Akku/agentic-coding-starter-kit
Minimal, growing starter kit for agent-driven development with Git and Backlog.md (Claude Code, Codex, Copilot)
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 Akku/agentic-coding-starter-kit/.claude ./rig-agentic-coding-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 Akku/agentic-coding-starter-kit/.claude/skills/handoff .claude/skills/handoff $ npx degit Akku/agentic-coding-starter-kit/.claude/skills/project-setup .claude/skills/project-setup $ npx degit Akku/agentic-coding-starter-kit/.claude/skills/promote-learning .claude/skills/promote-learning $ npx degit Akku/agentic-coding-starter-kit/.claude/skills/retro .claude/skills/retro $ npx degit Akku/agentic-coding-starter-kit/.claude/skills/testing-practices .claude/skills/testing-practices
$ curl -fsSL --create-dirs -o .claude/agents/ux-designer.md https://raw.githubusercontent.com/Akku/agentic-coding-starter-kit/main/.claude/agents/ux-designer.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 (5)
Subagents (1)
| ux-designer model: inherit | UX/UI designer for projects with a user interface. Creates mockups (desktop and mobile), reviews screens and flows, proposes design improvements with reasons and delivers implementable specs (states, |
Similar rigs
Akku/stem
STEM: An Agile Agentic Coding Harness. Guided setup with goals and vision, (token-effective) spec driven development, and retros. Works best with 1 Human and Claude Code.
Fort Knox 2.3k tok · · Q28
Suksan01/agent-hq
Agent HQ: a live command center for Claude Code agent teams
Pragmatist 506 tok · · Q0
nodelike/sikemux
The IDE for you and your coding agents. Run Claude Code, Codex and other agents next to your code, terminals, Git and a real browser, in one native app for Mac and Linux. Built in Rust with GPUI.
Pragmatist 3.4k tok · · Q23
netresearch/retro-skill
LLM-driven session retrospection skill: detects friction in agent sessions and materializes learnings into correct destinations (user-memory, project-rules, skill PRs, checkpoints, harness artefacts)
Minimalist 1.5k tok · · Q0