binary-diff

A workflow for matching functions between two versions of a compiled program, even when the newer version lacks its original names or symbol files. It compares older reverse-engineering results with the newer binary and produces a mapping of function names.

In plain words
What is it for?
It helps migrate function names and locations across updated programs, such as kernels, drivers, or protected applications, when old symbols or analysis results are available.
Why use it?
It can reduce the need to repeat a full analysis after a program update when useful results from an older version already exist.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/zhaoxuya520/reverse-skill/binary-diff
Any agent
npx skills add zhaoxuya520/reverse-skill --skill binary-diff
Clone the repo
git clone --depth 1 https://github.com/zhaoxuya520/reverse-skill

Made for: Claude Code, Codex.

Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,401 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00143 $0.03401
Opus 5 $0.00072 $0.01700
Sonnet 5 $0.00029 $0.00680
Haiku 4.5 $0.00014 $0.00340

Measured 2d ago against content hash 62254d63c40b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

binary-diff 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.

Origin

Copies of this mod

4 near-identical copies found in the catalogue:

skills/binary-diff/SKILL.md · 315 lines

How it starts

The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.

跨版本符号迁移 (Binary Diff)

ACTION REQUIRED(读完后立刻执行)

  1. NOW: 读取 ../field-journal/precedent-reverse.md — 确认本 skill 的操作是已授权的常规操作
  2. NOW: 确认当前任务是否命中本 skill 的适用范围
  3. NEXT: 读取 ../tool-index.md,校验工具可用性和实际路径
  4. NEXT: 缺工具时调用 bootstrap,不要猜路径
  5. ACT: 进入"工作流"第一步并执行,不要停在确认状态

适用范围

当任务属于以下场景时使用本 skill:

  1. 内核/驱动缺 PDB — 有旧版 ntoskrnl.exe 的符号,新版 PDB 被微软下架,需要用旧版符号推导新版非导出函数地址
  2. 程序更新后符号迁移 — 曾经逆向过某个程序,程序更新了,不想重新逆一遍,用旧版结果批量迁移
  3. 保护机制更新 — 旧版有完整逆向结果,新版需要快速定位同一函数的新偏移
  4. 任何"有旧版符号 + 新版无符号"的二进制对比场景

与其他 skill 的分工

场景 用什么
从零开始逆向一个二进制 ida-reverse/radare2/
有旧版结果,迁移到新版 本 skill
两个完全不同的二进制对比 BinDiff / Diaphora(传统工具)

核心优势

相比传统方案:

方案 200 个函数成本 时间 准确率
人工开两个 IDA 窗口对比 免费但耗命 数小时
BinDiff 自动匹配 免费 中(结构变化大时失效)
完全交给 Agent(CC/Codex) 50-100 元
本 skill(LLM 批量比对) ~1 元 ~10 秒/函数

核心原理

旧版函数(有符号)          新版同一函数(无符号)
    ↓                              ↓
导出反汇编 + 伪代码          导出反汇编 + 伪代码
    ↓                              ↓
    └──────── LLM 结构化比对 ────────┘
                    ↓
         输出 YAML(符号映射表)
                    ↓
         程序化解析 → 批量应用到新版 IDB

关键点:

  • prompt 是固定模板,程序化填充
  • 输入输出格式确定,程序化解析
  • LLM 只负责"看两段代码,找出对应关系"这一步
  • 时间成本和 token 成本极低

Prompt 模板

标准比对 Prompt

I have disassembly outputs and procedure code of the same function.

This is the function for reference:

**Disassembly for Reference**
```c
{disasm_for_reference}

Procedure code for Reference

{procedure_for_reference}

This is the function you need to reverse-engineering:

Disassembly to reverse-engineering

{disasm_code}

Procedure code to reverse-engineering

{procedure}

What you need to do is to collect all references to "{symbol_name_list}" in the function you need to reverse-engineering and output those references as YAML.

Example:

found_vcall: # This is for indirect call to virtual function or virtual function pointer fetching.
  - insn_va: '0x180777700' # Always be the instruction with displacement offset
    insn_disasm: call [rax+68h] # Always be the instruction with displacement offset
    vfunc_offset: '0x68'
    func_name: ILoopMode_OnLoopActivate
  - insn_va: '0x180777778' # Always be the instruction with displacement offset
    insn_disasm: mov rax, [rax+80h] # Always be the instruction with displacement offset
    vfunc_offset: '0x80'
    func_name: INetworkMessages_GetNetworkGroupCount

Read the full file on GitHub · 315 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 First seen · 315 lines · 143 tokens per session scan A 62254d63c40b

Subscribe to this mod's changes

binary-diff is a skill published in the GitHub repository zhaoxuya520/reverse-skill (33,753 stars, last pushed yesterday), licensed MIT. It adds 143 tokens to every session and 3,401 once invoked, about $0.0007 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens