmatist 15.8k tok ·
trupo-zz/claude-code-setup-sample
Sample Claude Code config pack for a fictional app: CLAUDE.md, permissions, a guard hook with tests, 3 skills. AI-assisted. MIT.
Fort Knox 19.0k tok ·
veronicani/claude-code-config
Claude Code setup for my workflow
Skill Collector 2.4k tok ·