new-repo

new-repo is a skill for Claude Code from PBNZ/repo-kit. It costs 67 tokens per session (2,794 once invoked), scanned A, original, Apache-2.0.

A repository scaffold that creates a new code repository using the RepoKit standard, a set of conventions and templates for repository structure.

In plain words
What is it for?
It is for creating a new module, plugin, or project repository with the required files and settings.
Why use it?
Starting a repository from scratch can miss required files or apply the wrong structure. This workflow fills the appropriate templates and stops for local review.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions AGENTS.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the repokit plugin — 2 skills shipped together

Good fit It is for creating a new module, plugin, or project repository with the required files and settings.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add PBNZ/repo-kit
Claude Code
/plugin install repokit

Made for: Claude Code.

Or install repokit, the plugin that ships this one along with the rest of its 2 skills.

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-repo

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/pbnz/repo-kit/new-repo"><img src="https://agentmods.dev/badge/skills/pbnz/repo-kit/new-repo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,794 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 $0.00067 $0.02794
Opus 5 $0.00034 $0.01397
Sonnet 5 $0.00013 $0.00559
Haiku 4.5 $0.00007 $0.00279

Measured 11d ago against content hash 0a936f32e052, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

new-repo 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 11d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (templates/addons/living-docs/core/scripts/check-docs.ps1, templates/core/scripts/install-privacy-guard.ps1, templates/core/scripts/repokit-check.ps1, …), 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.

plugins/repokit/skills/new-repo/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

new-repo — scaffold a RepoKit-standard repository

You scaffold a new repository by copying bundled templates and filling in their {{placeholders}} (copy-and-fill — there is no separate templating engine). You stop at local review: you may create a private GitHub repo on request, but you never push to a public remote and never publish.

Your templates live under this skill's own directory. At load you were given a line Base directory for this skill: <ABS>. Read every template as <ABS>/templates/<...>. Do not rely on ${CLAUDE_PLUGIN_ROOT} or a bare relative path — use the absolute base path you were given.

Two reference files (read them from the same base dir as you need them):

  • references/file-set-resolution.md — exactly which templates apply for a given type × tier.
  • references/placeholders.md — the placeholder list and the post-scaffold self-check.

Inputs

Gather these from the user's arguments / message, else ask — keep it to load-bearing questions:

  • name — the repo / directory name. Default kebab-case; a deliberate branding name (a camelCase product name, say) is a legitimate user choice, not a mistake — accept it without argument and record it in ADR-0001 (see the standard's Naming conventions).
  • description — one line.
  • type — one of: powershell-module, docker-compose, power-platform-connectors, skill-plugin, collection, mcp-server, app-ts, app-python, script-collection.
  • visibilityprivate (= Core tier), public (= +Public), or published (= +Published).
  • author — the identity stamped wherever an author/owner/copyright value is written. Default: the GitHub handle of the gh-authenticated user (gh api user --jq .login; no gh → ask). A real personal name only when the user explicitly chooses one for this repo — that choice is a declared variance: record it in ADR-0001 and give it a START-HERE row (see the standard's Author identity).
  • license — default Apache-2.0.
  • living-docs add-on — yes/no, default no. Ask: "Will this repo's docs track live operational state (deployed resources, scheduled jobs, long-running migrations)?" If yes, the add-on stamps docs/RUNBOOK.md, docs/STATE.json, scripts/check-docs.ps1, and a docs.yml check workflow (see references/living-docs-rules.md).
  • early licenceprivate repos only, default no. Ask: "Is a public release already planned?" If yes, stamp LICENSE now from the Public-tier template, and ask one follow-up: "Will third-party licensed material be incorporated while still private?" — if so, also stamp NOTICE (see references/file-set-resolution.md, Early licence). Record both answers in ADR-0001. No START-HERE variance row — an early licence on a promotion-planned repo follows the standard's Promotion path, it doesn't deviate from it.
  • For powershell-module only: ModuleName (PascalCase, e.g. MyModule).

Read the full file on GitHub · 163 lines

Files

What ships with it

58 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. 11d ago First seen · 163 lines · 67 tokens per session scan A 0a936f32e052

Subscribe to this mod's changes

new-repo is a skill published in the GitHub repository PBNZ/repo-kit (1 stars, last pushed 29d ago), licensed Apache-2.0. It adds 67 tokens to every session and 2,794 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

captain-recall

Use when the user asks WHY or WHAT-HAPPENED questions about this system — historical decisions, past incidents, why code/config is shaped a certain way, where something is deployed, who decided what, or the state of work in flight. Queries the tsubasa knowledge graph for cited answers.

ramarahmanda/tsubasa · 65 tokens

captain-delegate

Use when implementation work is approved and ready to be executed — the captain briefs subagents, supervises them, unblocks or escalates when they stall, and validates results against the knowledge graph before accepting. The captain never writes feature code itself.

ramarahmanda/tsubasa · 54 tokens

captain-onboard

Use when the user wants to CREATE a captain here — "set up tsubasa", "be my captain", "init a captain for this repo/workspace", "I want a captain- " — or to UPDATE an existing one after updating the CLI ("I upgraded tsubasa, now what"). Scaffolds .tsubasa/, auto-detects knowledge sources, runs the first ingest, and…

ramarahmanda/tsubasa · 110 tokens

captain-inject

Use when the user STATES A FACT about the system or tells the captain to remember/learn something — "update your knowledge", "remember this", "we dropped X for Y", "the outage was caused by Z", environment URLs, team contacts, deployment flows, tribal knowledge, corrections to what the Captain believes. Validates…

ramarahmanda/tsubasa · 85 tokens

captain-capture

Use at DECISION MOMENTS — the user accepts a proposed design/approach after discussion, approves a plan, or concludes "let's do X". Persists the decision as an ADR + event in the tsubasa knowledge graph so it is never lost.

ramarahmanda/tsubasa · 58 tokens

decision

Single entry point for all decision operations: capture, search, manage. Routes based on natural language intent.

zimalabs/code-decisions · 23 tokens