Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions .claude-plugin/marketplace.json
Original file line number Diff line number Diff line change
Expand Up @@ -9,14 +9,14 @@
},
"metadata": {
"description": "Disciplined MCP server + skill system. Iron Laws, 1% Rule, rationalization tables, SessionStart hook injection.",
"version": "1.4.0"
"version": "1.5.0"
},
"plugins": [
{
"name": "hyperstack",
"source": "./",
"description": "Disciplined MCP server + skill system. 12 plugins and 80 tools covering designer, shadcn/ui, design tokens, ui/ux, React Flow v12, Motion v12, Lenis, React 19, Echo, Go, Rust. 22 skills with adversarial enforcement.",
"version": "1.4.0",
"description": "Disciplined MCP server + skill system. 16 plugins and 121 tools covering designer, shadcn/ui, design tokens, ui/ux, React Flow v12, Motion v12, Lenis, React 19, Echo, Go, Rust, product-manager, marketing, reflect, optimizer. 29 skills with adversarial enforcement.",
"version": "1.5.0",
"category": "productivity",
"strict": true
}
Expand Down
4 changes: 2 additions & 2 deletions .claude-plugin/plugin.json
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
{
"name": "hyperstack",
"displayName": "Hyperstack",
"description": "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 SessionStart hook injection. Forces your agent to use real docs, real DESIGN.md contracts, and real verification before shipping.",
"version": "1.4.0",
"description": "Disciplined MCP server + skill system. 16 plugins and 121 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, Rust, product-manager, marketing, reflect, and optimizer. 29 skills with adversarial enforcement: Iron Laws, 1% Rule, rationalization tables, and SessionStart hook injection. Forces your agent to use real docs, real DESIGN.md contracts, and real verification before shipping.",
"version": "1.5.0",
"author": {
"name": "Orkait",
"email": "orkaitsolutions@gmail.com"
Expand Down
2 changes: 1 addition & 1 deletion .cursor-plugin/plugin.json
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
"name": "hyperstack",
"displayName": "Hyperstack",
"description": "Senior Staff Engineer persona + domain knowledge MCP server for React Flow, Motion, Go, Rust, design tokens, and more",
"version": "1.4.0",
"version": "1.5.0",
"author": {
"name": "Orkait",
"email": "orkaitsolutions@gmail.com"
Expand Down
16 changes: 16 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,22 @@

All notable changes to Hyperstack are documented here. Format follows Keep a Changelog; versioning is SemVer.

## [1.5.0] - 2026-09-04

### Added
- **`react-pro-coder` skill**: 56 React and Next.js rules with stable IDs (`CD-3`, `ST-2`, `DF-5`) across component design, hooks, state placement, performance, data fetching (RSC, React 19 Actions, `use()`), TypeScript, styling and accessibility, architecture, testing, and production security. Gated on `react_get_constraints` so framework ground truth stays in the plugin. Ships a review checklist keyed to rule IDs, a 10-section output contract, and a negative-doubt routine.
- **`python-pro-coder` skill**: 60 FastAPI + Pydantic v2 + SQLAlchemy 2.0 rules (`PD-4`, `AS-2`, `SE-5`) across project structure, modelling, endpoint design, settings, dependency injection, async and performance, security, error handling, database access, testing, and observability. Gated on a version-verified stack file that names the dead dependencies and their replacements: `python-jose` (abandoned, CVE-2024-33664) to PyJWT or joserfc, `passlib` (breaks on Python 3.13+) to pwdlib, `@app.on_event` to `lifespan`, `AsyncClient(app=app)` to `ASGITransport`.
- **`best-practices` reference set**: four new files covering rules no skill held - coupling and abstraction (Law of Demeter, Command-Query Separation, flag arguments, rule of three, leaky abstractions, cargo cult), change hygiene (atomic commits, PR size, automate-before-human, review conduct, tracked debt), architecture at scale (modular monolith default, dependency direction, 12 factors, ADRs), and an operations baseline (structured logs, metrics vs logs, liveness vs readiness, graceful degradation, N+1).

### Changed
- **`engineering-discipline` + `design-patterns-skill` merged into `best-practices`**: the two skills shipped byte-identical copies of the same six pattern reference files (2172 duplicated lines), and `design-patterns-skill` was a strict subset of the other's Quick Reference mode. The merged skill keeps the pattern-selection table and AI-bias guidance that only `design-patterns-skill` carried, and declares `supersedes: ["engineering-discipline", "design-patterns-skill"]`. Callers updated across 20 files.
- **`worktree-isolation`**: `wtg` reference refreshed to the current engine, with an expanded setup guide and multi-repo feature-group notes.
- Manifest counts reconciled against the live server: 16 plugins, 121 tools, 29 skills, 4 personas. README badges, install guide, summary, and CREDITS carried stale figures from several releases back.

### Removed
- `skills/design-patterns-skill/` and `skills/engineering-discipline/` (both absorbed by `best-practices`).
- `references/misc/overview.md`: an orphaned Kiro-era install document that restated `SKILL.md` and described a directory layout that no longer exists.

## [1.4.0] - 2026-07-18

### Added
Expand Down
2 changes: 1 addition & 1 deletion CREDITS.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ Hyperstack's gate skill enforcement pattern - Iron Laws, 1% Rule, rationalizatio

Five Hyperstack workflow skills (`ship-gate`, `debug-discipline`, `run-plan`, `deliver`, `forge-plan`) are structurally derived from their superpowers equivalents. They have since been extended with MCP integration, DESIGN.md pipeline hooks, and Hyperstack-specific domain content.

Everything else - the MCP server, 11 plugins, 79 tools, designer engine, DESIGN.md pipeline, React Flow / Motion / Lenis / Echo / Go / Rust / design tokens domain content, shadcn expert, and SessionStart hook - has no equivalent in superpowers and is original work.
Everything else - the MCP server, 16 plugins, 121 tools, designer engine, DESIGN.md pipeline, React Flow / Motion / Lenis / Echo / Go / Rust / design tokens domain content, shadcn expert, and SessionStart hook - has no equivalent in superpowers and is original work.

---

Expand Down
20 changes: 10 additions & 10 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,8 +12,8 @@
</p>

<p>
<img src="https://img.shields.io/badge/12_plugins-80_tools-6366f1?style=flat-square" alt="Plugins" />
<img src="https://img.shields.io/badge/22_skills-adversarial_gates-a855f7?style=flat-square" alt="Skills" />
<img src="https://img.shields.io/badge/16_plugins-121_tools-6366f1?style=flat-square" alt="Plugins" />
<img src="https://img.shields.io/badge/29_skills-adversarial_gates-a855f7?style=flat-square" alt="Skills" />
<img src="https://img.shields.io/badge/SessionStart-hook_injected-f59e0b?style=flat-square" alt="Hook" />
</p>

Expand All @@ -25,7 +25,7 @@

**Hyperstack is a disciplined engineering harness for AI coding agents.**

It provides the necessary **Ground Truth** (via 80 specialized MCP tools) and **Adversarial Enforcement** (via 22 rigorous skills) to transform a generic LLM into a high-precision Senior Engineer.
It provides the necessary **Ground Truth** (via 121 specialized MCP tools) and **Adversarial Enforcement** (via 29 rigorous skills) to transform a generic LLM into a high-precision Senior Engineer.

Unlike standard "polite" instructions, Hyperstack uses **Iron Laws** and a **SessionStart hook** to force agents to check real documentation, follow precise design specs, and provide binary verification before shipping.

Expand Down Expand Up @@ -85,8 +85,8 @@ If you aren't using the Autopilot, follow the **Unified Bootstrap** to set up bo
It is not just a library; it is a **disciplined harness** made of three tightly-coupled layers:

1. **The Harness**: Bootstraps the agent, routes internal specialist roles (`hyper`, `website-builder`), and enforces global development invariants.
2. **The MCP Ground Truth**: 12 TypeScript plugins (80 tools) that provide deterministic data. No hallucinated imports or invented component specs.
3. **The Adversarial Gates**: 22 skills with **"Enforcement Teeth"**. These aren't suggestions; they are Iron Laws supported by rationalization tables that counter every excuse an agent uses to skip quality gates.
2. **The MCP Ground Truth**: 16 TypeScript plugins (121 tools) that provide deterministic data. No hallucinated imports or invented component specs.
3. **The Adversarial Gates**: 29 skills with **"Enforcement Teeth"**. These aren't suggestions; they are Iron Laws supported by rationalization tables that counter every excuse an agent uses to skip quality gates.

> [!IMPORTANT]
> **Use Hyperstack if** you want to force your agent to check docs, write designs first, and prove its work.
Expand All @@ -100,12 +100,12 @@ graph TD
Harness --> Gates{Adversarial Gates}

subgraph "The Enforcement Layer"
Gates -->|Iron Laws| Skills[21 Skills with Enforcement Teeth]
Gates -->|Iron Laws| Skills[29 Skills with Enforcement Teeth]
Skills -->|SessionStart| Injection[Auto-Context Injection]
end

subgraph "The Knowledge Layer"
Skills -->|Ground Truth| MCP[12 MCP Plugins / 80 Tools]
Skills -->|Ground Truth| MCP[16 MCP Plugins / 121 Tools]
MCP -->|Designer| Design[DESIGN.md Pipeline]
MCP -->|Verified| Code[Programmatic Compliance Check]
end
Expand Down Expand Up @@ -221,7 +221,7 @@ Your AI calls these for deterministic data. Memory is not acceptable. Every plug
| 📈 **Product & Growth** | `optimizer`, `product-manager`, `marketing`, `reflect` | DSA technique matching, Product risk gates (JTBD, RICE), Positioning & GTM, Target-customer screen/feature review |

> [!TIP]
> **118 tools across 16 plugins**. Every tool is designed to provide the "Senior Engineer" answer, bypassing the "AI Slop" default.
> **121 tools across 16 plugins**. Every tool is designed to provide the "Senior Engineer" answer, bypassing the "AI Slop" default.

### Layer 2: Skills (Enforcement Teeth)

Expand Down Expand Up @@ -303,7 +303,7 @@ Domain-expert lenses `hyper` auto-engages when their triggers match the request

</details>

Full index at `skills/INDEX.md`. Regenerate with `bash scripts/generate-skills-index.sh` after adding or editing any skill.
Full index at `skills/INDEX.md`. Regenerate with `bun scripts/generate-skills-index.ts` after adding or editing any skill.

---

Expand Down Expand Up @@ -503,7 +503,7 @@ We welcome contributions that follow the **Disciplined Engineering** standard.

```bash
# Regenerate the skills index after editing
bash scripts/generate-skills-index.sh
bun scripts/generate-skills-index.ts
```

## 📄 License
Expand Down
2 changes: 1 addition & 1 deletion docs/benchmarks-spec.md
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ This is the exact thing the quarterly audit proved by hand (Next 15->16 async pa
| Goals | Non-goals (v1) |
|---|---|
| One claim, deterministic metric, multi-model | Measuring "code quality" broadly (fuzzy, needs a judge) |
| Reproducible single command, raw results stamped | Benchmarking all 12 plugins (start with high-drift ones) |
| Reproducible single command, raw results stamped | Benchmarking all 16 plugins (start with high-drift ones) |
| A README number that replaces faith | A judge-model rubric (avoid fuzzy scoring in v1) |
| Re-runnable each quarter alongside the audit | Proving the agent *will* call the tools (that is v2) |

Expand Down
4 changes: 2 additions & 2 deletions gemini-extension.json
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
{
"name": "hyperstack",
"description": "Disciplined MCP server + skill system. 12 plugins, 80 tools, 22 skills with adversarial enforcement. Designer/DESIGN.md pipeline, shadcn/ui, React Flow, Motion, Lenis, React 19, Echo, Go, Rust, design tokens, UI/UX.",
"version": "1.4.0",
"description": "Disciplined MCP server + skill system. 16 plugins, 121 tools, 29 skills with adversarial enforcement. Designer/DESIGN.md pipeline, shadcn/ui, React Flow, Motion, Lenis, React 19, Echo, Go, Rust, design tokens, UI/UX.",
"version": "1.5.0",
"contextFileName": "GEMINI.md"
}
6 changes: 3 additions & 3 deletions install.md
Original file line number Diff line number Diff line change
Expand Up @@ -18,8 +18,8 @@ If you only remember four things, remember these:
Three tightly-coupled pieces, installed together:

1. **An internal harness** - bootstrap, internal role routing, and workflow control. Current internal roles include `main` and `website-builder`.
2. **An MCP server** with 12 plugins and 80 tools - deterministic knowledge for React Flow v12, Motion v12, Lenis, React 19 / Next.js, Echo, Go, Rust, design tokens, UI/UX principles, shadcn/ui (Base UI edition), and the `designer` DESIGN.md pipeline.
3. **A skill system** with 21 skills including adversarial enforcement gates (`blueprint`, `designer`, `forge-plan`, `ship-gate`, `best-practices`) and a SessionStart hook that face-injects the `hyperstack` skill at every session start.
2. **An MCP server** with 16 plugins and 121 tools - deterministic knowledge for React Flow v12, Motion v12, Lenis, React 19 / Next.js, Echo, Go, Rust, design tokens, UI/UX principles, shadcn/ui (Base UI edition), product management, marketing, algorithmic optimization, and the `designer` DESIGN.md pipeline.
3. **A skill system** with 29 skills including adversarial enforcement gates (`blueprint`, `designer`, `forge-plan`, `ship-gate`, `best-practices`) and a SessionStart hook that face-injects the `hyperstack` skill at every session start.

The install steps below wire the public pieces the user actually needs: the MCP
server and the skills. The internal harness is shipped inside the repository and
Expand Down Expand Up @@ -343,7 +343,7 @@ Once all verifications pass, your final action is to explain the new reality to

> "System Synchronized. Hyperstack is now active.
>
> I have installed the **Disciplined Engineering Harness** with 12 plugins and 80 tools. I have also established your **Iron Laws** (~/.hyperstack/skills).
> I have installed the **Disciplined Engineering Harness** with 16 plugins and 121 tools. I have also established your **Iron Laws** (~/.hyperstack/skills).
>
> From now on:
> - I will not refactor code without a failing test.
Expand Down
4 changes: 2 additions & 2 deletions package-lock.json

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

4 changes: 2 additions & 2 deletions package.json
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"name": "@orkait-ai/hyperstack",
"version": "1.4.0",
"description": "Disciplined MCP server + skill system. 16 plugins, 117 tools, 27 skills, 3 personas with adversarial enforcement. Personas (product-manager gate; marketing + reflect capabilities), Designer/DESIGN.md pipeline, shadcn/ui, React Flow, Motion, Lenis, React 19, Echo, Go, Rust, design tokens, UI/UX.",
"version": "1.5.0",
"description": "Disciplined MCP server + skill system. 16 plugins, 121 tools, 29 skills, 4 personas with adversarial enforcement. Personas (product-manager gate; marketing + reflect + bro capabilities), Designer/DESIGN.md pipeline, shadcn/ui, React Flow, Motion, Lenis, React 19, Echo, Go, Rust, design tokens, UI/UX.",
"bin": {
"hyperstack": "bin/hyperstack.mjs"
},
Expand Down
6 changes: 3 additions & 3 deletions summary.md
Original file line number Diff line number Diff line change
Expand Up @@ -67,8 +67,8 @@ Hyperstack uses internal roles to manage complexity. These roles are **internal
- **`hyper` (Core):** The conductor. Owns request classification, routing, gate enforcement, final verification, and delivery.
- **`website-builder` (Specialist):** Owns website-facing design/implementation, CTA hierarchy, and page structure. Delegates back to `hyper` for verification.

### 9. The Skill System (21 skills, 3 categories)
Every skill has a `category:` frontmatter field. The index at `skills/INDEX.md` is auto-generated from frontmatter by `bash scripts/generate-skills-index.sh`.
### 9. The Skill System (29 skills, 3 categories)
Every skill has a `category:` frontmatter field. The index at `skills/INDEX.md` is auto-generated from frontmatter by `bun scripts/generate-skills-index.ts`.

- **Core (13):** blueprint, forge-plan, run-plan, best-practices, ship-gate, deliver, test-first, debug-discipline, code-review, autonomous-mode, subagent-ops, parallel-dispatch, worktree-isolation
- **Domain (6):** designer, shadcn-expert, behaviour-analysis, security-review, readme-writer, python-pro-coder, react-pro-coder
Expand Down Expand Up @@ -113,7 +113,7 @@ Every skill references its upstream and downstream edges explicitly.

**Active development.** Main branch is stable and the Docker image publishes automatically on push.

Eleven plugins, seventy-nine tools, twenty-one skills, and two internal agents (`hyper` and `website-builder`). The SessionStart hook is wired. The adversarial enforcement is in place. The designer pipeline works end-to-end (verified via test harness). shadcn is integrated as an optional choice.
Sixteen plugins, one hundred twenty-one tools, twenty-nine skills, four personas, and two internal agents (`hyper` and `website-builder`). The SessionStart hook is wired. The adversarial enforcement is in place. The designer pipeline works end-to-end (verified via test harness). shadcn is integrated as an optional choice.

### Remaining work
- More pressure-test scenarios for gate skills (forge-plan, best-practices, behaviour-analysis, test-first)
Expand Down
Loading