rhiza-claude: Instructions file for Claude Code

CLAUDE.md

rhiza-claude CLAUDE.md is an instructions file for Claude Code from Jebel-Quant/rhiza-claude. It costs 6,209 tokens per session, scanned A, original, MIT.

Repository-specific instructions for working on rhiza-claude, a plugin marketplace project, including its commands, architecture, and conventions.

In plain words
What is it for?
Use them when modifying rhiza-claude, running its quality checks, or interpreting the results of those checks.
Why use it?
They explain which project rules apply, including that this repository is not itself managed by Rhiza and that its quality command runs in a limited mode.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Jebel-Quant/rhiza-claude's own configuration. It tells Claude Code how to work on rhiza-claude 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 rhiza-claude configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to Jebel-Quant/rhiza-claude. 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/Jebel-Quant/rhiza-claude/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Jebel-Quant/rhiza-claude

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 rhiza-claude CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jebel-quant/rhiza-claude/claude-md/github.svg)](https://agentmods.dev/instructions/jebel-quant/rhiza-claude/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jebel-quant/rhiza-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/jebel-quant/rhiza-claude/claude-md/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 rhiza-claude CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jebel-quant/rhiza-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/jebel-quant/rhiza-claude/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,209 This file is loaded in full into every session.
When invoked 6,209 The same file — it is already loaded in full.
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 $0.06209 $0.06209
Opus 5 $0.03104 $0.03104
Sonnet 5 $0.01242 $0.01242
Haiku 4.5 $0.00621 $0.00621

Measured yesterday against content hash 2e81a7479a9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

rhiza-claude CLAUDE.md 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 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.

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.md · 361 lines

How it starts

The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code sessions in rhiza-claude — the Claude Code plugin marketplace providing the rhiza plugin.

Read this first: which side of the boundary you're on

This repo is the plugin. It is not a rhiza-managed repo — there is no .rhiza/ directory, no template.yml, no template.lock, and nothing here is synced from anywhere. That has two consequences worth internalising before you touch anything:

  • /rhiza:quality runs here in its degraded mode. Its step-0 check looks for .rhiza/template.yml and .rhiza/template.lock; both are absent, so it skips every template-delivered gate, runs the targets this repo's own local.mk documents, and scores the design work. It used to refuse outright. Read any score it produces as what it says it is — a design-led assessment on this repo's own gates, not a Rhiza verdict, and not comparable to a managed repo's number.
  • The "locally-owned vs Rhiza-owned" scoping rule doesn't apply. Every file here is locally owned. When you read that rule in plugin/prompts/scorecard.md, you're reading a rule this repo ships for other repos, not one that governs it — which is also why degraded mode inverts it: with no template, the Makefile, local.mk and workflows are this repo's own work and are squarely in scope.

Commands

The targets live in local.mk, not the Makefile. The Makefile is the shim shape rhiza's core bundle ships — front door, uv bootstrap, and a %: catch-all that delegates unknown targets to rhiza-task. Nothing here delegates: an explicit rule beats a pattern rule, so every target below is local.mk's. Add a target there, never to the Makefile.

make help           # list every target
make fmt            # all prek hooks over every file (delegated to rhiza-task)
make audit          # bandit over the scripts, zizmor over the workflows
make complexity     # radon CC/MI — the census this file quotes; reports, never fails
make test           # pytest over tests/, 100% coverage gate on scripts/
make e2e            # only the end-to-end tests, no coverage gate (template-drift's target)
make portable       # everything except e2e, no coverage gate (the cross-platform CI job's target)
make book           # build the docs site into _book/ (runs paper + test first)
make book-serve     # docs with live reload
make paper          # build the LaTeX paper (needs tectonic or pdflatex)
make paper-figures  # regenerate the paper's figures
make clean          # drop caches and build artifacts
make changelog      # regenerate CHANGELOG.md from conventional commits
make install        # install the plugin via the claude CLI

Read the full file on GitHub · 361 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 Changed 2e81a7479a9f
  2. 9d ago First seen · 361 lines · 6,209 tokens per session scan A 2ee572e6403e

Subscribe to this mod's changes

rhiza-claude CLAUDE.md is an instructions file published in the GitHub repository Jebel-Quant/rhiza-claude (4 stars, last pushed yesterday), licensed MIT. It adds 6,209 tokens to every session, about $0.0310 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens