init

A command that creates a new local WordPress Studio site with its content files taken from a GitHub repository. Studio is a local WordPress development app.

In plain words
What is it for?
Use it to start a new local site from an a8c GitHub repository, with an optional project name for the folder and Studio site.
Why use it?
It sets up the local site and repository connection from the repository and project name, instead of requiring each setup step by hand.

Command

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.

agentmods
npx agentmods add commands/a8cteam51/claude-code-plugins/init
Clone the repo
git clone --depth 1 https://github.com/a8cteam51/claude-code-plugins
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,570 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
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 $0.00044 $0.01570
Opus 5 $0.00022 $0.00785
Sonnet 5 $0.00009 $0.00314
Haiku 4.5 $0.00004 $0.00157

Measured yesterday against content hash 9836fffd3399, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

init scanned grade C with 2 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 yesterday.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Do not run `curl`, `unzip`, `rm -rf wp-content`, `git clone`, or `studio site create` outside the script.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Do not run `curl`, `unzip`, `rm -rf wp-content`, `git clone`, or `studio site create` outside the script.
plugins/studio-repo-clone/commands/init.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/studio-repo-clone:init

Orchestrate the studio-repo-clone workflow. All filesystem mutations, git auth preflight, .gitignore patching, and Studio invocation are delegated to ${CLAUDE_PLUGIN_ROOT}/scripts/scaffold.sh — your job is to gather inputs, choose the target directory, and invoke the script. Never replicate the script's behaviour inline; that breaks the repeatability guarantee.

Inputs

Parse $ARGUMENTS as up to two whitespace-separated tokens:

  • Token 1: repo (owner/repo shorthand or git URL — required).
  • Token 2 (optional): project name. If present, must be a valid directory name (lowercase, digits, hyphens, underscores).

If the repo is missing, ask via AskUserQuestion (free-text via "Other"). Do not proceed without one.

Derive the repo name from the URL (used as the suggested project name):

  • owner/reporepo
  • https://github.com/owner/repo(.git)?repo
  • [email protected]:owner/repo.gitrepo

Step 1 — get the project name

The project name is used for both the root folder and the Studio site name.

  • If token 2 was provided and is valid, use it. Confirm in plain text.

  • Otherwise ask via AskUserQuestion:

    1. <repo-name> (recommended)
    2. (Other for custom name)

    If the user provides something invalid (spaces, uppercase, punctuation), slugify it (e.g. "My Cool Project" → "my-cool-project") and confirm the slug back before proceeding.

Step 2 — choose the target directory

Run pwd, basename "$(pwd)", and ls -A "$(pwd)".

Also detect the user's effective Studio base directory from existing Studio sites — Studio has no CLI flag that exposes its install root, so we infer it from studio site list:

studio site list --format json 2>/dev/null \
  | jq -r '.[].path // empty' 2>/dev/null \
  | xargs -I {} dirname {} \
  | sort | uniq -c | sort -rn \
  | awk 'NR==1 {sub(/^[[:space:]]*[0-9]+[[:space:]]+/, ""); print}'

jq is used for JSON parsing (robust against escaped quotes / minified output), xargs -I {} preserves paths with spaces, and the awk strips the leading uniq -c count without splitting on whitespace inside the path.

Read the full file on GitHub · 113 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. yesterday First seen · 113 lines · 44 tokens per session scan C 9836fffd3399

Subscribe to this mod's changes

init is a command published in the GitHub repository a8cteam51/claude-code-plugins (3 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 1,570 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.