Borrowing it
Nothing to install: this file belongs to 2233admin/reverse-skill-evolver. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/2233admin/reverse-skill-evolver/main/.kiro/steering/reverse-routing.mdgit clone --depth 1 https://github.com/2233admin/reverse-skill-evolverWrote 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/instructions/2233admin/reverse-skill-evolver/reverse-routing)<a href="https://agentmods.dev/instructions/2233admin/reverse-skill-evolver/reverse-routing"><img src="https://agentmods.dev/badge/instructions/2233admin/reverse-skill-evolver/reverse-routing/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/instructions/2233admin/reverse-skill-evolver/reverse-routing"><img src="https://agentmods.dev/badge/instructions/2233admin/reverse-skill-evolver/reverse-routing.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 | $0.00986 | $0.00986 |
| Opus 5.5 | $0.00394 | $0.00394 |
| Sonnet 5.5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
reverse-skill-evolver reverse-routing.md 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.
What it actually says
逆向技能路由 — 自动触发规则
当用户的消息包含以下任意关键词时,必须在执行任务前先完成路由流程:
触发词: 逆向、反编译、IDA、radare2、Frida、Hook、APK、二进制、ELF、PE、so、dll、签名、加密参数、CTF、渗透、Nmap、漏洞、还原源码、还原、反汇编、脱壳、解压、payload、shellcode、内核模块、驱动加载、源码还原、渗透测试、红队、HW、攻防演练、打点、SQL注入、SQLMap、目录爆破、FFUF、密码破解、Hashcat、Hydra、Metasploit、Nuclei、端口扫描、SRC、Bug Bounty、WAF bypass、符号迁移、bindiff、浏览器自动化、Playwright、JS逆向、jshookmcp、CDP、SourceMap、抓包、HTTP捕获、anything-analyzer、画图、流程图、Mermaid、写报告、writeup、Go逆向、Rust逆向、固件、IoT、binwalk、unblob、Firmadyne、EMBA、UBI、squashfs、UART、JTAG、AFL++、boofuzz、恶意软件、YARA、内网渗透、横向移动、域渗透、BloodHound、权限提升、SUID、Mimikatz、Kerberoasting、C2、Cobalt Strike、近源渗透、BadUSB、EDR绕过、AV bypass、免杀、unhook、direct syscall、indirect syscall、Hells Gate、SysWhispers、ETW patch、AMSI patch、call stack spoofing、MITRE T1562、pe-sieve、CrowdStrike、Defender bypass、SentinelOne、钓鱼、社工、供应链攻击、攻击链、完整渗透、攻击面评估、后渗透、Pentest Swarm、pentestswarm、HexStrike、MetasploitMCP、mcp-kali-server、SSTI、SSTImap、XSS、XSStrike、WordPress、WPProbe、AdaptixC2、Fluxion、Coercer、NetExec、evil-winrm、Certipy、Responder、wfuzz、Wireshark、BurpSuite、BurpMCP、Burp代理、Intruder爆破、Repeater重放、Collaborator、代理历史、GEF、GDB、pwn、栈溢出、堆溢出、ROP、ret2libc、one_gadget、libc-database、tcache、fastbin、kernel pwn、SMEP、SMAP、KASLR、modprobe_path、commit_creds、pwntools、pwndbg、N-day、Nday、补丁差分、patch diff、CVE复现、ghidriff、Diaphora、DeepDiff、Patch Tuesday
触发后必须执行的流程
- 读取路由表: 读
skills/routing.md,按目标类型/用户意图匹配子 skill - 查经验: 读
skills/field-journal/_index.md,看有没有同类历史经验可复用 - 确认工具: 读
skills/tool-index.md(如果存在),确认本机工具可用性 - IDA MCP 端口: 不要硬编码 13337,扫描 13337-13350 找活跃端口(多实例递增)
- 执行任务: 进入对应 skill 的工作流
- 任务完成后: 回写
skills/field-journal/,更新_index.md
IDA MCP 注意事项
- IDA 每次打开新文件会分配新端口(13337→13338→13339...)
- 检查方法: 扫描端口 或 读
%APPDATA%\Hex-Rays\IDA Pro\mcp\instances\下的 JSON - 测试案例目录有共享工具:
测试案例/mcp_call.py(自动发现端口)
禁止行为
- ❌ 不要跳过路由直接开始逆向
- ❌ 不要硬编码 IDA MCP 端口
- ❌ 不要跳过 field-journal 查询
- ❌ 任务完成后不要跳过经验回写
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 · 32 lines · 986 tokens per session scan A 57772a679df3
reverse-skill-evolver reverse-routing.md is an instructions file published in the GitHub repository 2233admin/reverse-skill-evolver (17 stars, last pushed today), licensed MIT. It adds 986 tokens to every session, about $0.0039 per session on Opus 5.5. 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 2026-10-11.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).