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/dinglebear-ai/dendrite/claude-android-ninjanpx skills add dinglebear-ai/dendrite --skill claude-android-ninjagit clone --depth 1 https://github.com/dinglebear-ai/dendriteWrote 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/dinglebear-ai/dendrite/claude-android-ninja)<a href="https://agentmods.dev/skills/dinglebear-ai/dendrite/claude-android-ninja"><img src="https://agentmods.dev/badge/skills/dinglebear-ai/dendrite/claude-android-ninja.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 | $0.00099 | $0.08513 |
| Opus 5 | $0.00049 | $0.04256 |
| Sonnet 5 | $0.00020 | $0.01703 |
| Haiku 4.5 | $0.00010 | $0.00851 |
Grade A, and why
claude-android-ninja 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 2d 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
60 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.
- .github/FUNDING.yml 15 B
- .github/ISSUE_TEMPLATE/bug_report.md 907 B
- .github/ISSUE_TEMPLATE/feature_request.md 1.2 KB
- .gitignore 2.5 KB
- agents/openai.yaml 241 B
- assets/convention/AndroidApplicationBaselineProfileConventionPlugin.kt 980 B
- assets/convention/AndroidApplicationComposeConventionPlugin.kt 778 B
- assets/convention/AndroidApplicationConventionPlugin.kt 1.3 KB
- assets/convention/AndroidApplicationJacocoConventionPlugin.kt 945 B
- assets/convention/AndroidFeatureConventionPlugin.kt 1.9 KB
- assets/convention/AndroidLibraryComposeConventionPlugin.kt 765 B
- assets/convention/AndroidLibraryConventionPlugin.kt 2.1 KB
- assets/convention/AndroidLibraryJacocoConventionPlugin.kt 925 B
- assets/convention/AndroidLintConventionPlugin.kt 1.2 KB
- assets/convention/AndroidRoomConventionPlugin.kt 1.3 KB
- assets/convention/AndroidTestConventionPlugin.kt 920 B
- assets/convention/build.gradle.kts 3.6 KB
- assets/convention/config/AndroidCompose.kt 2.3 KB
- assets/convention/config/AndroidInstrumentationTest.kt 613 B
- assets/convention/config/GradleManagedDevices.kt 1.7 KB
- assets/convention/config/Jacoco.kt 5.0 KB
- assets/convention/config/KotlinAndroid.kt 3.7 KB
- assets/convention/config/PrintApksTask.kt 943 B
- assets/convention/config/ProjectExtensions.kt 419 B
- assets/convention/DetektConventionPlugin.kt 2.1 KB
- assets/convention/FirebaseConventionPlugin.kt 1.4 KB
- assets/convention/HiltConventionPlugin.kt 1.0 KB
- assets/convention/JvmLibraryConventionPlugin.kt 734 B
- assets/convention/KotlinSerializationConventionPlugin.kt 676 B
- assets/convention/PlayVitalsReportingConventionPlugin.kt 745 B
- assets/convention/PlayVitalsReportingTask.kt 1.7 KB
- assets/convention/QUICK_REFERENCE.md 15 KB
- assets/convention/SentryConventionPlugin.kt 784 B
- assets/convention/SpotlessConventionPlugin.kt 1.7 KB
- assets/detekt.yml.template 16 KB
- assets/libs.versions.toml.template 15 KB
- assets/proguard-rules.pro.template 9.7 KB
- assets/settings.gradle.kts.template 4.2 KB
- CHANGELOG.md 234 B
- LICENSE.md 11 KB
- README.md 15 KB
- references/android-accessibility.md 46 KB
- references/android-ci-cd.md 8.8 KB
- references/android-code-coverage.md 7.5 KB
- references/android-data-sync.md 71 KB
- references/android-debugging.md 13 KB
- references/android-graphics.md 35 KB
- references/android-i18n.md 27 KB
- references/android-media.md 6.5 KB
- references/android-navigation.md 87 KB
- references/android-notifications.md 39 KB
- references/android-performance.md 58 KB
- references/android-permissions.md 23 KB
- references/android-security.md 73 KB
- references/android-strictmode.md 8.3 KB
- references/android-theming.md 82 KB
- references/architecture.md 54 KB
- references/code-quality.md 8.8 KB
- references/compose-patterns.md 141 KB
- references/coroutines-patterns.md 59 KB
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.
- 2d ago First seen · 406 lines · 99 tokens per session scan A 333f5677031d
claude-android-ninja is a skill published in the GitHub repository dinglebear-ai/dendrite (1 stars, last pushed 9d ago), licensed AGPL-3.0. It adds 99 tokens to every session and 8,513 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
android-data-persistence
Use when implementing local data storage with Room, DataStore, or offline-first patterns. Covers entities, DAOs, migrations, Paging3, and the repository pattern for data management.
swift-actor-persistence
Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.
firebase-database
Use when syncing real-time data, structuring JSON trees, reading/writing, creating listeners, enabling offline persistence, managing presence, sharding, or writing security rules.
mongodb-connection
Optimize MongoDB client connection configuration (pools, timeouts, patterns) for any supported driver language. Use this skill when working/updating/reviewing on functions that instantiate or configure a MongoDB client (eg, when calling connect()), configuring connection pools, troubleshooting connection errors…
mongodb-schema-design
MongoDB schema design patterns and anti-patterns. Use when designing data models, reviewing schemas, migrating from SQL, or troubleshooting performance issues caused by schema problems. Triggers on "design schema", "embed vs reference", "MongoDB data model", "schema review", "unbounded arrays", "one-to-many", "tree…
mongodb-query-optimizer
Help with MongoDB query optimization and indexing. Use only when the user asks for optimization or performance: "How do I optimize this query?", "How do I index this?", "Why is this query slow?", "Can you fix my slow queries?", "What are the slow queries on my cluster?", etc. Do not invoke for general MongoDB query…