Yesterday-AI/ytstack
An opinionated OS for AI coding agents. Plan like a PM, execute like a senior eng. -- Claude Code plugin
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit Yesterday-AI/ytstack/.claude ./rig-ytstack # 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 Yesterday-AI/ytstack/.claude/skills/check-consistency .claude/skills/check-consistency $ npx degit Yesterday-AI/ytstack/skills/atomic-design .claude/skills/atomic-design $ npx degit Yesterday-AI/ytstack/skills/deutschland-stack-api .claude/skills/deutschland-stack-api $ npx degit Yesterday-AI/ytstack/skills/european-alternatives-api .claude/skills/european-alternatives-api $ npx degit Yesterday-AI/ytstack/skills/handoff-session .claude/skills/handoff-session $ npx degit Yesterday-AI/ytstack/skills/init-project .claude/skills/init-project $ npx degit Yesterday-AI/ytstack/skills/office-hours .claude/skills/office-hours $ npx degit Yesterday-AI/ytstack/skills/oss-project .claude/skills/oss-project $ npx degit Yesterday-AI/ytstack/skills/plan-ceo-review .claude/skills/plan-ceo-review $ npx degit Yesterday-AI/ytstack/skills/plan-eng-review .claude/skills/plan-eng-review $ npx degit Yesterday-AI/ytstack/skills/plan-milestone .claude/skills/plan-milestone $ npx degit Yesterday-AI/ytstack/skills/plan-task .claude/skills/plan-task $ npx degit Yesterday-AI/ytstack/skills/reassess-roadmap .claude/skills/reassess-roadmap $ npx degit Yesterday-AI/ytstack/skills/resume-session .claude/skills/resume-session $ npx degit Yesterday-AI/ytstack/skills/slice-milestone .claude/skills/slice-milestone $ npx degit Yesterday-AI/ytstack/skills/software-craftsmanship .claude/skills/software-craftsmanship $ npx degit Yesterday-AI/ytstack/skills/spawn-milestone-team .claude/skills/spawn-milestone-team $ npx degit Yesterday-AI/ytstack/skills/summarize-task .claude/skills/summarize-task $ npx degit Yesterday-AI/ytstack/skills/systematic-debugging .claude/skills/systematic-debugging $ npx degit Yesterday-AI/ytstack/skills/test-driven-development .claude/skills/test-driven-development $ npx degit Yesterday-AI/ytstack/skills/using-ytstack .claude/skills/using-ytstack $ npx degit Yesterday-AI/ytstack/skills/verification-before-completion .claude/skills/verification-before-completion
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/Yesterday-AI/ytstack/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/Yesterday-AI/ytstack/main/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/Yesterday-AI/ytstack/main/agents/verifier.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 (22)
check-consistencyatomic-designdeutschland-stack-apieuropean-alternatives-apihandoff-sessioninit-projectoffice-hoursoss-projectplan-ceo-reviewplan-eng-reviewplan-milestoneplan-taskreassess-roadmapresume-sessionslice-milestonesoftware-craftsmanshipspawn-milestone-teamsummarize-tasksystematic-debuggingtest-driven-developmentusing-ytstackverification-before-completion
Subagents (3)
| architect model: inherit | | |
| implementer model: inherit | | |
| verifier model: inherit | | |
Similar rigs
taiyyoson/my-claude-code
Version-controlled Claude Code setup with three working modes
Pragmatist 1.1k tok ·
nicolasaudran/claude-dotfiles
—
Pragmatist 320 tok ·
raiki61/claude-plugins
Two Claude Code loops that keep reviewing and researching until they reach a fixed point: the implementer and the grader are held in separate contexts, and the machine may only ever declare failure, never convergence. Japanese only for now.
Orchestrator 1.2k tok ·
RichardBray/dotfiles
My personal configuration files and settings
Skill Collector 671 tok ·