claudecodex

ytstack

BUNDLE: Yesterday Technologies Stack -- opinionated software-development OS for AI agents. Curated superpowers + gstack skills plus Project-OS artifact discipline (PROJECT.md, DECISIONS.md, KNOWLEDGE.md, milestone/slice/task hierarchy), orchestrated via SessionStart hooks.

2 on GitHubby Yesterdayv0.1.6MITupdated 1 month ago
/

Plugin ytstack from marketplace yesterday-public-plugins in Yesterday-AI/skills. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (22)

  • check-consistency

    Audit ytstack internal consistency. Compares README (source of truth) against docs/concept.md, .ytstack/DECISIONS.md, and actual plugin content (skills/, hooks/, agents/, artifacts). Reports drift: missing or extra skills, workflow mentions that do not resolve to real skills, trigger-map gaps, hook-

  • atomic-design

    Atomic Design methodology for structuring React/Next.js component libraries. Defines five levels (atoms, molecules, organisms, templates, pages) with hard import rules, classification tests, and anti-patterns. Use when creating, reviewing, or restructuring frontend components. - Read - Glob - Grep

  • deutschland-stack-api

    Use when picking technologies for German public-sector projects (Bund/Länder/Kommunen), EU digital sovereignty contexts, or when user mentions Deutschland-Stack / DS-konform / Verwaltungs-IT. Biases tech choices toward the 128 graduated open-source standards catalogued by the German government. Fetc

  • european-alternatives-api

    Use when picking software for EU customers, GDPR-driven replacements, digital-sovereignty contexts, or when user asks for the European / open-source version of a US product (Google Drive, Dropbox, Slack, …). Biases tech choices toward the 289 community-curated alternatives at european-alternatives.c

  • handoff-session

    User-triggered session handoff. Writes a detailed HANDOFF.md with current state, open items, pending decisions, and recommended resume prompt. Use before switching machines, before long breaks, or when you need to clear context intentionally. Parallel to the automatic pre-compact hook.

  • init-project

    Scaffold a ytstack project's `.ytstack/` directory with the 6 core artifacts (PROJECT.md, DECISIONS.md, KNOWLEDGE.md, RUNTIME.md, STATE.md, PREFERENCES.md). Use AFTER a pitch has been validated via office-hours (and optionally plan-ceo-review / plan-eng-review in concept-mode) -- init-project reads

  • office-hours

    Use as the first step when a new project, feature, or initiative has not yet been validated, or whenever the premise needs a forcing-question test. Six forcing questions expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Produces OFFICE-HOURS.md p

  • oss-project

    Scaffold, polish, and publish open-source projects with AI-first documentation, governance, and CI. Use when: Starting a new OSS package, polishing/publishing an existing repo, setting up AGENTS.md / CONTEXT.md / DECISIONS.md / ROADMAP.md, onboarding AI agents to a codebase, or creating standard com

  • plan-ceo-review

    Challenge premise, scope, and ambition via four modes: SCOPE EXPANSION, SELECTIVE EXPANSION, HOLD SCOPE, SCOPE REDUCTION. Auto-detects mode: concept-mode reviews a pitch (OFFICE-HOURS.md) before any scaffolding exists; milestone-mode reviews a committed milestone (M###-CONTEXT.md + M###-ROADMAP.md)

  • plan-eng-review

    Review execution approach for feasibility, architecture, data flow, edge cases, test coverage, performance, and security risks. Auto-detects mode: concept-mode reviews a pitch (OFFICE-HOURS.md) for technical feasibility before any scaffolding; milestone-mode reviews slice-plans (M###-S##-PLAN.md) be

  • plan-milestone

    Plan the next milestone: goal, exit criteria, rough size. Creates M###-CONTEXT.md and M###-ROADMAP.md. Run after init-project has scaffolded `.ytstack/`, before slice-milestone. Draws the goal from a validated pitch when available (OFFICE-HOURS.md or prior milestones); if no pitch exists yet in gree

  • plan-task

    Flesh out a single task within the current slice. Reads M###-S##-PLAN.md, picks the next unplanned task, writes M###-S##-T##-PLAN.md with exact file paths + verification steps. Enforces fits-one-context-window rule. Run after slice-milestone, before executing the task.

  • reassess-roadmap

    After a slice completes, review whether the milestone roadmap still fits reality. Reads recent summaries, surfaces deviations, prompts for roadmap changes (add/split/reorder/remove slices). Run at slice boundaries, not mid-slice.

  • resume-session

    Reconstruct working context at the start of a new session. Reads STATE.md + HANDOFF.md (if present) + latest 3 T##-SUMMARY.md files and synthesizes a 'where we are' briefing. Run at session start before doing anything else.

  • slice-milestone

    Break the current milestone into slices. Reads M###-ROADMAP.md, asks for slice content until all slices are filled. Creates M###-S##-PLAN.md per slice. Enforces 1-7 tasks per slice (iron rule). Run after plan-milestone, before plan-task.

  • software-craftsmanship

    Clean code, robust architecture, no test slop. Foundational skill for high-quality software engineering, code structure, and reviews.

  • spawn-milestone-team

    Dispatch the current milestone's slices to a Claude Code Agent Team. Each teammate works on a slice in parallel with its own 200k context (replaces GSD's fresh-subprocess-per-task pattern). Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 and v2.1.32+. Run after slice-milestone + plan-eng-review.

  • summarize-task

    After executing a task, write its outcome summary. Reads M###-S##-T##-PLAN.md, prompts for what happened, writes M###-S##-T##-SUMMARY.md, flips checkbox in slice-plan, updates STATE.md. Optionally stages git. Run once per task completion.

  • systematic-debugging

    Root-cause debugging in four phases: investigate, analyze, hypothesize, implement. Iron Law -- no fixes without root cause. Thin ytstack wrapper around the vendored superpowers systematic-debugging procedure, routing findings into KNOWLEDGE.md / DECISIONS.md. Use when hitting a bug, test failure, or

  • test-driven-development

    RED-GREEN-REFACTOR: write a failing test, watch it fail, write minimal code, watch it pass, commit. Thin ytstack wrapper around the vendored superpowers test-driven-development procedure, injecting the current task's plan as context. Use during task execution.

  • using-ytstack

    Establishes how agents find and invoke ytstack skills. Requires Skill-tool invocation before any response when a ytstack skill applies. Auto-injected by the SessionStart hook. Not meant for direct user invocation.

  • verification-before-completion

    Run verification commands and confirm output before claiming work is complete. Evidence before assertions. Thin ytstack wrapper around the vendored superpowers verification-before-completion procedure, injecting the current task's verification command. Use before commit, before PR, before summarize-

Subagents (3)

  • architect

    Plan-before-implement reviewer. Use when a ytstack milestone has been sliced and needs architectural sign-off before tasks start executing. Also useful during plan-ceo-review / plan-eng-review delegation -- the architect agent reviews the proposed plan against the project's existing code, DECISIONS.

  • implementer

    Execute one slice of a ytstack milestone. Use when a slice-plan is approved and the lead dispatches you with a specific `M###-S##-PLAN.md` to work through. You own one slice at a time. You claim each task from the shared task list, execute via `ytstack:plan-task` → `test-driven-development` → `verif

  • verifier

    Evidence-before-assertions gatekeeper. Use when an implementer claims a task or slice is done, before the lead accepts closure. The verifier runs the plan's verification commands from a cold context, captures output, decides pass / pass-with-caveats / fail. Blocks premature "done" claims. Examples:

Hooks (8)

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-start"

  • PreCompact

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/pre-compact"

  • SessionEnd

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-end"

  • TeammateIdle

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/teammate-idle"

  • TaskCreated

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/task-created"

  • TaskCompleted

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/task-completed"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/pre-tool-use-edit"

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/post-tool-use-bash"

View source on GitHub

More from Yesterday-AI/skills

All 22 plugins →

BUNDLE: Yesterday Agent Stack -- generic skills for AI agents in human-AI collaboration and AI-as-expert workflows (Levels of AGI 3-4). Stateful patrols, agent-to-agent orchestration, self-improvement, durable infra ops. No Yesterday-infra dependencies; works for any team running long-running Claude Code agents.

14 skills

2

office

claude

BUNDLE: Daily-work core tier. Generic productivity, creative, and knowledge skills for daily work; nothing requires external SaaS keys at install time. Optional SaaS integrations (Figma, Miro, Voxtral TTS, VRR transit) live in office-extras.

5 skills

2

BUNDLE: SysOps -- generic infrastructure-provisioning, deployment, and observability skills for agents. opentofu + railway-deploy + butler-deploy + land-and-deploy + canary + setup-deploy.

3 skills

2

Durchsucht lokale Codex- und Claude-Code-Transkripte nach früherer Arbeit zu einem benannten Thema. Nutze ihn, wenn die nutzende Person wissen möchte, was er dazu schon gemacht hat, oder eine frühere Session fortsetzen möchte.

1 skill

2

Verpackt einen bestehenden Agent-Skill als Microsoft-365-App-Paket für Copilot Cowork — Manifest, Icons, Konvertierung abgelehnter Dateiformate und Vorab-Validierung per CLI. Für den Weg vom lokalen SKILL.md-Ordner in den M365-Tenant; schreibt selbst keine Skills und betrifft nicht Anthropics Claude Cowork.

1 skill

2

Turn an existing skill or a fresh idea into a catalog-ready shareable skill -- run the quality gate, decide catalog and standalone-vs-bundle placement, pick the category, scaffold SKILL.md (+ optional .plugin.json), update the catalog docs, and open a PR. Use when adding a new skill to the catalog or promoting a personal skill into a shareable one.

1 skill

2

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Maintain ytstack?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins22 plugins