Yodecomp: Instructions file for Claude Code

CLAUDE.md

Yodecomp CLAUDE.md is an instructions file for Claude Code from shinyquagsire23/Yodecomp. It costs 41,532 tokens per session, scanned A, original, CC0-1.0.

Project-specific instructions for Yodecomp, a buildable C++ recreation and extension of LucasArts' Desktop Adventures game engine. They cover the current goals, build and debugging process, and WebAssembly support.

In plain words
What is it for?
Working on Yoda Stories or Indiana Jones' Desktop Adventures engine code, including native builds, debugging, code generation, and WebAssembly builds.
Why use it?
They preserve the project's reverse-engineering progress and define the checks needed to avoid regressing its close match to the original game executable.

Instructions file for Claude Code

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

This is shinyquagsire23/Yodecomp's own configuration. It tells Claude Code how to work on Yodecomp 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 Yodecomp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shinyquagsire23/Yodecomp. 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/shinyquagsire23/Yodecomp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/shinyquagsire23/Yodecomp

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 Yodecomp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shinyquagsire23/yodecomp/claude-md/github.svg)](https://agentmods.dev/instructions/shinyquagsire23/yodecomp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shinyquagsire23/yodecomp/claude-md"><img src="https://agentmods.dev/badge/instructions/shinyquagsire23/yodecomp/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 Yodecomp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/shinyquagsire23/yodecomp/claude-md"><img src="https://agentmods.dev/badge/instructions/shinyquagsire23/yodecomp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41,532 This file is loaded in full into every session.
When invoked 41,532 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 $0.41532 $0.41532
Opus 5 $0.20766 $0.20766
Sonnet 5 $0.08306 $0.08306
Haiku 4.5 $0.04153 $0.04153

Measured 2d ago against content hash 3d8a9c21575f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Yodecomp 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 2d 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 · 1,669 lines

How it starts

The opening of the file, as written. The whole thing — 1,669 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Yodecomp — Desktop Adventures decompilation + engine

Decompilation of LucasArts' Desktop Adventures engine (Yoda Stories / Indiana Jones' Desktop Adventures) into real, buildable C++/MFC source, plus an extended multi-game engine built on it. Patterns follow ~/workspace/OpenJKDF2 (CMake, macOS/Linux hosts, wine for Windows toolchains). Claude is permitted to modify this file with any useful notes that will aid other/later Claudes.

Deep history lives in PLAN_COMPLETED.md — the full phased plan (A–G), TU/struct status tables, the v1–v71 milestone chain, and the ⭐ KEY codegen lessons #1–#40 + MFC-matching lessons (later lessons #41–#47 are standing bullets in this file) (cite as "PLAN_COMPLETED.md lesson #N"). This file carries only what's needed to work NOW.

Where the project stands (2026-07-11, v87; re-baselined 217→234 at v100 (MEASUREMENT FIX); 234→237 at v102, 237→240 at v103, 240→244 at v104, 244→247 at v105, 247→249 at v106, 249→250 at v107, 250→251 at v108, 251→255 at v110 (REAL MATCHES); 255→252 at v114 — a DELIBERATE, user-approved re-baseline DOWN, see below; held at 252 at v115; 252→255 at v116 (REAL MATCHES — the CONTAINER CALL FORM, lesson #48); held at 255 at v117, which landed no new match but cut 654 bytes of residual STRUCTURALLY via the new LENGTH census, lesson #49; 255→257 at v118 (REAL MATCHES — the MEMBER-ALIAS/CSE-reload dial, lesson #50, plus the INNER-BLOCK decl axis no tool could reach); 257→258 at v119 (REAL MATCH — the COMPOSITE LEVER, lesson #51: two dials that each measure WORSE alone, including on LENGTH, landing together; it also cut 1029 bytes of residual across four more functions and put four more LENGTHS exactly on their Ghidra extents); 258→255 at v120 — the SECOND DELIBERATE, user-approved re-baseline DOWN, for a real ARITY BUG in TextDialog::Layout, see below; v120 also cut 1050 bytes of residual across three functions and put two more LENGTHS exactly on their extents; 255→256 at v121 (REAL MATCH — the CROSS-JUMPED IF/ELSE, lesson #52: a constant argument materialized by a BRANCH in the original is two duplicated CALLS tail-merged, not an expression); held at 256 at v122 — no new byte-match, but OnNewDocument 0x41bb10's LENGTH went 946 -> 975 = its extent EXACTLY (537 B -> 422) on a RECOVERED MISSING SOURCE CONSTRUCT, the house CATCH_ALL+THROW_LAST, found by lesson #53's read-it-out-of-your-own-exact-code method; held at 256 at v123 — no new byte-match, but the SIX closest-to-exact functions in the project (11 bytes total) were PROVEN unreachable from the source and closed: lesson #54, the compare-encoding peephole)

Read the full file on GitHub · 1,669 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. 2d ago Changed · +681 lines · +17,516 tokens per session 3d8a9c21575f
  2. 4d ago Changed · +305 lines · +7,321 tokens per session 887ed418beed
  3. 9d ago First seen · 683 lines · 16,695 tokens per session scan A 3ca0bcd501ee

Subscribe to this mod's changes

Yodecomp CLAUDE.md is an instructions file published in the GitHub repository shinyquagsire23/Yodecomp (22 stars, last pushed 3d ago), licensed CC0-1.0. It adds 41,532 tokens to every session, about $0.2077 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

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

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