mandragora: Instructions file for Claude Code

CLAUDE.md

mandragora CLAUDE.md is an instructions file for Claude Code from mvrozanti/mandragora. It costs 233 tokens per session, scanned B, original, no licence file.

Repository instructions for using Claude Code in the Mandragora project, including its project workflow and rules for safe work by multiple agents.

In plain words
What is it for?
Use it when working on the mvrozanti/mandragora codebase with Claude Code.
Why use it?
It gives Claude Code project-specific guidance so its changes follow the repository’s conventions and file-safety rules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

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

Reuse

Borrowing it

Nothing to install: this file belongs to mvrozanti/mandragora. 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/mvrozanti/mandragora/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mvrozanti/mandragora

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 mandragora CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mvrozanti/mandragora/claude-md"><img src="https://agentmods.dev/badge/instructions/mvrozanti/mandragora/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 233 This file is loaded in full into every session.
When invoked 233 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00233 $0.00233
Opus 5.5 $0.00093 $0.00093
Sonnet 5.5 $0.00047 $0.00047
Haiku 4.5 $0.00023 $0.00023

Measured 19d ago against content hash 214e7d8b4cb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

mandragora CLAUDE.md scanned grade B 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 19d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

Claude Code may run `sudo nixos-rebuild switch --flake <worktree>#mandragora-desktop` directly to iterate before landing, but only from a clean commit (a WIP commit in the worktree is fine) that descends from what is run
CLAUDE.md · 19 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 19d ago Changed · +49 tokens per session 214e7d8b4cb7
  2. 2mo ago First seen · 19 lines · 184 tokens per session scan B c5d0d2609105

Subscribe to this mod's changes

mandragora CLAUDE.md is an instructions file published in the GitHub repository mvrozanti/mandragora (5 stars, last pushed 2d ago), with no licence file. It adds 233 tokens to every session, about $0.0009 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

mandragora CLAUDE.md compared with instructions from other repositories

mandragora CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mandragora CLAUDE.mdmvrozanti/mandragoraInstructions file52d agononeB233Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode