hyperstack
01Plugin Claude Code
Hyperstack: MCP server + adversarial skill system with SessionStart bootstrap injection.
Plugin Claude Code
Hyperstack: MCP server + adversarial skill system with SessionStart bootstrap injection.
Plugin Claude Code
Disciplined MCP server + skill system. 12 plugins and 80 tools covering designer (6 personalities, 13 page templates, 9 presets), shadcn/ui, design tokens, ui/ux, React Flow v12, Motion v12, Lenis, React 19, Echo, Go, and Rust. 22 skills with adversarial enforcement: Iron Laws, 1% Rule, rationalization tables, and…
Instructions file CodexOpenCode
AGENTS.md instructions for orkait/hyperstack, covering final steering doc, 1. core law, 2. role, 3. source priority and 4. local steering files.
Instructions file Gemini CLI
Gemini CLI instructions for orkait/hyperstack: Disciplined MCP server + skill system with adversarial enforcement. Core focus: React Flow v12, Motion v12, Lenis, React 19, Echo, Go, Rust, and the Designer pipeline.
Skill Claude CodeCodex
Senior Staff Engineer Persona + Unified MCP Server. Provides deep architectural discipline and deterministic knowledge across React Flow, Motion, Echo, Go, Rust, and UI/UX design systems.
Hook
Runs when a session starts on startup, clear and compact, executing session-start.mjs via node. From orkait/hyperstack.
Skill Claude CodeCodex
Use when the user chooses fully autonomous execution. Aggressively uses the entire Hyperstack to implement the solution end-to-end without asking for human review.
Skill Claude CodeCodex
Systematic UI/UX behaviour analysis for interactive applications. Audits every user action, state transition, view mode, and edge case like an experienced QA + UX engineer. Produces a complete interaction matrix with expected vs actual behaviour, finds inconsistencies, dead states, and missing feedback. Use when…
Skill Claude CodeCodex
Use before any feature build, component creation, or behaviour modification. MCP-surveyed design with a hard gate before any implementation. Do not skip, do not skim, do not rationalize your way out of it.
Skill Claude CodeCodex
The generalist persona engine - "bro", "bro mode", or any end-to-end task spanning ui-ux, design, coding, marketing, sales. A very capable, pragmatic 28-30 human who decomposes new challenges into sub-problems, solves each with the full skill/MCP/web surface, and combines the learnings. Evidence-backed and blunt about…
Skill Claude CodeCodex
Use when completing tasks, implementing features, or before merging - to dispatch a review subagent and handle feedback with technical rigor.
Skill Claude CodeCodex
Deep context-loading protocol. Use when you must understand an unfamiliar codebase before answering, reviewing, or changing it - "codemode", "load the codebase", "map this repo", "understand before you touch". Maps structure, dependency graph, architecture, fragile components, behaviour, and high-impact improvements…
Skill Claude CodeCodex
Use when encountering any bug, test failure, or unexpected behaviour. Root cause investigation is mandatory before any fix attempt.
Skill Claude CodeCodex
Use after all implementation tasks are complete. Runs final verification, confirms the branch is clean, detects the workspace environment, and executes the chosen delivery method.
Skill Claude CodeCodex
Apply core programming principles and design patterns from Clean Code, The Pragmatic Programmer, Code Complete, Refactoring, and Design Patterns. Use when writing code, reviewing PRs, refactoring, or designing system architecture.
Skill Claude CodeCodex
Evidence-based design decision engine. Intention gate that produces non-slop UI/UX by grounding in the existing codebase first, then forcing every visual choice through industry context, cognitive science, design master principles, and anti-pattern detection before code generation. Outputs DESIGN.md contract all…
Skill Claude CodeCodex
Apply senior-level software engineering discipline including design patterns, SOLID principles, architectural reasoning, systematic verification, and safety gates. Use when writing production code, complex features, reviewing code, refactoring systems, or when engineering rigor and correctness are required. Supports…
Skill Claude CodeCodex
Use after blueprint design approval to produce a task-by-task implementation plan grounded in MCP-verified API calls. No placeholders, no assumed syntax.
Skill Claude CodeCodex
Use when designing or revamping a frontend section or whole page and you want to explore real-React variants in an isolated, dev-only lab before writing production code. Cook variants for one target at a time, lock the winner, watch an additive page assemble in /lab-view, then wire it properly. Forces real-stack…
Skill Claude CodeCodex
Use to do product marketing for any brand - position it, find the message, write the copy ("marketing words"), set brand voice, plan go-to-market and growth. Pulls ground-truth frameworks (Dunford, Schwartz, Cialdini, Byron Sharp, Traction, Reforge...) via the marketing MCP tools and applies them. Trigger when asked…
Skill Claude CodeCodex
Teaches runtime analysis - deriving Big-O straight from code - and how to derive a better algorithm by removing redundant work, then confirms the technique via the optimizer catalog and web-searches the implementation. Suggests the complexity win as Big-O before -> after. Evidence-gated, not premature - stays quiet…
Skill Claude CodeCodex
Use when facing 2+ independent tasks that can be investigated or executed without shared state or sequential dependencies.
Skill Claude CodeCodex
Use BEFORE any net-new feature, product, or scope decision - the product-manager persona gate. Grounds the build in a validated customer problem (opportunity-vs-solution, four risks, prioritized call) and emits PASS/BLOCK/NEEDS-INPUT before design or engineering. Advisory for tweaks; user can override.
Skill Claude CodeCodex
Writes or rewrites project README files using repository evidence instead of generic filler. Use when creating a new README, improving an existing README, or auditing an LLM-written README for inaccuracies, missing setup details, weak quickstarts, unclear audience fit, vague feature claims, or poor presentation…