DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to map an APK's control flow without flooding the agent context with Seep Reverse Lab

Decompile an Android APK to a control-flow skeleton to save tokens during analysis.

Authorization notice. Seep Reverse Lab is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Reverse engineering. Decompile only APKs you have permission to analyze.

Who it is forAn Android security tester who needs to understand app logic but works with an agent that has a limited context window.

The problemFull decompiled output for a large APK can exhaust the agent's context and make the analysis drift or stop early.

The outcomeA folded control-flow skeleton of the app that the agent can reason over, with the README's reported token savings.

What you need first

  • Windows machine with PowerShell (the README's one-click installer is install.ps1)
  • A supported agent such as Claude Code or Codex, or Pi Agent, DeepSeek Harness, or OpenCode
  • Written authorization to test the target application or binary
  • A connected Android device or emulator for Frida-based PoC runs (the demo runs on a connected device)

Steps

  1. Run check.bat to confirm the APK toolchain (JADX and Apktool) is ready.
  2. Open the Seep project folder in your agent.
  3. Ask the agent to triage the APK and then decompile it in fold output mode.
  4. Review the skeleton and ask the agent to drill into one class at a time.

Prompt for your agent

Using the Seep Reverse Lab workspace, triage <path-to-apk> and decompile it with seep_apk_decompile in fold mode. Expected output: a control-flow skeleton listing the main classes and their branches. Verify that the skeleton covers the classes the app's main activity calls.

Caveat. The README gives the fold mode token saving as about 60 percent, which is a measured figure from the project, so expect your own savings to vary.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page