compare-state

compare-state is a command for Claude Code from SetsunaYukiOvO/x64dbg-mcp. It costs 8 tokens per session (535 once invoked), scanned A, original, MIT.

A command that records debugger state at two execution points and compares the results. The state can include registers, memory, the call stack, and machine-code instructions.

In plain words
What is it for?
Use it to compare before-and-after execution states while debugging, tracing behavior, or investigating a suspected change.
Why use it?
It makes changes during program execution easier to identify and relate to the code path being followed.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit Use it to compare before-and-after execution states while debugging, tracing behavior, or investigating a suspected change.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/setsunayukiovo/x64dbg-mcp/compare-state"><img src="https://agentmods.dev/badge/commands/setsunayukiovo/x64dbg-mcp/compare-state.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 535 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 $0.00008 $0.00535
Opus 5 $0.00004 $0.00267
Sonnet 5 $0.00002 $0.00107
Haiku 4.5 $0.00001 $0.00053

Measured 12d ago against content hash 67dd98eb7cb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

compare-state 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 12d 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/compare-state.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a state comparison analyst connected to x64dbg/x32dbg via MCP. Capture and compare debugger states.

Phase 1: Capture Snapshot A (Current State)

  1. Call debug_get_state to confirm the debugger is paused.
  2. Call context_get_snapshot with include_memory: true, include_stack: true.
  3. Call register_list for detailed register values.
  4. Call disassembly_at at the current instruction pointer (cip) with count: 10.
  5. Call stack_get_trace for the call stack.
  6. Call bookmark_set at the current instruction pointer (cip) to mark Snapshot A position.

Report:

Snapshot A captured at 0x... ([symbol])
  Registers, stack, memory: saved

Ready. Execute to your comparison point, then tell me to capture Snapshot B.
(Use debug_run, debug_step_over, debug_step_into, or debug_run_to)

Phase 2: Capture Snapshot B

After the user advances execution: 6. Call context_get_snapshot with the same parameters. 7. Call register_list again. 8. Call disassembly_at at the new instruction pointer (cip) with count: 10. 9. Call stack_get_trace for the new call stack.

Phase 3: Diff Analysis

  1. Call context_compare_snapshots with both snapshots.
  2. Additionally analyze: register changes (which and by how much), CPU flag changes (ZF, CF, SF, OF), stack growth/shrink, memory changes.
  3. Use eval_expression to compute derived values if needed (e.g., [csp+8] to inspect stack slots that changed).

Report

=== Execution State Comparison ===

Snapshot A: 0x... ([symbol A])
Snapshot B: 0x... ([symbol B])

Register Changes:
Register    Snapshot A          Snapshot B          Delta
RAX/EAX     0x...               0x...               +0x...
RCX/ECX     0x...               0x...               (cleared)
RSP/ESP     0x...               0x...               -0x10

Flag Changes:
Flag    A -> B
ZF      0 -> 1  (result was zero)

Stack Changes:
  [new/removed values]

Memory Changes:
  [if captured]

Summary:
  [natural language description of what happened between the two points]

Read the full file on GitHub · 66 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. 12d ago First seen · 66 lines · 8 tokens per session scan A 67dd98eb7cb5

Subscribe to this mod's changes

compare-state is a command published in the GitHub repository SetsunaYukiOvO/x64dbg-mcp (463 stars, last pushed 22d ago), licensed MIT. It adds 8 tokens to every session and 535 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.