What is hermes-apk-reverse-engineering?

A workflow for examining and modifying authorized Android application packages, or APKs. An APK is the installable file used to distribute an Android app; the workflow covers its code, settings, native libraries, and Flutter components.

Use it to decode an APK, inspect its manifest and code, analyze injection points, add a Flutter runtime and Smali changes, update configuration, then rebuild, align, sign, and verify the result.

It makes APK work evidence-based by requiring findings at each stage, from decoding and analysis through rebuilding, signing, and verification. This helps track what changed and whether the final package is valid.

How MarwanDevSpace/mcp-flutter-apk-injector configures Claude Code and

Reuse

Borrowing it

Nothing to install: this file belongs to MarwanDevSpace/mcp-flutter-apk-injector. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/MarwanDevSpace/mcp-flutter-apk-injector/main/.agents/skills/hermes-apk-reverse-engineering/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/MarwanDevSpace/mcp-flutter-apk-injector

Made for: Claude Code, Codex.

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/skills/marwandevspace/mcp-flutter-apk-injector/hermes-apk-reverse-engineering/github.svg)](https://agentmods.dev/skills/marwandevspace/mcp-flutter-apk-injector/hermes-apk-reverse-engineering)

Your own site

<a href="https://agentmods.dev/skills/marwandevspace/mcp-flutter-apk-injector/hermes-apk-reverse-engineering"><img src="https://agentmods.dev/badge/skills/marwandevspace/mcp-flutter-apk-injector/hermes-apk-reverse-engineering/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/marwandevspace/mcp-flutter-apk-injector/hermes-apk-reverse-engineering"><img src="https://agentmods.dev/badge/skills/marwandevspace/mcp-flutter-apk-injector/hermes-apk-reverse-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 921 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00034	$0.00921
Opus 5.5	$0.00014	$0.00368
Sonnet 5.5	$0.00007	$0.00184
Haiku 4.5	$0.00003	$0.00092

Measured 2mo ago against content hash da8cef537123, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hermes-apk-reverse-engineering 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 2mo 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.

.agents/skills/hermes-apk-reverse-engineering/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermes+ Android Workspace Integrity Skill

This skill implements the canonical GEMINI.md contract for authorized Android workspace analysis and transformation. It is complementary guidance; when it differs from GEMINI.md, the root workspace contract is authoritative.

Evidence-first workflow

Stage	Action	Required evidence
Decode	Run `decompile_apk` into a dedicated workspace.	Input path/hash, package, SDK values, manifest path, Smali roots, and ABI directories.
Analyze	Run `analyze_injection_surface` without workspace mutation.	Application/activity/JNI/Flutter findings, native `.so` libraries, security analysis (anti-debug, root checks, SSL pinning, obfuscators), multi-dex roots, warnings, and candidate hooks.
Prepare	Build or validate the Flutter payload.	ABI coverage, native libraries, assets, build mode, engine identity, and warning set.
Integrate	Run `inject_flutter_runtime_and_smali` only after selecting a supported mode.	Generated descriptors, changed files, register/lifecycle evidence, and warnings.
Configure	Run `patch_manifest_and_config` for reviewed manifest changes.	Exact component, permission, application, and rendering deltas.
Verify	Run `recompile_align_and_sign` as the final output step.	Build, alignment, signature, certificate context, output path, and artifact classification.

Deep reverse engineering & security audit

Anti-debugging & Root Detection: Review securityAnalysis results (isDebuggerConnected, RootBeer, su binaries, test-keys, TracerPid). Ensure injected Smali execution paths do not trip host tamper mechanisms.
Native Libraries & ABI Parity: Inspect nativeLibraries mapping per ABI before payload synthesis. Ensure injected Flutter libraries match the target's native architectures.
Multi-DEX Integrity: Resolve classes and methods across all smali_classes* directories. Never assume a single primary smali/ root in modern applications.

Read the full file on GitHub · 50 lines

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.

2mo ago Changed · +6 lines da8cef537123
2mo ago First seen · 44 lines · 34 tokens per session scan A 4a90778e6c60

Subscribe to this mod's changes

hermes-apk-reverse-engineering is a skill published in the GitHub repository MarwanDevSpace/mcp-flutter-apk-injector (5 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 921 once invoked, about $0.0001 per session on Opus 5.5. 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.

Mobile Security

hermes-apk-reverse-engineering next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hermes-apk-reverse-engineeringMarwanDevSpace/mcp-flutter-apk-injector	Skill	5	2mo ago	MIT	A	34	Claude Code, Codex
orca-emulator-androidstablyai/orca	Skill	117k	yesterday	MIT	A	102	Claude Code, Codex
glance-canonical-layoutsandroid/skills	Skill	10k	yesterday	Apache-2.0	A	56	Claude Code
android-tombstone-symbolicationdotnet/skills	Skill	5.8k	yesterday	MIT	A	176	Claude Code
dogfoodcallstack/agent-device	Skill	5.3k	yesterday	MIT	A	55	Claude Code
winapp-mauimicrosoft/winappCli	Skill	1.4k	yesterday	MIT	A	68	Claude Code
app_remixrome-os/rome	Skill	889	yesterday	MIT	A	50	Claude Code, Codex

mcp-flutter-apk-injector: Skill for Claude Code