agentmods.dev

d2r-horadric-tools: Instructions file for Claude Code

CLAUDE.md

d2r-horadric-tools CLAUDE.md is an instructions file for Claude Code from crabsmadethis/d2r-horadric-tools. It costs 1,076 tokens per session, scanned A, original, MIT.

Repository instructions for d2r-horadric-tools, software that reads and edits Diablo II: Resurrected save files. They define trusted data sources, save-file safety rules, and requirements for checking edits.

In plain words
What is it for?
Use it when looking up game data, editing .d2s character saves, preserving existing file structure, creating verified backups, and validating each edit phase.
Why use it?
Save files contain interdependent binary data, and invented identifiers or direct edits can corrupt them. The instructions require using verified local data, making backups, staging writes, and scanning after changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is crabsmadethis/d2r-horadric-tools's own configuration. It tells Claude Code how to work on d2r-horadric-tools 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 d2r-horadric-tools configures →

not rated 5repo 1mo ago A scan 1,076 tokens original MIT
View source ↗ crabsmadethis/d2r-horadric-tools
Reuse

Borrowing it

Nothing to install: this file belongs to crabsmadethis/d2r-horadric-tools. 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/crabsmadethis/d2r-horadric-tools/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/crabsmadethis/d2r-horadric-tools

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 d2r-horadric-tools CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/crabsmadethis/d2r-horadric-tools/claude-md/github.svg)](https://agentmods.dev/instructions/crabsmadethis/d2r-horadric-tools/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/crabsmadethis/d2r-horadric-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/crabsmadethis/d2r-horadric-tools/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 d2r-horadric-tools CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/crabsmadethis/d2r-horadric-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/crabsmadethis/d2r-horadric-tools/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,076 This file is loaded in full into every session.
When invoked 1,076 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 $0.01076 $0.01076
Opus 5 $0.00538 $0.00538
Sonnet 5 $0.00215 $0.00215
Haiku 4.5 $0.00108 $0.00108

Measured 12d ago against content hash d4d15f719b16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

d2r-horadric-tools 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 12d 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.

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 · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Instructions

Follow these rules when working in this repository. They apply to Claude Code slash commands, MCP tool use, and direct file edits.

Data Sources

  • Do not invent item IDs, UIDs, stat encodings, runeword IDs, skill IDs, or binary format values.
  • Read the generated data modules in d2r_chargen/data/ before using D2R constants:
    • unique_items.py
    • set_items.py
    • item_bases.py
    • item_dimensions.py
    • runewords.py
    • item_stat_cost.py
    • skills.py
  • Use MCP lookups such as d2r_lookup_unique, d2r_lookup_runeword, and d2r_search when available.
  • Do not trust web research for D2R game data. If the value is not in local extracted data or a verified source file, treat it as unknown.

Save-File Invariants

  • Do not rebuild a .d2s from scratch when a targeted edit can preserve the existing file structure. Header fields around 0x14-0x7F are interdependent.
  • Back up before writing any .d2s:
shutil.copy2(path, path + ".pre_DESCRIPTION_bak")
  • Verify the backup exists before editing.
  • Write to a temp or staging path first. Do not write directly to the live save path.
  • Run the scanner after every edit phase:
d2r-chargen scan <name>
  • Verify checksums after writing:
stored == calc_checksum(result)
  • Verify file-size fields when the write changes file length.
  • Promote the temp file to the live path only after scanner validation passes.
  • Do not stack multiple risky edits before scanning.
  • Treat scanner hard errors as deployment blockers unless bit-level evidence proves the scanner is wrong.
  • D2R caches saves at session startup. Fully exit and relaunch D2R after file changes; staying on character select is not enough.

Item and Stat Encoding

  • Items must include stat properties. build_item() with only unique_id and no magic_attributes can display the correct name with zero stats.
  • Encode item properties from item_stat_cost.py.
  • Grouped stats with num_params > 0 must encode all parameter and value pairs under the same stat ID. Splitting or omitting grouped values can make a save fail to join.
  • Merc gear direct injection requires canonical JM[merc] encoding:
    • col=bodyloc, not 0
    • runeword low 12 bits are id + 27
    • runeword high 4 bits are 5
    • lf_count=0
  • Use equipment_mode: direct for mercenary YAML. The stash-and-equip workaround is not required for direct mode.

Read the full file on GitHub · 126 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. 12d ago First seen · 126 lines · 1,076 tokens per session scan A d4d15f719b16

Subscribe to this mod's changes

d2r-horadric-tools CLAUDE.md is an instructions file published in the GitHub repository crabsmadethis/d2r-horadric-tools (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,076 tokens to every session, about $0.0054 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.

Game developmentcascchargend2rdiablo-2diablo-2-resurrectedmcp-server
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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 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

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