dunx: Skill for Claude Code

.claude/skills/new-package/SKILL.md

new-package is a skill for Claude Code from petarzarkov/dunx. It costs 97 tokens per session (1,491 once invoked), scanned A, original, MIT.

A process for adding a workspace to a monorepo, a repository that contains several related projects, as a published package, command-line tool, private workspace, or example.

In plain words
What is it for?
Creating a new @dunx package or CLI, adding private repository code, or adding an example with the correct workspace structure.
Why use it?
It ensures the new workspace has the required metadata, build entry points, exports, documentation, and publishing settings.

Skill for Claude Code

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

This is petarzarkov/dunx's own configuration. It tells Claude Code how to work on dunx 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 dunx configures →

Reuse

Borrowing it

Nothing to install: this file belongs to petarzarkov/dunx. 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/petarzarkov/dunx/main/.claude/skills/new-package/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/petarzarkov/dunx

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 new-package

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/petarzarkov/dunx/new-package"><img src="https://agentmods.dev/badge/skills/petarzarkov/dunx/new-package.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,491 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00097 $0.01491
Opus 5 $0.00048 $0.00745
Sonnet 5 $0.00019 $0.00298
Haiku 4.5 $0.00010 $0.00149

Measured 9d ago against content hash 7661196e105e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

new-package 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 9d 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/new-package/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/new-package

packages/core is the reference. Copy its shape rather than composing a manifest from memory.

Pick the parent first

Parent For Published Reference
packages/ framework an app imports yes packages/core
tools/ a CLI a consumer runs (bunx @dunx/<name>) yes tools/mcp
internal/ repo-only: site, harness, bundle, shared UI no internal/ui
examples/ an app that consumes the packages no examples/minimal

Two lists decide what publishes, and both must name a new published parent - they are the only places that know: PUBLISHABLE_DIRS in scripts/version.ts and PUBLISHED_DIRS in scripts/update-readme.ts. private: true is what actually stops a publish, so getting the parent wrong fails safe.

A workspace with no build script is skipped by scripts/build-all.ts, which is how internal/ui ships as source with its exports pointing at src/.

Published package - packages/<name>/ or tools/<name>/

  1. package.json - copy packages/core/package.json and change name to @dunx/<name>, description, keywords, homepage, and repository.directory - the last two carry the parent, so tools/<name> rather than packages/<name> for a CLI. Leave the rest alone. The fields that are not optional:
    • "type": "module" - without it verbatimModuleSyntax raises TS1287 against ESM syntax, and Node treats the shipped ESM as CommonJS
    • main + typesdist/ paths, and an exports map with types and import conditions. No module field, no require condition - ESM only
    • "files": ["LICENSE", "README.md", "dist"] - without it src/ ships
    • version: "0.0.0" - scripts/version.ts owns it from here
    • scripts verbatim: build, test, test:cov, typecheck
  2. tsconfig.json - exactly packages/core/tsconfig.json: extends the root, include: ["src"], exclude: ["node_modules", "dist"]. One per package. Do not add a build variant.
  3. src/index.ts re-exporting the public surface, LICENSE, README.md.
  4. bun install to link the workspace.
  5. bun run build && bun run typecheck && bun run test.
  6. bun run gen:cov && bun run gen:readme - picks up the coverage badge and the README Packages table row.
  7. Add the row to the Packages Overview table in CLAUDE.md.
  8. First publish must be manual - see /release.

Read the full file on GitHub · 102 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. 9d ago First seen · 102 lines · 97 tokens per session scan A 7661196e105e

Subscribe to this mod's changes

new-package is a skill published in the GitHub repository petarzarkov/dunx (111 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 1,491 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

nestjs

Use when building or structuring a NestJS backend — feature modules, providers and DI wiring, provider scopes and request-lifecycle order, where to bind guards/pipes/interceptors/filters, and testing with Test.createTestingModule. NOT a bare Express/Fastify service with no DI (that is nodejs), NOT framework-agnostic…

ericrisco/rsc-harness · 81 tokens

terraform-test

Comprehensive guide for writing and running Terraform tests. Use when creating test files (.tftest.hcl), writing test scenarios with run blocks, validating infrastructure behavior with assertions, mocking providers and data sources, testing module outputs and resource configurations, or troubleshooting Terraform test…

Cloudgeni-ai/opengeni · 59 tokens

bun-guides-test

Practical guides for testing TypeScript applications, mocking modules, mocking fetch, and running unit tests in Bun.

LuigiColantuono/bun-docs-toolkit · 27 tokens

Node Expert

Node Expert delivers production-grade technical work with clear architecture, tests, maintainability, and operational awareness.

ahmadrrrtx/xr · 23 tokens

server-side-calls

Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.

trpc/trpc · 61 tokens

insta-snapshots

Guide for working with and updating insta snapshot tests in Oxc without terminal interaction.

oxc-project/oxc · 22 tokens