shipjaw-adopt

shipjaw-adopt is a skill for Claude Code from XyDisorder/shipjaw. It costs 0 tokens per session (1,868 once invoked), scanned A, original, MIT.

An adoption workflow for bringing an existing TypeScript, Next.js, or React TypeScript application under the Shipjaw documentation and development process.

In plain words
What is it for?
It is for surveying an existing app, merging Shipjaw documentation, planning architecture improvements, and adding agent rules and missing development tools.
Why use it?
It identifies gaps in the app's documentation and architecture without automatically rewriting the product code or starting the project over.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Cursor.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is - [ ] ./scripts/survey-adopt-state.sh <root> (read fully, incl. arch signals).

Good fit It is for surveying an existing app, merging Shipjaw documentation, planning architecture improvements, and adding agent rules and missing development tools.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/XyDisorder/shipjaw
agentmods
npx agentmods add skills/xydisorder/shipjaw/shipjaw-adopt

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-adopt

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/xydisorder/shipjaw/shipjaw-adopt"><img src="https://agentmods.dev/badge/skills/xydisorder/shipjaw/shipjaw-adopt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,868 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 $0.00000 $0.01868
Opus 5 $0.00000 $0.00934
Sonnet 5 $0.00000 $0.00374
Haiku 4.5 $0.00000 $0.00187

Measured 3d ago against content hash d429c777595d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

shipjaw-adopt 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.

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-adopt/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shipjaw-adopt

Adopt only. Bring an existing app under the Shipjaw continuation contract without re-scaffolding or rewriting the product by default.

After adopt → use shipjaw-ask (including the proposed arch convergence phase). Never run shipjaw-build on a non-empty app that already has product code.

Templates / kit: ../shipjaw-build/templates/ · ../shipjaw-build/templates/scaffold/ · ../shipjaw-build/templates/technical-plan-converge-arch.md. Complete Shipjaw KB already: shipjaw-ask + migration — not a full re-adopt.

Anti-triggers

  • No app yet / empty folder → /shipjaw then prompt/build
  • Rough idea only → shipjaw-prompt
  • Complete Shipjaw KB already (documentation/INDEX.md + knowledge-base/architecture.md + features-index.md) → shipjaw-ask (migration upgrades if needed). Partial docs → stay here and merge (never wipe).
  • Non-TypeScript repo → refuse
  • User wants a full rewrite / new Next app → shipjaw-build in a new folder, not adopt-in-place

Checklist

- [ ] Detect TS/Next app
- [ ] ./scripts/survey-adopt-state.sh <root>  (read fully, incl. arch signals)
- [ ] Classify: NO_DOCS | PARTIAL_DOCS | FULL_SHIPJAW_KB
- [ ] If FULL → stop; hand off shipjaw-ask
- [ ] ≤2 clarify Q only for gaps survey couldn't answer
- [ ] init-docs-skeleton (idempotent)
- [ ] Absorb foreign plans → roadmap / features-index / decisions / changelog
- [ ] Architecture practice audit (read-only) → gaps table in architecture.md
- [ ] Propose converge-arch phase (plan only; no mass refactor)
- [ ] copy-continuation-contract + stamp-provenance --adopted
- [ ] Tooling gaps idempotent
- [ ] validate-docs + validate-docs-drift + run-gate (cheap)
- [ ] Write documentation/handoff.md (next /shipjaw-ask … + arch P0)
- [ ] Status snapshot + improvement plan summary + /shipjaw-ask handoff

Workflow

1. Detect + survey (mandatory)

../shipjaw-build/scripts/survey-adopt-state.sh <project-root>

Read all sections, including architecture practice signals and the gate baseline (lint/typecheck). A pre-existing baseline failure isn't this adopt's fault — record it as an architecture.md gap (not a P0/P1 architecture row, its own line) so nobody mistakes it for a regression later, and so a future run-gate.sh run isn't a surprise.

Read the full file on GitHub · 178 lines

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 d429c777595d
  2. 11d ago First seen · 178 lines · 0 tokens per session scan A 39481ea62c76

Subscribe to this mod's changes

shipjaw-adopt is a skill published in the GitHub repository XyDisorder/shipjaw (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,868 tokens. 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.