Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/JacksonTai2007/cc-unlocknpx agentmods add commands/jacksontai2007/cc-unlock/decompileWrote 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/commands/jacksontai2007/cc-unlock/decompile)<a href="https://agentmods.dev/commands/jacksontai2007/cc-unlock/decompile"><img src="https://agentmods.dev/badge/commands/jacksontai2007/cc-unlock/decompile/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.
<a href="https://agentmods.dev/commands/jacksontai2007/cc-unlock/decompile"><img src="https://agentmods.dev/badge/commands/jacksontai2007/cc-unlock/decompile.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00869 |
| Opus 5.5 | $0.00000 | $0.00348 |
| Sonnet 5.5 | $0.00000 | $0.00174 |
| Haiku 4.5 | $0.00000 | $0.00087 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/decompile
Decompile an Android binary file and perform initial triage analysis.
Steps
1. Get target file
Parse $ARGUMENTS to determine the target file path. If no argument is provided, ask the user to specify a file.
Validate the file exists and determine its type by extension:
.apk/.xapk/.apks/.aab→ Android application package.jar/.aar→ Java/Android library.dex→ Dalvik bytecode.so→ Native shared library (use IDA/Ghidra, not jadx)
2. Check and install dependencies
Run the dependency check script for the current platform:
# Linux / macOS
bash scripts/check-deps.sh
# Windows
powershell -ExecutionPolicy Bypass -File scripts/check-deps.ps1
Parse output for INSTALL_REQUIRED:<dep> lines. If any required dependency is missing, install it:
bash scripts/install-dep.sh <dep>
# or on Windows:
powershell -ExecutionPolicy Bypass -File scripts/install-dep.ps1 <dep>
Do not proceed until all required dependencies (Java 17+, jadx) pass.
3. Decompile
Select the decompilation engine based on target type and situation. Read references/engine-selection.md for the decision tree.
| Situation | Engine | Reason |
|---|---|---|
| Standard APK/JAR/AAR | jadx | Best default, handles most cases |
| jadx produces broken code | fernflower | Different decompilation backend |
| Heavily obfuscated | both |
Cross-reference between engines |
| XAPK | jadx (per inner APK) | Auto-extracts and decompiles each APK |
| Need code-only analysis (skip resources) | jadx --no-res |
Faster output without resource files |
Run the decompile script:
# Linux / macOS
bash scripts/decompile.sh <target> -o <output-dir> [--deobf] [--engine jadx|fernflower|both]
# Windows
powershell -ExecutionPolicy Bypass -File scripts/decompile.ps1 <target> -o <output-dir> [-Deobf] [-Engine jadx|fernflower|both]
4. Analyze structure
After decompilation, perform initial triage:
- Read
AndroidManifest.xml— identify:- Package name, min/target SDK
- Launcher activity
- Declared services, receivers, providers
- Custom permissions and protection levels
- Exported components
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 First seen · 108 lines · 0 tokens per session scan A 972495ec9a83
decompile is a command published in the GitHub repository JacksonTai2007/cc-unlock (168 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 869 tokens. 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 2026-08-30.
decompile compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| decompileJacksonTai2007/cc-unlock | Command | 168 | 1mo ago | MIT | A | 0 | Claude Code |
| qa-changesOpenHands/extensions | Command | 176 | yesterday | MIT | A | 63 | Claude Code |
| react-nativegetsentry/toolkit | Command | 957 | yesterday | none | A | 0 | Claude Code |
| auditar-cascadingluanpdd/kit-mcp | Command | 5 | 4d ago | MIT | A | 54 | Claude Code |
| http-serviceMadAppGang/magus | Command | 14 | yesterday | MIT | A | 27 | Claude Code |
| doctordoncheli/don-cheli-sdd | Command | 59 | 2mo ago | Apache-2.0 | A | 76 | Claude Code |
| doctorfatihkan/badi | Command | 7 | 1mo ago | MIT | A | 0 | Claude Code |