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 NoOne-hub/JSReverser-MCP --skill jsreverser-mcp-playbookgit clone --depth 1 https://github.com/NoOne-hub/JSReverser-MCPWrote 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/noone-hub/jsreverser-mcp/jsreverser-mcp-playbook)<a href="https://agentmods.dev/skills/noone-hub/jsreverser-mcp/jsreverser-mcp-playbook"><img src="https://agentmods.dev/badge/skills/noone-hub/jsreverser-mcp/jsreverser-mcp-playbook/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/noone-hub/jsreverser-mcp/jsreverser-mcp-playbook"><img src="https://agentmods.dev/badge/skills/noone-hub/jsreverser-mcp/jsreverser-mcp-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00061 | $0.02298 |
| Opus 5 | $0.00030 | $0.01149 |
| Sonnet 5 | $0.00012 | $0.00460 |
| Haiku 4.5 | $0.00006 | $0.00230 |
Grade A, and why
jsreverser-mcp-playbook 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 13d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP 前端 JS 逆向作业规范
定位说明:
skills/jsreverser-mcp-playbook/references/*是 AI 快速执行版,用于任务中按需快速读取。docs/reference/*是 正式权威版,适合源码或已打包安装场景与仓库外部查阅。- 如果两者表述出现差异,以
docs/reference/*为准。
核心原则
Observe-firstHook-preferredBreakpoint-lastRebuild-orientedEvidence-firstTask-driven
先页面观察,再最小化采样,再做本地补环境,不要跳过取证直接猜环境。
目标场景
默认主场景是:
- 定位接口签名、加密参数、关键请求字段
- 在页面里确认哪个请求、哪个脚本、哪个函数参与参数生成
- 导出本地复现材料
- 在 Node 里按“代理 env log + first divergence + 最小因果单元”补环境跑通
- 跑通后再做 AST 去混淆、VMP 插桩或逻辑提纯
五阶段工作流
1. Observe
目标:
- 先确认目标请求、相关脚本、候选函数,不猜环境。
默认入口:
docs/reference/reverse-bootstrap.mdreferences/automation-entry.mdreferences/mcp-task-template.md
必须产出:
- 目标请求
- initiator 线索
- 可疑脚本 URL / scriptId
- 初始 task artifact
2. Capture
目标:
- 对目标请求做最小侵入采样,拿到参数样例、调用顺序、运行时证据。
规则:
- 优先 fetch/xhr hook
- 如果目标发生在首屏初始化、首个请求前参数装配、页面首次执行阶段,先用
inject_preload_script挂早期采样或补环境脚本 - 命中后先看 summary,再按需看 raw
- Hook 不足时再考虑断点
3. Rebuild
目标:
- 把页面证据导出为本地可迭代的 Node 复现工程。
参考:
references/local-rebuild.mdreferences/task-artifacts.md- 正式规范:
docs/reference/reverse-workflow.md
规则:
- 本地补环境必须以页面观测证据为依据
- 不允许空想式补
window/document/navigator/crypto/storage
4. Patch
目标:
- 按代理日志和
first divergence驱动补环境,直到本地脚本能稳定跑出目标参数。
规则:
- 先读代理 env log,再记录当前
first divergence - 一次只做一个补丁决策,不是机械地一次只改一个属性
- 一个补丁决策对应一个最小因果单元:值 / 函数壳 / 返回对象 / 最小对象契约
diff_env_requirements仅作辅助,不替代代理日志- 每次补丁后立即复测,并记录
first divergence是否前移 - 每次补丁都写入 task artifact
- 快速执行版看
references/env-patching.md,正式规范以docs/reference/env-patching.md为准
5. DeepDive
目标:
- 本地跑通后,再做去混淆、VMP、控制流还原、业务逻辑提纯。
规则:
- 如果当前任务只是出签名,这一阶段可以降级
- 如果要长期复用算法链路,这一阶段必须做
- 进入纯算法提纯阶段时,优先读取
docs/reference/pure-extraction.md
场景路由
Task-driven 工具路由
当 MCP 已暴露 reverse task 工作流工具时,默认优先按下面顺序选工具,而不是先读参数 workflow 文档:
- 新建任务
start_reverse_task
- 查状态 / 摘要 / timeline / compare / tag / update
manage_reverse_task
- 自动决定下一步并连续推进
orchestrate_reverse_task
- 一键跑“定位函数 -> 最小切片 -> pure 草稿 / port-ready 草稿”
run_reverse_agent
- 导出最少交付文件
export_portable_bundle
- 只查看参数蓝图 / 案例 workflow
get_parameter_workflowlist_parameter_workflowsrecommend_parameter_workflow
What ships with it
18 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.
- agents/openai.yaml 576 B
- references/ast-deobfuscation.md 122 B
- references/automation-entry.md 835 B
- references/cases/case-ast-deobfuscation.md 2.4 KB
- references/cases/case-signature-node-template.md 1.9 KB
- references/cases/case-window-honeypot.md 1.7 KB
- references/env-patching.md 618 B
- references/fallbacks.md 578 B
- references/instrumentation.md 198 B
- references/local-rebuild.md 852 B
- references/mcp-task-template.md 1.3 KB
- references/node-env-rebuild.md 180 B
- references/output-contract.md 344 B
- references/schemas/reverse-task-input.example.json 1.2 KB
- references/schemas/reverse-task-input.schema.json 4.7 KB
- references/task-artifacts.md 518 B
- references/task-input-template.md 744 B
- references/tool-defaults.md 367 B
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.
- 13d ago First seen · 240 lines · 61 tokens per session scan A 03a0e35d7c4b
jsreverser-mcp-playbook is a skill published in the GitHub repository NoOne-hub/JSReverser-MCP (1,006 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 2,298 once invoked, about $0.0003 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.