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/jacksontai2007/cc-unlock/android-reversenpx skills add JacksonTai2007/cc-unlock --skill android-reversegit clone --depth 1 https://github.com/JacksonTai2007/cc-unlockWrote 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/jacksontai2007/cc-unlock/android-reverse)<a href="https://agentmods.dev/skills/jacksontai2007/cc-unlock/android-reverse"><img src="https://agentmods.dev/badge/skills/jacksontai2007/cc-unlock/android-reverse.svg" alt="Measured on agentmods" 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 | $0.00214 | $0.03439 |
| Opus 5 | $0.00107 | $0.01720 |
| Sonnet 5 | $0.00043 | $0.00688 |
| Haiku 4.5 | $0.00021 | $0.00344 |
Grade A, and why
android-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 4d 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
100% identical to android-reverse — 0 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Android Reverse Framework
这是面向真实 Android 应用逆向交付的工作流入口,不是要求每次加载全部资料的知识库。
边界
- 只处理用户有权分析的 Android 应用、样本、设备和流量。
- 普通 Android 开发、系统/ROM/TEE 逆向、iOS 逆向和未授权利用不属于本技能。
- 不主动触发真实短信、支付、生产账号流量、数据清除或不可逆安装操作;需要时先说明影响并取得确认。
两种工作模式
快速分诊
范围窄、只需静态回答且不涉及动态取证或修改目标时,直接完成最小反编译、关键词搜索和证据结论。不要为了一个“有没有壳”问题创建完整状态机。
完整任务
出现以下任一情况时创建 task-local:T2-T5 交付、多轮续跑、动态取证、patch/重签、协议迁移、跨 Java/JNI/Native 建链或保护绕过。
node <SKILL_BASE>/tools/task/task-start.mjs <task-id>
启动协议见 docs/reference/reverse-bootstrap.md,契约字段见 references/task-contract-protocol.md。
核心原则
1. Observe before change
先确定目标、运行环境和第一条可证伪假设,再选择工具。工具可用不等于当前路线正确。
2. Artifact before claim
将要支撑根因、patch 或交付的事实,先写入 run/fixtures.json 或对应日志,再更新 route-state。聊天里的推断不能自动升级为证据。
3. Bridge before deep native
涉及 JNI 时,先建立 System.loadLibrary → JNI_OnLoad/RegisterNatives → Java↔Native 映射。没有桥接证据,不把任意 SO 函数语义提升为业务结论。
4. Verify before declare
- T2:脚本独立运行并命中目标数据。
- T3:no-op 重签基线通过,业务 patch 通过安装、冷启动和任务特定回归。
- T4:协议字段、算法和来源可回指。
- T5:独立实现对至少两组不同输入/输出向量通过
task-verify,最终运行时不依赖原 SO/RPC/Frida/ADB。
5. Goal-lock and stop-loss
每个阶段检查当前动作是否推进用户原始 objective。相同工具和策略连续三次失败、连续 tombstone 或没有新增证据时,先 retrospective 再 pivot;不要用细微脚本变体伪装新路线。
完整任务强制执行循环
“执行轮”指一个可证伪假设及其直接的 probe、patch 或 verify,不按聊天轮数或工具调用数量计算。完整任务的每个执行轮都按以下顺序推进:
- 回读
task.json::objective、当前 deliverable、相关 criteria 和state/route-state.json::execution,确认本轮动作直接缩短交付路径。 - 首次运行动态工具、连接设备或执行安装/重签/目标状态变更前,读取
references/environment-preflight.md,只检查当前路线和用户指定工具需要的能力;有清数据、真实账号流量或不可逆影响时先取得确认。 - 在首次领域操作前读取一个直接匹配的 playbook;后续出现新信号时只补读新命中的协议,不遍历全部资料。
- 写明可证伪假设、预期观察、失败判据和失败后的不同方向,再执行能区分假设的最小动作。
- 动作结束后先把原始证据写入任务目录。每次 probe、patch、verify 和工具预检,无论
success / failed / invalid / inconclusive / blocked,都立即运行task-record-attempt;聊天或report.md不能替代结构化尝试记录。 - 运行
task-advance。状态为ready-to-continue时执行nextExecutableAction,不要停在状态复述。 - 同一工具和策略连续三次失败、动态测试连续失败、tombstone 累积或多轮没有新增验收证据时,读取
references/failure-protocol.md,先写 retrospective,再选择与失败历史实质不同的 pivot。 - 在分诊/环境预检完成、获得改变路线的关键证据或 patch/verify 结果、pivot 前、暂停/上下文交接前更新
report.md;报告是阶段摘要,原始证据仍以run/产物为准。
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.
- agents/openai.yaml 1.1 KB
- artifacts/tasks/_TEMPLATE/core-task.json 2.4 KB
- artifacts/tasks/_TEMPLATE/core/core-task.json 2.4 KB
- artifacts/tasks/_TEMPLATE/core/logcat.jsonl 1 B
- artifacts/tasks/_TEMPLATE/core/memory-evidence.jsonl 1 B
- artifacts/tasks/_TEMPLATE/core/network.jsonl 1 B
- artifacts/tasks/_TEMPLATE/core/report.md 997 B
- artifacts/tasks/_TEMPLATE/core/run/closeout.mjs 928 B runs code
- artifacts/tasks/_TEMPLATE/core/run/fixtures.json 131 B
- artifacts/tasks/_TEMPLATE/core/run/run-local.mjs 178 B runs code
- artifacts/tasks/_TEMPLATE/core/run/validate-fixture.mjs 203 B runs code
- artifacts/tasks/_TEMPLATE/core/run/verify-once.mjs 1.6 KB runs code
- artifacts/tasks/_TEMPLATE/core/runtime-evidence.jsonl 1 B
- artifacts/tasks/_TEMPLATE/core/state/clues.md 355 B
- artifacts/tasks/_TEMPLATE/core/state/progress.md 513 B
- artifacts/tasks/_TEMPLATE/core/state/route-plan.md 1.9 KB
- artifacts/tasks/_TEMPLATE/core/state/route-state.json 3.4 KB
- artifacts/tasks/_TEMPLATE/core/static-evidence.jsonl 1 B
- artifacts/tasks/_TEMPLATE/core/task.json 2.4 KB
- artifacts/tasks/_TEMPLATE/core/timeline.jsonl 1 B
- artifacts/tasks/_TEMPLATE/extensions/anti-emulator-debug.json 207 B
- artifacts/tasks/_TEMPLATE/extensions/art-runtime.json 212 B
- artifacts/tasks/_TEMPLATE/extensions/call-flow.json 203 B
- artifacts/tasks/_TEMPLATE/extensions/crypto-protocol.json 248 B
- artifacts/tasks/_TEMPLATE/extensions/ctf.json 188 B
- artifacts/tasks/_TEMPLATE/extensions/deobfuscation.json 202 B
- artifacts/tasks/_TEMPLATE/extensions/device-fingerprint.json 212 B
- artifacts/tasks/_TEMPLATE/extensions/dex-loader.json 461 B
- artifacts/tasks/_TEMPLATE/extensions/framework-runtime.json 265 B
- artifacts/tasks/_TEMPLATE/extensions/hook-injection.json 204 B
- artifacts/tasks/_TEMPLATE/extensions/java-api.json 199 B
- artifacts/tasks/_TEMPLATE/extensions/jni-bridge.json 248 B
- artifacts/tasks/_TEMPLATE/extensions/kernel-assisted-re.json 212 B
- artifacts/tasks/_TEMPLATE/extensions/native-network.json 253 B
- artifacts/tasks/_TEMPLATE/extensions/native-so.json 203 B
- artifacts/tasks/_TEMPLATE/extensions/protection-bypass.json 1003 B
- artifacts/tasks/_TEMPLATE/extensions/runtime-hooking.json 257 B
- artifacts/tasks/_TEMPLATE/extensions/smali-patching.json 197 B
- artifacts/tasks/_TEMPLATE/extensions/so-runtime-evidence.json 212 B
- artifacts/tasks/_TEMPLATE/extensions/split-delivery.json 250 B
- artifacts/tasks/_TEMPLATE/extensions/static-triage.json 247 B
- artifacts/tasks/_TEMPLATE/extensions/stealth-hook.json 199 B
- artifacts/tasks/_TEMPLATE/extensions/storage-ipc.json 197 B
- artifacts/tasks/_TEMPLATE/extensions/trace-analysis.json 204 B
- artifacts/tasks/_TEMPLATE/extensions/unidbg-simulation.json 210 B
- artifacts/tasks/_TEMPLATE/extensions/vmp-analysis.json 200 B
- artifacts/tasks/_TEMPLATE/extensions/webview-hybrid.json 197 B
- artifacts/tasks/_TEMPLATE/logcat.jsonl 1 B
- artifacts/tasks/_TEMPLATE/memory-evidence.jsonl 1 B
- artifacts/tasks/_TEMPLATE/network.jsonl 1 B
- artifacts/tasks/_TEMPLATE/README.md 1.0 KB
- artifacts/tasks/_TEMPLATE/report.md 997 B
- artifacts/tasks/_TEMPLATE/run/anti-emulator-bypass.js 72 B runs code
- artifacts/tasks/_TEMPLATE/run/anti-frida-bypass-advanced.js 7.7 KB runs code
- artifacts/tasks/_TEMPLATE/run/anti-frida-bypass.js 6.8 KB runs code
- artifacts/tasks/_TEMPLATE/run/anti-root-bypass-advanced.js 8.5 KB runs code
- artifacts/tasks/_TEMPLATE/run/anti-root-bypass.js 4.8 KB runs code
- artifacts/tasks/_TEMPLATE/run/api-call-example.js 46 B runs code
- artifacts/tasks/_TEMPLATE/run/api-map.md 79 B
- artifacts/tasks/_TEMPLATE/run/art-runtime-notes.md 117 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.
- 4d ago First seen · 224 lines · 214 tokens per session scan A 315bc59ab0bb
android-reverse is a skill published in the GitHub repository JacksonTai2007/cc-unlock (137 stars, last pushed 4d ago), licensed MIT. It adds 214 tokens to every session and 3,439 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to android-reverse, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
google-mobile-ads-banner
Provides instructions to implement, integrate, or configure Google Mobile Ads (GMA) banner ads in Android, iOS, or Unity mobile applications. Use when the task involves setting up banner ads in a mobile application. Don't use for other ad formats like interstitial or rewarded ads.
google-mobile-ads-interstitial
Provides instructions for implementing, integrating, or configuring Google Mobile Ads (GMA) SDK interstitial ads in Android, iOS, or Unity mobile applications. Use when the task involves setting up interstitial ads. Don't use for "rewarded interstitial" ads.
google-mobile-ads-rewarded
Provides instructions for implementing, integrating, or configuring Google Mobile Ads (GMA) SDK rewarded ads in Android, iOS, or Unity mobile applications. Use when the task involves setting up rewarded ads. Don't use for "rewarded interstitial" ads.
google-mobile-ads-get-started
Provides instructions for integrating the Google Mobile Ads (GMA) SDK. Use this skill when the user wants to get started with, install, integrate, set up, or configure the SDK for AdMob or Ad Manager, GMA Next-Gen SDK or mobile ads framework in an Android, iOS, or Unity application.
mobile-games
Mobile game development principles. Touch input, battery, performance, app stores.
building-mobile-game
Build mobile games and game-like interactive experiences in React Native and Expo. Use when Codex is creating or refactoring arcade, puzzle, casual, action, physics-based, or animation-heavy gameplay, including Expo game setup with the with-reanimated template, sprite-sheet generation and extraction, frame-based…