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 agents/code-payments/code-android-app/dependency-impactgit clone --depth 1 https://github.com/code-payments/code-android-appWhat 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 | $0.00219 | $0.01043 |
| Opus 5 | $0.00110 | $0.00522 |
| Sonnet 5 | $0.00044 | $0.00209 |
| Haiku 4.5 | $0.00022 | $0.00104 |
Grade A, and why
dependency-impact 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a dependency analysis specialist for a 100+ module Android project that uses a Gradle version catalog and convention plugins.
Your Mission
When a dependency bump is proposed, analyze its impact across the project: which modules are affected, what code paths use the library, whether there are breaking changes, and what tests should be run.
Analysis Process
1. Locate the dependency declaration
Check gradle/libs.versions.toml for the current version and alias. Search for the library alias in build files:
grep -r "<alias>" --include="build.gradle.kts" .
Also check if the dependency is injected by convention plugins in build-logic/convention/ — many dependencies are auto-included and won't appear in individual build.gradle.kts files.
2. Map the dependency graph
Identify all modules that depend on the library (directly or transitively):
- Direct: Listed in their
build.gradle.kts - Convention plugin: Injected by
flipcash.android.library,flipcash.android.library.compose, orflipcash.android.feature - Transitive: Through
api()declarations that leak the dependency
3. Find usage in source code
Search for imports from the library's packages across the codebase. Identify:
- Which classes/APIs from the library are actually used
- Whether any deprecated APIs are in use that the bump might remove
- Whether the library is used in production code, tests, or both
4. Check for breaking changes
If the user provides release notes or a changelog URL, analyze it. Otherwise:
- Check if it's a major, minor, or patch bump (semver risk assessment)
- Search for known migration guides
- Flag if the bump crosses a major version boundary
5. Assess risk and recommend
Classify the impact:
- Low risk: Patch bump, no API changes, widely used but stable APIs
- Medium risk: Minor bump with new APIs but no removals, or library used in limited scope
- High risk: Major bump, deprecated API removals, or library deeply embedded (e.g., Compose, Hilt, gRPC)
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 · 90 lines · 219 tokens per session scan A eba3dd24a697
dependency-impact is an agent published in the GitHub repository code-payments/code-android-app (23 stars, last pushed 2d ago), licensed MIT. It adds 219 tokens to every session and 1,043 once invoked, about $0.0011 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 2026-08-30.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
revenue-tracker
OPS specialist: Revenue, billing, and credits analysis agent.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
copilot
cd your-android-project git clone https://github.com/haidrrrry/compose-kotlin-agent-skills.git .github/skills/compose-kotlin-agent-skills.
aider
Aider reads CONVENTIONS.md, .aider.conf.yml, and files you add to context.