init

init is a skill for Claude Code from Jebel-Quant/rhiza-claude. It costs 49 tokens per session (3,116 once invoked), scanned A, original, MIT.

A repository setup command for making a folder a rhiza-managed Python, Rust, or Go project. It adds a pointer to the template repository, a project skeleton, licensing, and a pull request as part of the setup.

In plain words
What is it for?
Use it to initialize a project for rhiza management, select the template reference, create the required skeleton and license, and prepare the initial pull request.
Why use it?
It gives a new repository the structure and connection needed to follow a shared template. It also makes the setup reviewable through a pull request and leaves later syncing as a separate action.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool; mentions Claude Code.

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 rhiza plugin — 10 skills, 1 hook shipped together

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 Jebel-Quant/rhiza-claude
Claude Code
/plugin install rhiza

Made for: Claude Code.

Or install rhiza, the plugin that ships this one along with the rest of its 10 skills, 1 hook.

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 init

README.md
[![agentmods](https://agentmods.dev/badge/skills/jebel-quant/rhiza-claude/init.svg)](https://agentmods.dev/skills/jebel-quant/rhiza-claude/init)
Your own site
<a href="https://agentmods.dev/skills/jebel-quant/rhiza-claude/init"><img src="https://agentmods.dev/badge/skills/jebel-quant/rhiza-claude/init.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,116 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00049 $0.03116
Opus 5 $0.00024 $0.01558
Sonnet 5 $0.00010 $0.00623
Haiku 4.5 $0.00005 $0.00312

Measured 5d ago against content hash 0a11defa1dd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

init scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

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

allowed-tools: Bash(git*), Bash(gh*), Bash(glab*), Bash(uv*), Bash(curl*), Bash(brew*), Bash(ls*), Bash(basename*), Bash(pwd*), Bash(date*), Read, Write, Edit, AskUserQuestion, Skill
plugin/skills/init/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running /init in the current working directory. Goal: make this folder a rhiza-managed repo and deliver it as a PR.

/init writes exactly one file itself.rhiza/template.yml, the pointer saying which template repository this repo follows and at which ref. Everything else it Reads from the procedure that owns it, so each concern has one source of truth and /init stays a coordinator rather than a second implementation:

what procedure step
uv on the machine plugin/prompts/install-uv.md 1
work branch off an untouched default plugin/prompts/pr-base.md 4
skeleton + the pyproject.toml shape the gates need plugin/prompts/skeleton.md (applies plugin/prompts/python-version.md) 6
SPDX metadata + the LICENSE file plugin/prompts/license.md 6

Those are internal procedures, not slash commands — deliberately kept out of any directory Claude Code scans, so the user can't invoke them. Read each at the step that calls for it (${CLAUDE_PLUGIN_ROOT}/prompts/<name>.md; in a source checkout the variable is empty, so use the repo-relative path) and follow it as written. Never re-implement one inline — no hand-rolled pyproject.toml edits, no LICENSE writing, no uv init of your own.

No sync, no gates. Bootstrapping is two PRs: #1 (/init) makes the repo rhiza-managed; #2 (/update, after #1 merges) pulls the template content. Keeping the sync out of /init stops it re-implementing /update and drifting from it. The user runs /docs for README.md/CLAUDE.md/mkdocs.yml and /quality for a scorecard.

Argument (optional): $ARGUMENTS — the repository name; default basename "$PWD". Hold as NAME.

Work through these steps. Stop and report if a precondition fails.

1. Preconditions

  • Already rhiza-managed? → hand off. If a .rhiza/ directory exists (test -d .rhiza), invoke the update command via the Skill tool and stop. Don't write or touch anything under .rhiza/ yourself — bumping an existing config is /update's job. This holds even for a stray .rhiza/ with no template.yml.
  • uvRead plugin/prompts/install-uv.md and follow it, every run. A one-line no-op when uv is present; otherwise it installs it. If uv --version still fails, stop.
  • Gitgit rev-parse --is-inside-work-tree (ignore the error if absent). No repo ⇒ git init -b main. If a repo exists, record any origin as EXISTING_ORIGIN.

You don't need to vet the folder's contents: everything /init runs is additive and never overwrites, so an empty folder and a mature repo are the same case.

Read the full file on GitHub · 202 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. 5d ago First seen · 202 lines · 49 tokens per session scan A 0a11defa1dd0

Subscribe to this mod's changes

init is a skill published in the GitHub repository Jebel-Quant/rhiza-claude (4 stars, last pushed 7d ago), licensed MIT. It adds 49 tokens to every session and 3,116 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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