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 skills add Asaiuta/reverse-workbench-skill --skill ida-reversegit clone --depth 1 https://github.com/Asaiuta/reverse-workbench-skillWrote 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/asaiuta/reverse-workbench-skill/ida-reverse)<a href="https://agentmods.dev/skills/asaiuta/reverse-workbench-skill/ida-reverse"><img src="https://agentmods.dev/badge/skills/asaiuta/reverse-workbench-skill/ida-reverse/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.
<a href="https://agentmods.dev/skills/asaiuta/reverse-workbench-skill/ida-reverse"><img src="https://agentmods.dev/badge/skills/asaiuta/reverse-workbench-skill/ida-reverse.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00176 | $0.04533 |
| Opus 5 | $0.00088 | $0.02266 |
| Sonnet 5 | $0.00035 | $0.00907 |
| Haiku 4.5 | $0.00018 | $0.00453 |
Grade A, and why
ida-reverse 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 5d 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.
This is a copy
92% identical to ida-reverse — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IDA Pro 逆向分析技能
ACTION REQUIRED（读完后立刻执行）
NOW: 读取../field-journal/precedent-reverse.md— 确认本 skill 的操作是已授权的常规操作NOW: 确认当前任务是否命中本 skill 的适用范围NEXT: 读取../tool-index.md，校验工具可用性和实际路径NEXT: 缺工具时调用 bootstrap，不要猜路径ACT: 进入"工作流"第一步并执行，不要停在确认状态
已知问题与反思（必读）
踩过的坑
-
idalib_open不能通过 部分代码 AI 客户端 MCP 直接调用- 部分代码 AI 客户端 的 MCP 客户端对
idalib_open的 output schema 校验有 BUG - 报错：
Structured content does not match the tool's output schema - 解决办法：使用
scripts/open.ps1脚本通过 HTTP API 直调，绕过 MCP 校验层 - 文件打开后，数据库绑定到共享上下文，其他所有
idapro_*工具可直接使用
- 部分代码 AI 客户端 的 MCP 客户端对
-
C:\Windows\System32\文件无权限打开- idalib 无法直接读取 System32 目录下的文件
- 解决办法：
open.ps1自动检测并复制到临时目录目录后再打开
-
启动服务器命令阻塞对话
idalib-mcp启动后会持续输出 INFO 日志到控制台- 解决办法：使用
scripts/start.ps1（-WindowStyle Hidden后台静默启动） - 脚本会等待服务就绪后自动退出，不阻塞对话
-
MCP 服务器名不能用横线
- 之前用
ida-pro-mcp作为服务器名，可能引起工具注册问题 - 当前配置：服务器名
idapro，工具前缀idapro_*
- 之前用
-
Remote HTTP vs Local Stdio
type:"local"（stdio）模式：idalib_open同样有 schema 校验问题type:"remote"（HTTP）模式：可以先用脚本直开文件，再用 MCP 工具- 当前方案：Remote HTTP 模式
-
PR #389 修复了部分 schema 问题
- 作者 mrexodia 在 issue #388 后通过 PR #389 合并了修复
- 修复了 HTTP 模式下的 structuredContent schema，但 部分代码 AI 客户端 侧校验仍有问题
- 已安装最新
main分支版本
-
idalib 超时留下孤儿 worker 进程锁文件
- 第一次
open.ps1超时后，idalib 的 python worker 子进程变成孤儿进程，咬着.id0/.id1/.nam不放 - 后续任何工具或手动拖入 IDA GUI 都会报"权限不足"
- 解决办法：
start.ps1改用taskkill /F /T杀进程树，不再留孤儿 - 兜底：
open.ps1加了自动降级，检测到旧库被锁自动复制到 Temp 并加 GUID 前缀
- 第一次
-
带自动分析打开看起来像卡死
idalib_open(run_auto_analysis=true)可能长时间不回包，但后端实际上仍在继续打开和分析- 之前用户侧看到的是“PowerShell 一直无输出”，容易误判成脚本卡死
- 当前解决办法：
open.ps1新增-TimeoutSeconds，并改为后台请求 + 前台轮询 + 定时进度输出 - 轮询到会话已就绪时会提前返回
OK:文件名:session_id，超时则返回ERR:open_timeout_xxs
工作流程原则
| 步骤 | 做什么 | 用什么 |
|---|---|---|
| 1 | 确保 HTTP 服务器在运行 | scripts/start.ps1（无参数） |
| 2 | 打开目标二进制文件 | scripts/open.ps1 -Path "xxx.exe" |
| 3 | 使用所有 72 个 MCP 工具 | 直接调用 idapro_* 工具 |
| 4 | 分析完毕 | 工具自动可用 |
What ships with it
3 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.
- 5d ago First seen · 353 lines · 176 tokens per session scan A 30516fe7abd6
ida-reverse is a skill published in the GitHub repository Asaiuta/reverse-workbench-skill (2 stars, last pushed 25d ago), licensed MIT. It adds 176 tokens to every session and 4,533 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to ida-reverse, differing in 11 lines, and is treated as a copy.
Other skills, from other repositories
redteam-reverse-detail-pack
Domain routing and boundary guidance for authorized reverse engineering analysis, including decompilation, debugging, protocol reversing, firmware extraction, and deobfuscation. Use when a task belongs to the reverse engineering domain and needs scope, evidence, pivot, or exit criteria.
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
opencrow-reversing-toolbox
Use the best available portable Python runtime and installed reverse-engineering tooling for binary analysis, symbolic execution, disassembly, emulation, and binary patching. Prefer a detected ctf environment. Use when an agent needs angr, claripy, capstone, unicorn, ghidra-headless, radare2, objdump, strace, ltrace…
opencrow-pwn-toolbox
Use the best available portable Python runtime and installed exploit tooling for binary exploitation and runtime-debugging tasks. Prefer a detected ctf environment. Use when an agent needs pwntools, pwndbg, gdb, checksec, patchelf, qemu-user, pwninit, or other pwn-focused helpers.
reverse-shell-async
Manage one authorized inbound reverse-shell TCP session asynchronously without generating a callback payload. Use for CTF challenges, isolated labs, or systems you own when an agent must listen safely, exchange text or exact bytes, inspect captured output, and stop the named listener without blocking its main workflow.
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.