Display Name
Pilot Shell
Category
Workflows & Knowledge Guides
Sub-Category
General
Primary Link
https://github.com/maxritter/pilot-shell
Author Name
Max Ritter
Author Link
https://maxritter.net
License
Other (specify below)
Other License
Source Code is Open, using Pilot requires a Subscription after free Trial
Description
Claude Code is powerful. Pilot Shell makes it reliable. Start a task, grab a coffee, come back to production-grade code. Tests enforced. Context preserved. Quality automated.
Validate Claims
I'm Max, a senior IT freelancer from Germany. My clients hire me to ship production-quality code — tested, typed, formatted, and reviewed. When something goes into production under my name, quality isn't optional.
Claude Code writes code fast. But without structure, it skips tests, loses context, and produces inconsistent results — especially on complex, established codebases where there are real conventions to follow and real regressions to catch. I tried other frameworks. Most of them add complexity — dozens of agents, elaborate scaffolding, thousands of lines of instruction files — but the output doesn't get better. You just burn more tokens, wait longer, and deal with more things breaking.
So I built Pilot Shell. Instead of adding process on top, it bakes quality into every interaction. Linting, formatting, and type checking run as enforced hooks on every edit. TDD is mandatory, not suggested. Context is preserved across sessions. Every rule exists because I hit a real problem: a bug that slipped through, a regression that shouldn't have happened, a session where Claude cut corners and nobody caught it.
This isn't a vibe coding tool, it's true agentic engineering, made simple. You install it in any existing project, run pilot, then /sync to learn your codebase. The guardrails are just there. The end result is that you can walk away — start a /spec task, approve the plan, go grab a coffee. When you come back, the work is tested, verified, formatted, and ready to ship.
Specific Task(s)
/spec Build a Kanban task board app using Next.js (App Router), SQLite (via Drizzle ORM + better-sqlite3), Tailwind CSS with shadcn/ui components, and @hello-pangea/dnd for drag-and-drop.
Single-page task board with three columns: To Do, In Progress, Done. Users can:
- Drag and drop task cards between columns (optimistic UI, no flicker)
- Create new tasks (title, description, priority: Low/Medium/High)
- Edit existing tasks via a modal dialog
- Delete tasks with confirmation dialog
- See task count badges on each column header
Each task card shows: title, truncated description (2 lines), and a color-coded priority badge (red=High, amber=Medium, green=Low).
Use Next.js Server Actions for all CRUD operations. SQLite database with a single "tasks" table (id, title, description, priority, status, position, created_at). Seed ~15 sample tasks on first run.
UI: shadcn/ui Card, Dialog, AlertDialog, Button, Badge, Input, Select, Label, Textarea. Sonner for toast notifications.
Specific Prompt(s)
Use the /spec command
Additional Comments
No response
Recommendation Checklist
Display Name
Pilot Shell
Category
Workflows & Knowledge Guides
Sub-Category
General
Primary Link
https://github.com/maxritter/pilot-shell
Author Name
Max Ritter
Author Link
https://maxritter.net
License
Other (specify below)
Other License
Source Code is Open, using Pilot requires a Subscription after free Trial
Description
Claude Code is powerful. Pilot Shell makes it reliable. Start a task, grab a coffee, come back to production-grade code. Tests enforced. Context preserved. Quality automated.
Validate Claims
I'm Max, a senior IT freelancer from Germany. My clients hire me to ship production-quality code — tested, typed, formatted, and reviewed. When something goes into production under my name, quality isn't optional.
Claude Code writes code fast. But without structure, it skips tests, loses context, and produces inconsistent results — especially on complex, established codebases where there are real conventions to follow and real regressions to catch. I tried other frameworks. Most of them add complexity — dozens of agents, elaborate scaffolding, thousands of lines of instruction files — but the output doesn't get better. You just burn more tokens, wait longer, and deal with more things breaking.
So I built Pilot Shell. Instead of adding process on top, it bakes quality into every interaction. Linting, formatting, and type checking run as enforced hooks on every edit. TDD is mandatory, not suggested. Context is preserved across sessions. Every rule exists because I hit a real problem: a bug that slipped through, a regression that shouldn't have happened, a session where Claude cut corners and nobody caught it.
This isn't a vibe coding tool, it's true agentic engineering, made simple. You install it in any existing project, run pilot, then /sync to learn your codebase. The guardrails are just there. The end result is that you can walk away — start a /spec task, approve the plan, go grab a coffee. When you come back, the work is tested, verified, formatted, and ready to ship.
Specific Task(s)
/spec Build a Kanban task board app using Next.js (App Router), SQLite (via Drizzle ORM + better-sqlite3), Tailwind CSS with shadcn/ui components, and @hello-pangea/dnd for drag-and-drop.
Single-page task board with three columns: To Do, In Progress, Done. Users can:
Each task card shows: title, truncated description (2 lines), and a color-coded priority badge (red=High, amber=Medium, green=Low).
Use Next.js Server Actions for all CRUD operations. SQLite database with a single "tasks" table (id, title, description, priority, status, position, created_at). Seed ~15 sample tasks on first run.
UI: shadcn/ui Card, Dialog, AlertDialog, Button, Badge, Input, Select, Label, Textarea. Sonner for toast notifications.
Specific Prompt(s)
Use the /spec command
Additional Comments
No response
Recommendation Checklist