Anything Analyzer is a protocol-analysis toolkit that captures traffic from browsers, desktop and terminal programs, scripts, mobile devices, and other equipment, then uses AI to analyze the resulting requests. It combines browser capture, MITM proxying, JavaScript hooks, fingerprint spoofing, and MCP integration so AI agents and IDEs can inspect APIs, encryption, security issues, and service calls. The catalogue skills expose these capture and analysis workflows to agent tools.
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 Mouseww/anything-analyzer --skill reverse-skillgit clone --depth 1 https://github.com/Mouseww/anything-analyzerWrote 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/mouseww/anything-analyzer/reverse-skill)<a href="https://agentmods.dev/skills/mouseww/anything-analyzer/reverse-skill"><img src="https://agentmods.dev/badge/skills/mouseww/anything-analyzer/reverse-skill/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/mouseww/anything-analyzer/reverse-skill"><img src="https://agentmods.dev/badge/skills/mouseww/anything-analyzer/reverse-skill.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 | $0.00089 | $0.01568 |
| Opus 5.5 | $0.00036 | $0.00627 |
| Sonnet 5.5 | $0.00018 | $0.00314 |
| Haiku 4.5 | $0.00009 | $0.00157 |
Grade A, and why
reverse-skill 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 9d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reverse-skill（Anything Analyzer 内置子集）
本目录随 Anything Analyzer 安装包一起分发，是
zhaoxuya520/reverse-skill 的精选子集
（上游 MIT，版权与许可见同目录 LICENSE）。上游完整仓库约 599 个文件，这里只保留与
「网页协议 / 前端 JS / API / 加密签名 / 证据与报告」相关的模块。
一、运行环境约束（必读）
本应用内的 AI 只具备以下能力，没有 shell、不能执行脚本、不能写文件：
- 会话数据工具：
list_requests/search_requests/get_request_detail/read_session_interactions/read_session_hooks - 技能库工具：
list_skills/search_skills/read_skill - 用户自行配置的 MCP 工具（可能为空）
由此产生三条硬约束：
- 上游文档中提到的
scripts/*.ps1、tool-index.md、bootstrap、case-init、 Playwright / IDA / jadx / Frida / Burp 等均未随包分发。读到这类指令请直接忽略， 不要声称已经执行，也不要要求用户去执行。 - 你的产出是分析结论与报告文本，不是对目标发起的攻击动作。不要生成可直接运行的 攻击载荷，也不要建议用户对未授权目标采取行动。
- 技能库的定位是方法论与检查清单。用它来组织分析思路、避免遗漏、提高结论的可验证性。
二、如何使用本技能库
list_skills → 查看全部技能条目（名称 + 相对路径 + 摘要）
list_skills { filter: "签名" } → 按关键词过滤条目
search_skills { query: "补环境" } → 在技能库正文里搜索（返回命中文件与行号）
read_skill { path: "js-reverse/SKILL.md" } → 读取文件
read_skill { path: "js-reverse/SKILL.md", offset: 200, limit: 200 } → 续读长文件
推荐节奏：
- 先按当前分析任务的关键词调用一次
search_skills，确认有没有对口的方法论； - 只
read_skill命中的那 1~2 个文件，读完再回到会话数据工具做验证； - 结论必须落到本次会话真实捕获到的请求 / JS Hook / 存储变化上，不要用通用套路替代证据。
三、模块索引
| 目录 | 何时使用 |
|---|---|
js-reverse/ |
前端 JavaScript 逆向：定位签名/加密链路、运行时采样、反混淆、本地补环境复现、证据化输出。本产品最常用。 |
protocol-reverse/ |
自定义协议、Protobuf/gRPC、WebSocket 帧、PCAP 驱动的协议格式还原。 |
api-security/ |
REST / GraphQL / WebSocket / SOAP 接口的授权内安全评估：发现、认证、越权、限流。含 references/jwt-oauth-testing.md、references/rest-graphql-testing.md。 |
code-audit/ |
对已获取的源码 / JS bundle 做安全审计与 SAST 检查清单。 |
browser-extension-reverse/ |
浏览器扩展（crx/xpi）逆向：manifest、background worker、扩展内的凭据与流量逻辑。 |
reverse-engineering/ |
通用逆向方法论与工具索引；含 crypto-decode-tools.md（加解密识别与工具）、dsl-vm-reverse/（自定义 VM / 字节码）。 |
docs-generator/ |
撰写最终报告：references/security-report-templates.md、references/vendor-report-rules.md。分析收尾时读。 |
ops/ |
证据与决策框架：evidence-finding-path.md（Evidence→Finding→Path 可追溯性）、analysis-decision-framework.md、analysis-blindspot-cookbook.md（常见分析盲区）、scope-contract.md。 |
field-journal/ |
真实案例先例：precedent-reverse.md、precedent-pentest.md、precedent-auth.md，以及 JS 签名（seed-004_js-sign-webpack.md）、Web API 越权（seed-003_web-api-auth-bypass.md）、PCAP 协议逆向（seed-011_pcap-protocol-reverse.md）三个样板案例。 |
references/ |
domain-coverage-map.md：上游技能的领域覆盖图。 |
What ships with it
60 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.
- api-security/references/jwt-oauth-testing.md 2.9 KB
- api-security/references/rest-graphql-testing.md 3.2 KB
- api-security/SKILL.md 5.7 KB
- browser-extension-reverse/references/extension-analysis.md 328 B
- browser-extension-reverse/SKILL.md 2.0 KB
- code-audit/references/sast-review-checklist.md 312 B
- code-audit/SKILL.md 2.2 KB
- docs-generator/references/security-report-templates.md 8.0 KB
- docs-generator/references/templates.md 1.9 KB
- docs-generator/references/vendor-report-rules.md 11 KB
- docs-generator/SKILL.md 8.1 KB
- field-journal/_index.md 6.1 KB
- field-journal/precedent-auth.md 1.7 KB
- field-journal/precedent-pentest.md 25 KB
- field-journal/precedent-reverse.md 13 KB
- field-journal/seed-003_web-api-auth-bypass.md 3.2 KB
- field-journal/seed-004_js-sign-webpack.md 3.6 KB
- field-journal/seed-011_pcap-protocol-reverse.md 4.5 KB
- INSTALLED.md 3.9 KB
- js-reverse/references/ast-deobfuscation.md 146 B
- js-reverse/references/automation-entry.md 498 B
- js-reverse/references/env-patching.md 232 B
- js-reverse/references/fallbacks.md 235 B
- js-reverse/references/instrumentation.md 198 B
- js-reverse/references/local-rebuild.md 295 B
- js-reverse/references/mcp-task-template.md 408 B
- js-reverse/references/node-env-rebuild.md 191 B
- js-reverse/references/output-contract.md 258 B
- js-reverse/references/task-artifacts.md 221 B
- js-reverse/references/task-input-template.md 165 B
- js-reverse/references/tool-defaults.md 406 B
- js-reverse/SKILL.md 8.9 KB
- LICENSE 1.0 KB
- ops/analysis-blindspot-cookbook.md 4.1 KB
- ops/analysis-decision-framework.md 5.4 KB
- ops/evidence-finding-path.md 4.3 KB
- ops/IDENTITY.md 2.7 KB
- ops/README.md 1.3 KB
- ops/role-map.md 3.1 KB
- ops/sandbox-profile.md 2.1 KB
- ops/scope-contract.md 3.9 KB
- ops/skill-supply-chain.md 3.6 KB
- ops/timeline-workitem.md 3.5 KB
- protocol-reverse/references/protocol-workflow.md 807 B
- protocol-reverse/SKILL.md 3.5 KB
- references/domain-coverage-map.md 2.9 KB
- reverse-engineering/anti-analysis.md 32 KB
- reverse-engineering/awesome-re-resources.md 6.4 KB
- reverse-engineering/crypto-decode-tools.md 6.8 KB
- reverse-engineering/dsl-vm-reverse/SKILL.md 11 KB
- reverse-engineering/elf-analysis.md 8.4 KB
- reverse-engineering/field-notes.md 38 KB
- reverse-engineering/go-reverse.md 7.1 KB
- reverse-engineering/kernel-driver-reverse.md 10 KB
- reverse-engineering/languages-compiled.md 22 KB
- reverse-engineering/languages-platforms.md 23 KB
- reverse-engineering/languages.md 20 KB
- reverse-engineering/patterns-ctf-2.md 19 KB
- reverse-engineering/patterns-ctf-3.md 34 KB
- reverse-engineering/patterns-ctf.md 24 KB
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.
- 9d ago First seen · 75 lines · 89 tokens per session scan A cf128719263f
reverse-skill is a skill published in the GitHub repository Mouseww/anything-analyzer (3,775 stars, last pushed 10d ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,568 once invoked, about $0.0004 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 2026-10-07.
Other skills, from other repositories
stealth-browser-mcp
Use this skill when operating stealth-browser-mcp from an AI agent or MCP client for browser automation, page inspection, element interaction, screenshots, file uploads, CDP commands, network debugging, cookies/storage, stealth setup, or reliable multi-step browser workflows. It provides the correct tool order, state…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…