What is safe-decompile?

A controlled command for examining and decompiling Android app files such as APKs, XAPKs, APKS, APKMs, JARs, and AARs. Decompiling turns packaged app files back into readable source-like code for analysis.

Use it to identify an Android artifact, inspect its structure, extract APIs, search and read source files, and summarize its architecture, network behavior, and authentication.

It keeps the investigation inside a sandbox and chooses an appropriate analysis path based on the app's technology and obfuscation.

safe-decompile — Command for coding agents by salingnh: A controlled command for examining and decompiling Android app…

Install

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.

agentmods

npx agentmods add commands/salingnh/android-reverse-engineering-mcp/safe-decompile

Clone the repo

git clone --depth 1 https://github.com/salingnh/android-reverse-engineering-mcp

Or install safe-android-reverser, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/salingnh/android-reverse-engineering-mcp/safe-decompile.svg)](https://agentmods.dev/commands/salingnh/android-reverse-engineering-mcp/safe-decompile)

Your own site

<a href="https://agentmods.dev/commands/salingnh/android-reverse-engineering-mcp/safe-decompile"><img src="https://agentmods.dev/badge/commands/salingnh/android-reverse-engineering-mcp/safe-decompile.svg" alt="Measured on agentmods" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 287 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00016	$0.00287
Opus 5	$0.00008	$0.00143
Sonnet 5	$0.00003	$0.00057
Haiku 4.5	$0.00002	$0.00029

Measured 4d ago against content hash c0e4c18414df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

safe-decompile 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.

plugins/safe-android-reverser/commands/safe-decompile.md · 22 lines

What it actually says

Analyze $ARGUMENTS using only the safe-android-reverser MCP server.

Call health. If the sandbox image/runtime is unavailable, stop and explain the setup step.
For APK/XAPK/APKS/APKM, call fingerprint first.
If the fingerprint identifies Flutter, React Native, Cordova/Capacitor, or Xamarin/.NET MAUI, explain that Java/Kotlin decompilation is not the primary path and do not wastefully continue.
Otherwise call decompile with the appropriate engine (jadx for Android packages, vineflower for JAR/AAR unless comparison is useful).
Call extract_api on the returned job_id.
Use search_source and read_source_file to investigate the highest-signal findings.
If Kotlin + moderate/high obfuscation is present, call recover_kotlin_names and treat results as confidence-scored candidates.
Return a concise architecture summary, API inventory, notable auth/network behavior, and the strongest source evidence.

Never call the legacy installer or reverse tools directly on the host.

Changes

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 · 22 lines · 16 tokens per session scan A c0e4c18414df

Subscribe to this mod's changes

safe-decompile is a command published in the GitHub repository salingnh/android-reverse-engineering-mcp (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 16 tokens to every session and 287 once invoked, about $0.0001 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.

Debugging Mobile ai-agents ai-tools android-reverse mcp-server reverse-engineering reverse-mcp

safe-decompile

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

decompile

/release

ingest

port_to_platform

research

code-review