parasite-eve-2-decomp: Instructions file for Claude Code

CLAUDE.md

parasite-eve-2-decomp CLAUDE.md is an instructions file for Claude Code from GabeRealB/parasite-eve-2-decomp. It costs 8,285 tokens per session, scanned A, original, CC0-1.0.

Repository instructions for recreating the exact machine code of Parasite Eve 2, a PlayStation game, from C source code. They describe where source files, headers, assembly files, libraries, and extracted game data live.

In plain words
What is it for?
Use them when editing decompiled game code, locating matched or unmatched functions, or working with overlay build configurations.
Why use it?
They help an agent navigate a large matching-decompilation project and understand which files are generated and which are maintained by hand.

Instructions file for Claude Code

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

This is GabeRealB/parasite-eve-2-decomp's own configuration. It tells Claude Code how to work on parasite-eve-2-decomp 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 parasite-eve-2-decomp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GabeRealB/parasite-eve-2-decomp. 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/GabeRealB/parasite-eve-2-decomp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/GabeRealB/parasite-eve-2-decomp

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 parasite-eve-2-decomp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gaberealb/parasite-eve-2-decomp/claude-md/github.svg)](https://agentmods.dev/instructions/gaberealb/parasite-eve-2-decomp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/gaberealb/parasite-eve-2-decomp/claude-md"><img src="https://agentmods.dev/badge/instructions/gaberealb/parasite-eve-2-decomp/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 parasite-eve-2-decomp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gaberealb/parasite-eve-2-decomp/claude-md"><img src="https://agentmods.dev/badge/instructions/gaberealb/parasite-eve-2-decomp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,285 This file is loaded in full into every session.
When invoked 8,285 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 $0.08285 $0.08285
Opus 5 $0.04143 $0.04143
Sonnet 5 $0.01657 $0.01657
Haiku 4.5 $0.00829 $0.00829

Measured today against content hash 56b09cd65b2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

parasite-eve-2-decomp 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 today.

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 · 520 lines

How it starts

The opening of the file, as written. The whole thing — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repository Overview

This is a matching decompilation project for Parasite Eve 2 (PS1). The goal is to create C code that, when compiled, produces the exact same assembly as the original game ROM.

Project Structure

  • src/<overlay> decompiled C (src/main, src/gameplay, src/title) and src/<family>/<overlay> for the generated overlay families (src/weapons/m93r, …)
  • include/<overlay> headers for that unit (include/main, include/gameplay, …)
  • asm/<ver>/<overlay>/nonmatchings unmatched functions (one .s per function). Overlays may be nested (e.g. asm/USA/stage1/101/nonmatchings).
  • asm/<ver>/<overlay>/matchings already-matched functions
  • lib library code such as Psy-Q objects we link against
  • assets binary asset blobs extracted from the rom

Generated overlay configs

main / gameplay / title have hand-written splat configs; each has quirks a template cannot express. Every other overlay is a flat .pe2pkg with the same shape, and there are 446 of them, so their configs are generated:

File Role
configs/USA/overlays.toml the manifest — keyed by package name, holding only what the decomp adds
configs/USA/overlay.template.yaml the shared config body
configs/USA/generated/*.yaml output, gitignored, rewritten by every ninja_config.py run
configs/USA/sym/<family>/<name>.txt per-overlay symbol map
configs/USA/sym/<family>.imports.txt main + gameplay imports, shared by the family

sha1, size and the .text span are derived from the package, never written in the manifest, so a config cannot drift from the data it describes.

Model streams are named too, by SHA-1 in asset_data.MODELS, because dedup otherwise lets whichever package sorts first name a shared mesh. A named mesh shows under that name in every package carrying it.

An overlay is an extracted package. Identified packages — and the folders and stage-0 files that contain them — are named in the extractor (tools/peassets/asset_data.py, preserved across dump_asset_db.py regeneration by sha1), so they extract as m93r.pe2pkg rather than pe2pkg_2.pe2pkg. The manifest key is that name and the config is built from assets/USA/pe2pkg/<key>.pe2pkg — file ids appear nowhere in the decomp. Several stage-0 ids can load one package (the extractor dedups by SHA-1, so 10500 and 10600 are one file); naming it once in the extractor is what makes it one thing here. The generator errors if two entries resolve to the same package.

Read the full file on GitHub · 520 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. today Changed · +27 lines · +445 tokens per session 56b09cd65b2c
  2. yesterday Changed · +17 lines · +289 tokens per session 2ee0f6cd9708
  3. 2d ago Changed · +7 lines · +136 tokens per session 8cc604c93c44
  4. 3d ago Changed · +112 lines · +1,926 tokens per session 94c5f108cea5
  5. 4d ago Changed · +9 lines · +151 tokens per session 1f8e3a647e43
  6. 7d ago Changed · +16 lines · +337 tokens per session e129afa9ddc2
  7. 11d ago First seen · 332 lines · 5,001 tokens per session scan A e4db2c005609

Subscribe to this mod's changes

parasite-eve-2-decomp CLAUDE.md is an instructions file published in the GitHub repository GabeRealB/parasite-eve-2-decomp (31 stars, last pushed today), licensed CC0-1.0. It adds 8,285 tokens to every session, about $0.0414 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 2026-08-30.

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 · 7,104 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