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/2233admin/reverse-skill-evolver/ida-reversenpx skills add 2233admin/reverse-skill-evolver --skill ida-reversegit clone --depth 1 https://github.com/2233admin/reverse-skill-evolverWhat 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 | $0.00178 | $0.03014 |
| Opus 5 | $0.00089 | $0.01507 |
| Sonnet 5 | $0.00036 | $0.00603 |
| Haiku 4.5 | $0.00018 | $0.00301 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 220 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
当前调用边界（必读）
踩过的坑
-
原生 MCP 与 CLI 使用同一条真实链路
- Codex 注册名为
idapro，地址默认是http://127.0.0.1:13337/mcp - 原生 MCP 适合代理直接调工具；Python 命令
reverse-skill适合登录安装、诊断和人工操作 - CLI 先按
2026-07-28调用server/discover；现代服务使用逐请求元数据，旧服务才降级到initialize/notifications/initialized和Mcp-Session-Id
- Codex 注册名为
-
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：
reverse-skill open自动检测并复制到临时目录后再打开
-
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
reverse-skill start；Python 用无窗口后台进程启动服务 - 命令会等待服务就绪后自动退出，不阻塞对话
-
MCP 注册名固定为
idapro- 服务器自身名称可以是
ida-pro-mcp；Codex 侧统一使用短注册名idapro - 运行
reverse-skill register，不要手工漂移配置文件
- 服务器自身名称可以是
-
传输固定为 Streamable HTTP
- 当前方案不使用 stdio，IDA CLI 也不经过 PowerShell
- 真正链路是
reverse-skill → HTTP MCP → idalib-mcp.exe → IDA
-
协议版本必须协商，不能写死服务端版本
- 客户端优先使用已发布版
2026-07-28的逐请求_meta，并镜像MCP-Protocol-Version/Mcp-Method/Mcp-Name/Mcp-Param-*头 - 遇到非现代响应才进入 legacy 初始化，接受
2025-11-25、2025-06-18或2025-03-26；status必须明确显示era - 现代协议没有协议会话；IDA database ID 是应用层显式句柄，不等同于
Mcp-Session-Id - MRTR 的
requestState必须原样回传且重试使用新的 JSON-RPC id；CLI 用--input-responses-json/--request-state显式完成该步骤 - 规范映射、双时代流程和本机验证见
references/mcp-2026-07-28-dual-era.md
- 客户端优先使用已发布版
-
健康服务不能为了“重启”被误杀
reverse-skill start先完成 MCP 初始化和tools/list健康检查- 服务健康时原样复用；只有显式传入
--replace-stale时，才清理陈旧idalib-mcp进程树后启动新服务
-
打开和分析可能是长请求
idb_open(run_auto_analysis=true)会等待 IDA 分析，应按样本规模设置根选项--timeout- 超时是明确失败，不用吞错、盲重试或伪造成功会话
工作流程原则
| 步骤 | 做什么 | 用什么 |
|---|---|---|
| 1 | 注册并检查 Codex MCP | reverse-skill register、status |
| 2 | 确保 HTTP 服务在运行 | reverse-skill start |
| 3 | 打开目标二进制文件 | reverse-skill open "xxx.exe" |
| 4 | 调用动态发现的工具 | 原生 idapro MCP，或 reverse-skill call |
| 5 | 分析完毕 | reverse-skill close <session-id> |
Python CLI
安装入口：<repo-root>\pyproject.toml；源码入口：python -m reverse_skill。
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.
- 2d ago First seen · 220 lines · 178 tokens per session scan A 7d481173d64c
ida-reverse is a skill published in the GitHub repository 2233admin/reverse-skill-evolver (13 stars, last pushed 22d ago), licensed MIT. It adds 178 tokens to every session and 3,014 once invoked, about $0.0009 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…