open-agent-ready-typescript: Skill for Claude Code

.claude/skills/scaffold-agent-ready/SKILL.md

scaffold-agent-ready is a skill for Claude Code from lucasgodt/open-agent-ready-typescript. It costs 145 tokens per session (1,160 once invoked), scanned A, original, MIT.

A starter TypeScript project with automated rules for dependency boundaries, mutation testing, protected tests and specifications, commit checks, and specification-first development.

In plain words
What is it for?
Use it when starting a backend API or service that needs enforced project structure, tests, specifications, and agent-editing safeguards.
Why use it?
It helps prevent unsafe changes and incomplete work from passing unnoticed. The checks run during verification, commits, and continuous integration.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is lucasgodt/open-agent-ready-typescript's own configuration. It tells Claude Code how to work on open-agent-ready-typescript itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything open-agent-ready-typescript configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lucasgodt/open-agent-ready-typescript. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lucasgodt/open-agent-ready-typescript/main/.claude/skills/scaffold-agent-ready/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lucasgodt/open-agent-ready-typescript

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 scaffold-agent-ready

README.md
[![agentmods](https://agentmods.dev/badge/skills/lucasgodt/open-agent-ready-typescript/scaffold-agent-ready/github.svg)](https://agentmods.dev/skills/lucasgodt/open-agent-ready-typescript/scaffold-agent-ready)
Your own site
<a href="https://agentmods.dev/skills/lucasgodt/open-agent-ready-typescript/scaffold-agent-ready"><img src="https://agentmods.dev/badge/skills/lucasgodt/open-agent-ready-typescript/scaffold-agent-ready/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 scaffold-agent-ready

Your own site · 80×15
<a href="https://agentmods.dev/skills/lucasgodt/open-agent-ready-typescript/scaffold-agent-ready"><img src="https://agentmods.dev/badge/skills/lucasgodt/open-agent-ready-typescript/scaffold-agent-ready.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,160 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 $0.00145 $0.01160
Opus 5 $0.00072 $0.00580
Sonnet 5 $0.00029 $0.00232
Haiku 4.5 $0.00015 $0.00116

Measured 10d ago against content hash 652fd6e3887b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

scaffold-agent-ready 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 10d 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/scaffold-agent-ready/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scaffold Agent-Ready TypeScript Project

Creates a new TypeScript project that inherits the five machine-enforced guardrails from https://github.com/lucasgodt/open-agent-ready-typescript, adapted to the user's domain and project shape. You are not copying an example app — you are transplanting a guardrail system and growing a new domain inside it.

The five guardrails (every variant, non-negotiable)

  1. Dependency rule as a build gate — dependency-cruiser config wired into verify, the commit hook and CI. The domain layer/package imports nothing.
  2. Mutation testing (Stryker) on domain + application code, break < 75%.
  3. Protected tests and specs — the PreToolUse hook blocks agent edits to tests/** and specs/** without a human-created .agent/allow-test-edits.
  4. Commit gate — a hook runs the full verify suite on git commit, blocking on failure and feeding errors back to the agent.
  5. Spec-driven development as a build gate — one Given/When/Then spec per use case, tests mirroring criteria one it("N. ...") per criterion, enforced by scripts/check-spec-coverage.mjs inside verify (use case without spec, orphan spec, or unmirrored criterion all fail the build). npm run new -- <name> scaffolds the golden path. Hierarchical AGENTS.md.

Step 0 — Gather what you need

Ask the user (only what's missing from context):

  1. Project name and target directory.
  2. Shape: backend API/service, frontend app, or monorepo? If they describe "an app with an API and a web client", that's a monorepo.
  3. Domain: what the software does, in one sentence, plus the 2–5 core operations (these become the first use cases).
  4. Anything to skip.

Step 1 — Read the variant reference

Read exactly one file before scaffolding, and follow it:

  • Backend API/service → references/backend.md
  • Frontend app (React/Vite) → references/frontend.md
  • Monorepo (apps + packages) → references/monorepo.md

Do not blend variants from memory; the monorepo reference already composes the other two where relevant.

Read the full file on GitHub · 86 lines

Files

What ships with it

3 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. 10d ago First seen · 86 lines · 145 tokens per session scan A 652fd6e3887b

Subscribe to this mod's changes

scaffold-agent-ready is a skill published in the GitHub repository lucasgodt/open-agent-ready-typescript (5 stars, last pushed 1mo ago), licensed MIT. It adds 145 tokens to every session and 1,160 once invoked, about $0.0007 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.