Open Source · Zero Config · Zero Dependencies

THE ENGINEERING LAYER
FOR AI CODING AGENTS.

57 engineering skills activate invisibly while you code. TDD, security, architecture, quality gates — enforced automatically. Context persists across every session. You see everything it does.

npx shipworthy init
View on GitHub ›
Benchmark
Same prompts. Same model.
One had Shipworthy.

Two agents ran identical 7-turn non-technical founder prompts. 36 automated checks — written before either agent ran — scored the output.

Without Shipworthy
41%15 / 36
DatabaseIn-memory arrays
ValidationNone
Loggingconsole.log
Types5x :any
Tests0
Secrets.env exposed
ErrorsNone
With Shipworthy
97%35 / 36
DatabaseSQLite + schemas
ValidationZod on every route
LoggingPino structured
TypesStrict TypeScript
Tests39 passing
SecretsGuarded + .gitignore
ErrorsProper status codes

Full methodology, all 10 task definitions, and reproduction scripts on GitHub.

How it works
Install once. Everything
else is automatic.
01

One command to start

Run npx shipworthy init in any project. Hooks install automatically. Skills load on demand. No config files to edit, no workflows to learn.

02

Hooks guard every action

Six hooks run in real time. Files scanned for secrets before writes. Bash commands checked for destructive patterns. Dependencies monitored. Everything logged transparently to your terminal.

03

Skills activate invisibly

Say "build a payment API" and TDD, input validation, security, and API design skills activate automatically. You code normally. The engineering happens underneath.

04

Context persists automatically

Hooks capture every session event — commits, security warnings, pattern detections. A regression fence of "NEVER do X" rules loads every session. No more repeating the same mistakes.

05

Quality compounds

Session signals auto-process into learnings and fence rules at next session start. Corrections become permanent knowledge. Every session starts smarter than the last — 95% automatic.

terminal
⚓ shipworthy session-start
┌─ ⚓ shipworthy ───────────────────────────┐
Tier: ENGINEER Health: all passed
Skills: 57 Hooks: 6 active
└──────────────────────────────────────────┘
⚓ shipworthy session-start › Regression fence: 5 rule(s) loaded
⚓ shipworthy session-start › Unprocessed signals: 8 from last session
 
⚓ shipworthy pre-tool-use › Scanning payments.ts
⚓ shipworthy signal › captured: pattern — console.log in payments.ts
⚓ shipworthy pre-tool-use › ! console.log in prod: WARN
0
Skills
0
Hooks
0
Commands
0
Agents
0
Dependencies
Capabilities
What 57 skills
actually cover.

Each skill is a Markdown file. No code, no runtime, no dependencies. Just engineering instructions that make AI agents build production-grade software.

Real-time guardrails

Six hooks guard every action. Secrets caught before files are written. Destructive commands blocked before execution. Security scans logged transparently.

Test-driven by default

Failing test first, then implementation, then verification. TDD happens automatically. You see "it works." Underneath: tests prove it.

Adaptive quality gates

5 files: light touch. 50 files: coverage thresholds. 500 files: security scans, performance budgets, circular import detection.

11 security profiles

Auto-detects application type — web, API, GraphQL, mobile, CLI, pipeline, IoT, desktop, infrastructure — and applies the right security checks.

Context intelligence

Hooks capture session signals automatically. Regression fence loads anti-patterns every session. Auto-retro processes corrections into permanent knowledge. 95% automatic.

Full transparency

Every hook, signal capture, and fence check logged with color-coded output. Skills announce themselves before activating. Toggle off with one environment variable.