shipjaw-build

shipjaw-build is a skill for Claude Code from XyDisorder/shipjaw. It costs 173 tokens per session (1,640 once invoked), scanned A, original, MIT.

A build workflow for starting a new TypeScript or Next.js application from a well-defined product prompt. It creates project documentation and sets rules for typing, testing, security, and code structure.

In plain words
What is it for?
It is for scaffolding a new web application, adding Vitest and Playwright tests, setting security headers, and shipping an initial version after checks pass.
Why use it?
It gives a new project a documented structure and verification process from the beginning, while identifying cases where starting over would be inappropriate.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit It is for scaffolding a new web application, adding Vitest and Playwright tests, setting security headers, and shipping an initial version after checks pass.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xydisorder/shipjaw/shipjaw-build
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add XyDisorder/shipjaw --skill shipjaw-build
Clone the repo
git clone --depth 1 https://github.com/XyDisorder/shipjaw

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for shipjaw-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/xydisorder/shipjaw/shipjaw-build/github.svg)](https://agentmods.dev/skills/xydisorder/shipjaw/shipjaw-build)
Your own site
<a href="https://agentmods.dev/skills/xydisorder/shipjaw/shipjaw-build"><img src="https://agentmods.dev/badge/skills/xydisorder/shipjaw/shipjaw-build/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for shipjaw-build

Your own site · 80×15
<a href="https://agentmods.dev/skills/xydisorder/shipjaw/shipjaw-build"><img src="https://agentmods.dev/badge/skills/xydisorder/shipjaw/shipjaw-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,640 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00173 $0.01640
Opus 5 $0.00086 $0.00820
Sonnet 5 $0.00035 $0.00328
Haiku 4.5 $0.00017 $0.00164

Measured 3d ago against content hash c9c466fc4a6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

shipjaw-build scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

The scan reads SKILL.md. This mod also ships 15 executable files (scripts/changelog-since-stamp.sh, scripts/copy-continuation-contract.sh, scripts/init-docs-skeleton.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/shipjaw-build/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shipjaw-build

Bootstrap-only. Turns a build-ready product prompt into a scaffolded TypeScript site and a committed documentation/ map. Later sessions use shipjaw-ask. Prefer shipjaw-prompt first when the idea is still vague.

Slash-preferred (disable-model-invocation) — avoid ambient auto-scaffold.

Operating principles: references/skill-principles.md (1–18) — open only if a principle conflict arises; hard rules below are enough for most runs.

Anti-triggers (stop — don't run bootstrap)

  • documentation/knowledge-base/ already exists → shipjaw-ask
  • Existing app code without Shipjaw KB → shipjaw-adopt (do not re-scaffold in place)
  • Idea is still vague / user wants help wording the product → shipjaw-prompt first
  • Single-file cosmetic / copy tweak with no product build
  • Non-TypeScript codebase
  • User only wants framework tutorial text (point at official docs)

Hard rules (never negotiable)

  1. Typingstrict: true. No any. unknown only at untyped entry points, narrowed via zod/type guard. → code-standards.md
  2. File size — hard cap 500 lines; plan split ~300.
  3. Architecture — canonical tree in project-structure.md (including types / constants / helpers, ports, composition root, thin adapters, error→UI/HTTP map). Contracts consumer updates only if packages/contracts/ exists. No grab-bag lib/utils.ts or layer barrels.
  4. Tests — Vitest for domain/application; Playwright + axe + keyboard/focus smoke for critical flows. Bug fix ⇒ regression test; never weaken tests to green. → testing-and-ci.md · regression-and-business-rules.md
  5. Security — secrets out of git; authz in application/; actions re-check session; middleware; CSP via scaffold next.config.ts.
  6. Documentation — committed documentation/. No app code before INDEX.md + phase-01. Stamp via scripts/stamp-provenance.sh.
  7. Verify — one gate/phase; stop after 2 failed attempts. On the second failure read references/gate-failure-modes.md before one last focused fix; then ask the human if still red.
  8. KB current — update before done; state not only in chat.
  9. UI floor — when shipping visible UI, obey references/design-constraints.md (+ product design-brief).

Read the full file on GitHub · 130 lines

Files

What ships with it

59 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago Changed · +9 lines c9c466fc4a6c
  2. 11d ago First seen · 121 lines · 173 tokens per session scan A ee4e9e896bd0

Subscribe to this mod's changes

shipjaw-build is a skill published in the GitHub repository XyDisorder/shipjaw (2 stars, last pushed 3d ago), licensed MIT. It adds 173 tokens to every session and 1,640 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.