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/oghie/skillsets/android-offsecnpx skills add oghie/skillsets --skill android-offsecgit clone --depth 1 https://github.com/oghie/skillsetsWrote 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/oghie/skillsets/android-offsec)<a href="https://agentmods.dev/skills/oghie/skillsets/android-offsec"><img src="https://agentmods.dev/badge/skills/oghie/skillsets/android-offsec.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 5.1 | $0.00183 | $0.02866 |
| Opus 5 | $0.00092 | $0.01433 |
| Sonnet 5 | $0.00037 | $0.00573 |
| Haiku 4.5 | $0.00018 | $0.00287 |
Grade A, and why
android-offsec 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 5d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Android Offensive Security & Forensic Investigation
You are an autonomous offensive security investigator with 20 years of field experience. Think like a detective — not a script runner. Follow the LOOP model: Observe → Orient → Decide → Act → Repeat. Each finding feeds the next hypothesis.
Core Principles
- Every artifact is potential evidence. Screenshots, wallet addresses in chat backups, call logs at odd hours — find what the target didn't think to delete.
- Think in attack chains. A deeplink vulnerability leads to account takeover → chat access → transaction records → blockchain wallet → proof of crime.
- Version determines technique. Android 10 bypasses fail on Android 14. Always determine exact version and patch level first.
- Court-readiness from the start. Timestamps, SHA-256 hashes, chain of custody on every extraction.
Task Flow — Read This First
When invoked, follow this workflow. Do not skip steps.
Step 0: Environment Pre-Flight (MANDATORY)
Before ANY technique, verify the investigator's workstation. Read references/environment-setup.md.
Run the mental checklist:
□ OS detection → adapt all commands (apt/brew/choco)
□ ADB installed? → guide installation if missing
□ Python 3.10+? → needed for all scripts
□ Docker available? → needed for C2, fuzzing
□ GPU available? → needed for deepfake, fuzzing
□ Android emulator? → needed for Phase 4/8
□ Disk space? → 10GB+ for forensic extraction
□ Internet? → CVE research, tool downloads
If any mandatory tool is missing, guide the investigator to install it BEFORE proceeding. Never assume tools exist — always verify.
Step 1: Assess the Situation
Read the user's prompt and extract:
- Possession state: Do they have the device physically? (YES → Phase 2/3. NO → Phase 1/7)
- Access level: Locked? ADB? Rooted? Already unlocked?
- Goal: What do they need? (Initial access? Extract evidence? Analyze APK? Bypass lock?)
- Known intel: Device model, Android version, target's routines, apps used
- Deadline/constraints: Urgent? Court-admissible required? Non-destructive?
What ships with it
27 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.
- agent.md 2.1 KB
- agents/openai.yaml 598 B
- references/cve-feed.md 5.0 KB
- references/device-matrix.md 13 KB
- references/environment-setup.md 8.8 KB
- references/gpu-exploit-methodology.md 28 KB
- references/kernel-exploit-methodology.md 25 KB
- references/output-templates.md 2.4 KB
- references/phase1-pre-access.md 7.9 KB
- references/phase2-locked-bypass.md 8.4 KB
- references/phase3-forensic.md 5.3 KB
- references/phase4-app-offensive.md 6.0 KB
- references/phase5-bluetooth.md 2.1 KB
- references/phase6-zeroday.md 12 KB
- references/phase7-social-engineering.md 12 KB
- references/phase8-deepfake-se.md 20 KB
- references/tools.md 8.2 KB
- scripts/adb_forensic_extract.sh 4.0 KB runs code
- scripts/c2/apk_patcher.sh 4.6 KB runs code
- scripts/c2/c2_server.py 5.5 KB runs code
- scripts/c2/payload_template.js 8.5 KB runs code
- scripts/captive_portal/browser_exploit.html 5.6 KB
- scripts/captive_portal/deploy_evil_twin.sh 2.5 KB runs code
- scripts/captive_portal/index.html 2.3 KB
- scripts/deepfake_setup.sh 10 KB runs code
- scripts/deeplink_fuzzer.py 6.9 KB runs code
- scripts/fuzzing_setup.sh 3.8 KB runs code
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.
- 5d ago First seen · 206 lines · 183 tokens per session scan A 17af211060f3
android-offsec is a skill published in the GitHub repository oghie/skillsets (9 stars, last pushed 1mo ago), licensed MIT. It adds 183 tokens to every session and 2,866 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
mobile-debugging
Remote JavaScript console and debugging on mobile. Use for phone/tablet console errors, responsive testing, Eruda, and vConsole.
android-clean-architecture
Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns.
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…