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 commands/theqmaks/areclaw-plugin/compare-versionsgit clone --depth 1 https://github.com/TheQmaks/areclaw-pluginWrote 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/theqmaks/areclaw-plugin/compare-versions)<a href="https://agentmods.dev/commands/theqmaks/areclaw-plugin/compare-versions"><img src="https://agentmods.dev/badge/commands/theqmaks/areclaw-plugin/compare-versions.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 | $0.00018 | $0.01388 |
| Opus 5 | $0.00009 | $0.00694 |
| Sonnet 5 | $0.00004 | $0.00278 |
| Haiku 4.5 | $0.00002 | $0.00139 |
Grade A, and why
compare-versions 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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/compare-versions
Compare two versions of the same Android application to identify what changed between releases: new features, security modifications, API additions or removals, permission changes, and protection updates.
Instructions
1. Parse the arguments and decompile both versions
The first argument is the OLD version, the second is the NEW version.
# Detect protections on both
apkid $OLD_APK
apkid $NEW_APK
# Decompile both with jadx
jadx -d workspace/output/old_version --deobf $OLD_APK
jadx -d workspace/output/new_version --deobf $NEW_APK
# Decode resources and smali for both
apktool d -o workspace/output/old_version-smali $OLD_APK
apktool d -o workspace/output/new_version-smali $NEW_APK
2. Diff the AndroidManifest
2a. Compare permissions
grep 'uses-permission' workspace/output/old_version-smali/AndroidManifest.xml | sort > /tmp/perms_old.txt
grep 'uses-permission' workspace/output/new_version-smali/AndroidManifest.xml | sort > /tmp/perms_new.txt
diff /tmp/perms_old.txt /tmp/perms_new.txt
Flag new dangerous permissions and removed permissions.
2b. Compare components
grep -E 'activity |service |receiver |provider ' workspace/output/old_version-smali/AndroidManifest.xml | sort > /tmp/comp_old.txt
grep -E 'activity |service |receiver |provider ' workspace/output/new_version-smali/AndroidManifest.xml | sort > /tmp/comp_new.txt
diff /tmp/comp_old.txt /tmp/comp_new.txt
Flag new exported components, removed components, and changed intent-filters.
2c. Compare SDK versions and security flags
Check for changes in: targetSdkVersion, minSdkVersion, debuggable, allowBackup, networkSecurityConfig.
3. Diff the code
3a. Compare file trees
find workspace/output/old_version -name "*.java" | sed 's|workspace/output/old_version/||' | sort > /tmp/files_old.txt
find workspace/output/new_version -name "*.java" | sed 's|workspace/output/new_version/||' | sort > /tmp/files_new.txt
# New files
comm -13 /tmp/files_old.txt /tmp/files_new.txt > /tmp/new_files.txt
# Removed files
comm -23 /tmp/files_old.txt /tmp/files_new.txt > /tmp/removed_files.txt
# Common files (candidates for content diff)
comm -12 /tmp/files_old.txt /tmp/files_new.txt > /tmp/common_files.txt
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 · 166 lines · 18 tokens per session scan A 575d89505795
compare-versions is a command published in the GitHub repository TheQmaks/areclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 1,388 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.
Other commands, from other repositories
compose-test
Run Compose UI tests with Espresso. Verify critical user flows.
app-store-audit
Run an enterprise pre submission compliance audit on an iOS or Android app against Apple App Store and Google Play rejection rules. Pass a project path or run from the project root.
ios-privacy
Prepare privacy labels, permissions, policy links, and data-use truth for iOS release.
maestro-selectors-instructions
Guide to using Maestro selectors for targeting UI elements in tests.
initialize-ios
Manual override: initialize ast-index for iOS/Swift/ObjC project.
mobile-performance-check
Analyze mobile app for performance issues using the mobile-best-practices database.