What is lsw1-decomp AGENTS.md?

A set of project instructions for matching the decompiled code of the 2005 GameCube game LEGO Star Wars: The Video Game to its original compiled form. Decompilation means recreating source code from a compiled game.

Use it to build the project, look up symbols, suggest or apply function names, prepare coding tasks, mine evidence from donor binaries, and measure matching progress.

It gives coding agents the project’s required compiler, source priorities, tools, and verification process so changes can be checked against the original game code.

How ellierocks/lsw1-decomp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ellierocks/lsw1-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/ellierocks/lsw1-decomp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ellierocks/lsw1-decomp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ellierocks/lsw1-decomp/agents-md/github.svg)](https://agentmods.dev/instructions/ellierocks/lsw1-decomp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ellierocks/lsw1-decomp/agents-md"><img src="https://agentmods.dev/badge/instructions/ellierocks/lsw1-decomp/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ellierocks/lsw1-decomp/agents-md"><img src="https://agentmods.dev/badge/instructions/ellierocks/lsw1-decomp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 819 This file is loaded in full into every session.

When invoked 819 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.

Model	Per session	Once invoked
Fable 5.1	$0.00819	$0.00819
Opus 5.5	$0.00328	$0.00328
Sonnet 5.5	$0.00164	$0.00164
Haiku 4.5	$0.00082	$0.00082

Measured 3d ago against content hash 849fc57394cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lsw1-decomp AGENTS.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 3d 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.

AGENTS.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LSW1 decomp agent guide

Matching decompilation of LEGO Star Wars: The Video Game (2005), GameCube GL5E4F. Game/Nu2 code uses SN Systems ProDG 3.9.3 (GCC) via tools/prodg_cc.py; the Dolphin SDK uses Nintendo CodeWarrior GC/1.2.5n from doldecomp/dolsdk2004. CrashWOC's CodeWarrior game code generation does not transfer.

Task routing

Start with strategy for the current phase; update it when the plan changes.
Improve the workflow as you go. Fix drafting, m2c, sweep and search tools when that unlocks matches more effectively than hand-editing each function. Preserve reproducible patches, test the fix and rerun it on affected targets to collect the wins. See workflow improvement.
Sprint tools cover target selection, ownership detection, queue accounting and verification. Choose scope and search effort for the task; T3 owns orchestration and continuation.
Matching: follow the quickstart for bootstrap, target selection, scoring and handoff, and C matching for strict verification and promotion. SDK work uses SDK import.
Game/Nu2 donor review: follow the OpenSaga workflow. Read donor_evidence.md and record hillclimb.py try --donor-note once per target/donor revision; retain accepted facts, rejected transfers or an explicit no-hit/unavailable limit in the PR or plateau handoff. With no name hit, hillclimb.py records the no-hit limit itself.
Binary evidence: Ghidra and REA provide decompiles, callers and cross-references. Confirm proposed types and names against target assembly; donor output and generated C are evidence, not the acceptance oracle.
Naming and research: research; check rejected renames first. Nu2, menus and scripts hold subsystem evidence. Confirm donor types against LSW1 accesses.
Configuration/splits: build configuration. Setup and the documentation index: README.
Checks and completion: development workflow. Run bash build.sh for splits, configuration, compiler wiring, candidate sources or reports, then python3 tools/matching_progress.py. Docs-only work needs link, content-preservation and git diff --check validation; required current-head CI still gates merge. Retain the matching evidence in PRs.

Read the full file on GitHub · 53 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.

3d ago Changed · +2 lines · +4 tokens per session 849fc57394cc
6d ago Changed · +9 lines · +199 tokens per session 0a970f65c413
7d ago Changed · -24 lines · -208 tokens per session 4f1ec10a69c4
8d ago Changed · +6 lines · +101 tokens per session 31ffdd2ecee9
9d ago Changed · -57 lines · -1,197 tokens per session 84cb500cace2
2mo ago First seen · 117 lines · 1,920 tokens per session scan A 07950c1d9b00

Subscribe to this mod's changes

lsw1-decomp AGENTS.md is an instructions file published in the GitHub repository ellierocks/lsw1-decomp (12 stars, last pushed yesterday), licensed CC0-1.0. It adds 819 tokens to every session, about $0.0033 per session on Opus 5.5. 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.

Game development

lsw1-decomp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
lsw1-decomp AGENTS.mdellierocks/lsw1-decomp	Instructions file	12	yesterday	CC0-1.0	A	819	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

lsw1-decomp: Instructions file for Codex