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.
npx agentmods add skills/dslsdzc/rev-skills/re-binaryninjanpx skills add dslsdzc/rev-skills --skill re-binaryninjagit clone --depth 1 https://github.com/dslsdzc/rev-skillsWrote 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.
[](https://agentmods.dev/skills/dslsdzc/rev-skills/re-binaryninja)<a href="https://agentmods.dev/skills/dslsdzc/rev-skills/re-binaryninja"><img src="https://agentmods.dev/badge/skills/dslsdzc/rev-skills/re-binaryninja.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00034 | $0.03480 |
| Opus 5 | $0.00017 | $0.01740 |
| Sonnet 5 | $0.00007 | $0.00696 |
| Haiku 4.5 | $0.00003 | $0.00348 |
Grade A, and why
re-binaryninja 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Binary Ninja 逆向工作流
何时使用 / 何时不用
- 用：需要 MLIL 中间语言（比裸反汇编可读得多）阅读函数逻辑；Python 脚本自动化标注/批处理；按预算选型（个人版/商业版）
- 用：需要 DFG 数据流图（寄存器/常量传播路径可视化）追踪单条数据的流向（密钥、标志位）
- 用：多架构目标（x86/ARM/MIPS/RISC-V/PowerPC 等常见架构均支持，移动/嵌入式目标可直接分析）
- 用：
RE_DECOMPILER=binaryninja场景下作为反编译器 - 不用：已有 Ghidra/IDA 工作流且无选型动机（按
RE_DECOMPILER会话变量，[[re-ghidra]] 默认） - 不用：纯命令行快速分析（[[re-radare2]] 更轻）；无头批处理最简场景（[[re-ghidra]] analyzeHeadless 生态更成熟）
- 不用：动态调试为主的目标（BN 内置调试器处于实验阶段——调试走 [[re-gdb]] / [[re-x64dbg]] / [[re-lldb]]）
- 不用：个人版做大规模无头自动化（headless 是商业版能力，见 [[gotchas]]）
工具准备
参考 [[platform-tips]]——Binary Ninja 静态分析免沙箱；脚本触发动态执行时默认沙箱内。
Binary Ninja（商业，有个人版）
- 下载/购买: 官网 binary.ninja（Commercial / Personal 个人版；个人版仅限个人用途，自动化与部分功能按版本受限）
- Windows: 安装器直接运行；macOS:
brew install --cask binary-ninja（社区 cask，需已有 license）；Linux: 官网 tar 包解压运行./binaryninja - 容器格式: 直接导入 PE/ELF/Mach-O/Dalvik/固件 ROM 等（不需要单独解包步骤）；带壳目标例外（壳段未解密，先脱壳）
- 验证: 打开任意样本完成自动分析，
Functions面板有函数列表；Options > About显示 license 类型 - Linux 无图形环境: GUI 版需要 X 显示（
xvfb-run ./binaryninja可临时跑）；批量任务直接走 headless（商业版），headless 不需要显示器 - 版本差异: 3.x/4.x 间 Python API 大体兼容但个别函数签名变化——脚本依赖先看
core_version()与发行说明（见 [[gotchas]]）
binaryninja Python API
- 安装: Binary Ninja 安装目录下运行
python install_api.py（把 API 注册进 Python 环境；PyPI 无 binaryninja 包，pip install binaryninja会失败） - 安装脚本会检测/提示匹配的 Python 版本——版本不匹配时脚本报错或注册失败，按提示换 Python 版本
- 验证:
python3 -c "import binaryninja; print(binaryninja.core_version())"输出与软件版本一致的版本号 - 无头批处理（商业版）: 没有
binaryninja-headless可执行文件——正路是install_api.py注册后直接写脚本binaryninja.load()（见 [[commands]] 序列 2）；headless license 走官方独立下载包（无 GUI，仅 headless license 可下载）
操作步骤
-
导入与分析：
File > Open选样本 → 自动分析（底部进度条）→ 左侧Functions/Data/References视图确认分析结果- 确认: 入口函数（entry）被识别、导入表（
Imports视图）有内容、字符串（Strings视图）可见 - 分析异常（函数少/字符串乱）→ 可能带壳，先 [[re-packer-id]] / [[re-anti-analysis]]
- 分析选项:
Options > Analysis勾选/关闭 pass——首次导入大文件或带混淆样本时先看这里，默认全开会慢
-
MLIL 阅读（IL 视图切换）：
- 双击函数进入反编译视图（默认 HLIL 高语言 IL）；
i在反汇编/LLIL/MLIL/HLIL 间循环，或右下角Options菜单选 IL 级别 - MLIL 特点: 变量显式化（
rax = rax ^ 0xdeadbeef）、类型恢复、条件跳转语义化——比裸反汇编可读，重点函数先看 MLIL 再下结论 - MLIL 示例（反汇编 vs MLIL）：
cmp eax, 0x1337 / jne L1 / mov byte [rdi], 1 / jmp L2 / L1: mov byte [rdi], 0 / L2: ...→ MLIL 直接呈现if (rax == 0x1337) *(uint8_t*)rdi = 1; else *(uint8_t*)rdi = 0;——读逻辑不用逐条跟跳转 - 反编译不清晰时降级: MLIL → LLIL（
View > IL > LLIL，低语言 IL，保留指令级细节）→ 反汇编（Space/汇编视图）逐层核对 - 注意:
m键在 Binary Ninja 里是「整数应用枚举显示」，不是 MLIL 切换——切 IL 用i
- 双击函数进入反编译视图（默认 HLIL 高语言 IL）；
What ships with it
2 files 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.
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.
- 6d ago First seen · 119 lines · 34 tokens per session scan A 4dd3c319c376
re-binaryninja is a skill published in the GitHub repository dslsdzc/rev-skills (40 stars, last pushed 8d ago), licensed Apache-2.0. It adds 34 tokens to every session and 3,480 once invoked, about $0.0002 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.
Other skills, from other repositories
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
deobfuscating-powershell-obfuscated-malware
Systematically deobfuscates multi-layer PowerShell malware using AST analysis, dynamic tracing, and tools like PSDecode and PowerDecode to reveal hidden payloads and C2 infrastructure. Use during incident response or malware analysis when a PowerShell script is obfuscated with encoding, string manipulation, or…
conducting-malware-incident-response
Respond to malware infections across enterprise endpoints by identifying the malware family, determining infection vectors, assessing spread, and executing containment, analysis, eradication, and recovery procedures aligned to MITRE ATT&CK. Use when responding to a confirmed or suspected malware infection, including…
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…
analyzing-network-covert-channels-in-malware
Detect and analyze covert communication channels used by malware, including DNS tunneling, ICMP exfiltration, steganographic HTTP, and other protocol abuse used for C2 and data exfiltration. Use when investigating suspicious DNS/ICMP/HTTP traffic patterns, hunting for hidden C2 channels in network captures, or…
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware using Ghidra with specialized scripts for function recovery, string extraction, and type reconstruction in stripped Go binaries.