reverse-algo

reverse-algo is a command for Claude Code from SetsunaYukiOvO/x64dbg-mcp. It costs 9 tokens per session (731 once invoked), scanned A, original, MIT.

A command that examines compiled machine code in x64dbg or x32dbg to identify an algorithm and produce pseudocode or documentation. Disassembly is the process of reading machine instructions rather than source code.

In plain words
What is it for?
Use it to inspect a function at a memory address, trace its callers and branches, resolve referenced data, and recognize patterns such as hashing, checksums, or encoding.
Why use it?
It helps make sense of a function when its original source code or useful documentation is unavailable.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

Part of the skills plugin — 1 skill, 11 commands shipped together

Good fit Use it to inspect a function at a memory address, trace its callers and branches, resolve referenced data, and recognize patterns such as hashing, checksums, or encoding.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/setsunayukiovo/x64dbg-mcp/reverse-algo
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/SetsunaYukiOvO/x64dbg-mcp

Made for: Claude Code.

Or install skills, the plugin that ships this one along with the rest of its 1 skill, 11 commands.

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 reverse-algo

README.md
[![agentmods](https://agentmods.dev/badge/commands/setsunayukiovo/x64dbg-mcp/reverse-algo/github.svg)](https://agentmods.dev/commands/setsunayukiovo/x64dbg-mcp/reverse-algo)
Your own site
<a href="https://agentmods.dev/commands/setsunayukiovo/x64dbg-mcp/reverse-algo"><img src="https://agentmods.dev/badge/commands/setsunayukiovo/x64dbg-mcp/reverse-algo/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 reverse-algo

Your own site · 80×15
<a href="https://agentmods.dev/commands/setsunayukiovo/x64dbg-mcp/reverse-algo"><img src="https://agentmods.dev/badge/commands/setsunayukiovo/x64dbg-mcp/reverse-algo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 731 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.
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 $0.00009 $0.00731
Opus 5 $0.00005 $0.00365
Sonnet 5 $0.00002 $0.00146
Haiku 4.5 $0.00001 $0.00073

Measured 11d ago against content hash bf8634f88498, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

reverse-algo 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 11d 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.

skills/commands/reverse-algo.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an algorithm analysis specialist connected to x64dbg/x32dbg via MCP. Analyze the algorithm at address: $1

If "$1" is empty, ask the user to provide an address.

Phase 1: Code Extraction

  1. Call disassembly_function at "$1" for complete function disassembly.
    • If function boundary detection fails, call disassembly_at with count: 100.
  2. Call symbol_from_address to check for a known name.
  3. Call function_get at the address to get precise start/end boundaries.
  4. Call memory_get_info to identify the owning module and section.
  5. Call xref_get at the function start to find all callers.

Phase 2: Structural Analysis

  1. Map the function structure:
    • Prologue (stack frame setup, register preservation)
    • Basic blocks at branch targets
    • Loops (backward jumps), conditionals (forward jumps), switch tables
  2. Resolve all CALL targets with symbol_from_address.
  3. For each referenced data address, call memory_read (64-256 bytes) to examine content.
  4. Identify constants and magic numbers:
    • Crypto: 0x67452301 (MD5/SHA1), 0x6A09E667 (SHA-256), 0x61707865 (ChaCha20)
    • CRC: 0xEDB88320 (CRC32), 0x04C11DB7
    • Encoding: 0x3F (Base64 mask), ASCII table references
    • Check for S-boxes, lookup tables, round constants

Phase 3: Dynamic Analysis

If the debugger is paused at the function entry: 8. Call register_list to capture input parameters. 9. Call stack_read_frame to read stack-passed parameters. 10. Step through one loop iteration with debug_step_over to observe values. 11. Use eval_expression to compute intermediate values with architecture-neutral aliases where possible, such as [csp+0x20]; use the target's native registers for register-specific expressions (for example, rax*4+rbx on x64 or eax*4+ebx on x86).

Phase 4: Report

=== Algorithm Analysis Report ===

Location: 0x... - 0x... ([size] bytes)
Function: [symbol name if known]
Module:   [module name]

Algorithm Identification:
  Type: [cryptographic / hash / compression / encoding / sorting / custom]
  Match: [known algorithm name, e.g., "AES-128-ECB", "CRC32", "Base64"]
  Confidence: [high/medium/low]
  Evidence: [constants, structure, patterns]

Function Signature (estimated):
  [return_type] function([params])

Pseudocode:
  [C-like pseudocode of the algorithm]

Data References:
  - 0x...: [e.g., "S-box lookup table (256 bytes)"]
  - 0x...: [e.g., "Round constants array"]

Control Flow:
  - Main loop: [address range], iterates [N] times
  - Key operations step-by-step

Notes:
  - [customizations from standard algorithm]
  - [potential weaknesses if crypto-related]

Read the full file on GitHub · 74 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. 11d ago First seen · 74 lines · 9 tokens per session scan A bf8634f88498

Subscribe to this mod's changes

reverse-algo is a command published in the GitHub repository SetsunaYukiOvO/x64dbg-mcp (460 stars, last pushed 21d ago), licensed MIT. It adds 9 tokens to every session and 731 once invoked, about $0.0000 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.