What is match-function?

A reverse-engineering workflow for matching one Parasite Eve 2 function so its compiled GCC 2.8.1 output for MIPS matches the target binary byte for byte.

Bootstrapping a function-matching workspace, making minimal C changes, compiling attempts, and checking them against the target object file.

It provides a repeatable process for compiling, comparing, and verifying function attempts instead of guessing from assembly alone.

How GabeRealB/parasite-eve-2-decomp configures Claude Code and Codex

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/.grok/skills/match-function/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/GabeRealB/parasite-eve-2-decomp

Made for: Claude Code, Codex.

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/skills/gaberealb/parasite-eve-2-decomp/match-function/github.svg)](https://agentmods.dev/skills/gaberealb/parasite-eve-2-decomp/match-function)

Your own site

<a href="https://agentmods.dev/skills/gaberealb/parasite-eve-2-decomp/match-function"><img src="https://agentmods.dev/badge/skills/gaberealb/parasite-eve-2-decomp/match-function/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/skills/gaberealb/parasite-eve-2-decomp/match-function"><img src="https://agentmods.dev/badge/skills/gaberealb/parasite-eve-2-decomp/match-function.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 999 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00065	$0.00999
Opus 5	$0.00032	$0.00500
Sonnet 5	$0.00013	$0.00200
Haiku 4.5	$0.00006	$0.00100

Measured 9d ago against content hash 99ab5f3bd0e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

match-function 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 9d 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.

.grok/skills/match-function/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Match one function

The matching loop (dumps, pins, permuter, verify) lives in tools/claude-decomp-env/MATCH_LOOP.md and is loaded as a Grok project rule (.grok/rules/match-loop.md). Follow it. Do not plan edits from asm-differ alone. Do not add register … asm("") because a saved register is wrong in the object dump.

Vacuum or ./tools/claude --bootstrap-only may already have created nonmatchings/<func>/ with base.c, target.o, and BRIEF.md. If that directory exists, do not re-run ./tools/claude.

If it does not exist, from the repo root:

./tools/claude --bootstrap-only <func>

That command resolves any overlay (asm/<ver>/<overlay>/…, including nested future units like stage1/101). Never search only asm/USA/main/. If tools/giveups/<func>/base.c exists, bootstrap copies that seed into base.c instead of m2c — start from it.

This session

Read BRIEF.md in the scratch dir.
cd there and run ./build.sh base.c with minimal edits so it compiles. Do not rewrite m2c/give-up C from the asm before the first score. If the seed is pinned, unpin as base_1.c and rescore.
Put each attempt in base_N.c. Prefer already-matched siblings in the same TU over m2c control flow.
After each ≥90% score, build.sh prints a NEXT: line. The next tool call is reading those dump files, then one C edit. Control-flow leftovers (branch/insert/delete ≠ 0) are not a pin/permuter job.
Grep DECOMPILATION_LEARNINGS.md for the mismatch; do not read the whole file.
Permuter only at ≥ 95% with branch=insert=delete=0, before pins. Vacuum also permutes after you exit if you leave a ≥95% unpinned base_N.c.
Stop after ~10 attempts with no gain (or ~40 total). build.sh will also flag a stall.

Finish

100%: replace INCLUDE_ASM in the host C file. New types go in this overlay's include/ (include/main/, include/gameplay/, include/<overlay>/). Not include/main/unknown_syms.h. Run ./tools/build-and-verify.sh and wait for ✅ BUILD SUCCEEDED. Commit matched <func> <attempts>.
Give up: append tools/difficult_functions as <func> <attempts> <best%>. Revert host C.
If vacuum launched you, leave the scratch dir (best unpinned base_N.c included). Vacuum archives it to tools/giveups/<func>/ then cleans the scratch. Otherwise delete the scratch after commit/give-up.
If the vacuum prompt says this is a disposable worktree (pe2-wt-<func>), commit only on this worktree. Do not git merge onto trunk and do not append tools/difficult_functions there; a later port agent on the original tree lands the result.
If the vacuum prompt says you are the port agent: rewrite the function onto current trunk. Never git merge / rebase / cherry-pick the worktree. Adapt to structs and TUs other agents already landed, then verify and commit on trunk.
Stale build/: worktrees copy existing binaries that still checksum from the INCLUDE_ASM version. sha256sum --check on build/USA/out/SLUS_010.42 is not a match. Only ./tools/build-and-verify.sh → ✅ BUILD SUCCEEDED counts. If python3 lacks splat/spimdisasm, use venv/bin/python3.

Read the full file on GitHub · 40 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.

9d ago First seen · 40 lines · 65 tokens per session scan A 99ab5f3bd0e7

Subscribe to this mod's changes

match-function is a skill published in the GitHub repository GabeRealB/parasite-eve-2-decomp (31 stars, last pushed today), licensed CC0-1.0. It adds 65 tokens to every session and 999 once invoked, about $0.0003 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.

Debugging

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens

parasite-eve-2-decomp: Skill for Claude Code