advanced-gradle-dependencies

advanced-gradle-dependencies is a skill for Claude Code, Codex from rnett/gradle-mcp. It costs 49 tokens per session (1,982 once invoked), scanned A, original, Apache-2.0.

Guidance for difficult Gradle dependency problems. Dependencies are external libraries a project uses, while variants, capabilities, and metadata control which library version or form Gradle selects.

In plain words
What is it for?
Use it for variant and attribute failures, dependency verification, metadata and selection rules, substitutions, capability conflicts, advanced version catalogs, repository policies, and caching.
Why use it?
It helps diagnose cases where ordinary dependency declarations or conflict checks cannot explain why Gradle selected, rejected, or verified a library.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for variant and attribute failures, dependency verification, metadata and selection rules, substitutions, capability conflicts, advanced version catalogs, repository policies, and caching.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rnett/gradle-mcp/advanced-gradle-dependencies
Install

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.

Any agent
npx skills add rnett/gradle-mcp --skill advanced-gradle-dependencies
Clone the repo
git clone --depth 1 https://github.com/rnett/gradle-mcp

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.

agentmods badge for advanced-gradle-dependencies

README.md
[![agentmods](https://agentmods.dev/badge/skills/rnett/gradle-mcp/advanced-gradle-dependencies/github.svg)](https://agentmods.dev/skills/rnett/gradle-mcp/advanced-gradle-dependencies)
Your own site
<a href="https://agentmods.dev/skills/rnett/gradle-mcp/advanced-gradle-dependencies"><img src="https://agentmods.dev/badge/skills/rnett/gradle-mcp/advanced-gradle-dependencies/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.

agentmods 80×15 button for advanced-gradle-dependencies

Your own site · 80×15
<a href="https://agentmods.dev/skills/rnett/gradle-mcp/advanced-gradle-dependencies"><img src="https://agentmods.dev/badge/skills/rnett/gradle-mcp/advanced-gradle-dependencies.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,982 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.01982
Opus 5 $0.00024 $0.00991
Sonnet 5 $0.00010 $0.00396
Haiku 4.5 $0.00005 $0.00198

Measured 6d ago against content hash af2ef9fdb3f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

advanced-gradle-dependencies 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 6d 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.

src/main/skills/advanced-gradle-dependencies/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Advanced Gradle Dependency Engineering

Diagnoses and fixes advanced Gradle dependency resolution problems as diagnose-to-fix loops across the operate/author split. This skill owns the cross-cutting lane between everyday dependency inspection (using-gradle) and basic dependency authoring (authoring-gradle-builds).

Positive Triggers (when to activate)

  • Variant selection failures or attribute mismatches, diagnosed via outgoingVariants and dependencyInsight --all-variants
  • Dependency verification metadata, PGP keys, and CI verification workflows
  • Component metadata rules, selection rules, dependency substitution, and composite build diagnosis
  • Capability conflicts, feature variants, lock modes, advanced version catalogs beyond everyday catalog entries, repository governance, and caching/freshness tuning

Negative Triggers (when NOT to activate)

  • Everyday dependency inspection, conflicts, or updates -> using-gradle
  • Dependency declarations, basic version catalogs, or basic locking -> authoring-gradle-builds
  • Running builds or generic failure diagnosis -> using-gradle
  • Non-dependency structural authoring -> authoring-gradle-builds

More info: Search the User Guide with gradle_docs(query="tag:userguide <term>"). Read gradle/wrapper/gradle-wrapper.properties before any version-sensitive advice; this skill's wrapper-first scoping is mandatory because resolution behavior is version-sensitive.

Constitution

  • ALWAYS use the Gradle MCP gradle tool (or the dedicated dependency inspection tools) instead of ./gradlew via shell for all resolution work.
  • ALWAYS read the wrapper version (gradle/wrapper/gradle-wrapper.properties) before applying version-sensitive advice; resolution reports, variant model behavior, and governance modes change across Gradle versions.
  • ALWAYS diagnose before fixing: run the matching authoritative report first (dependencyInsight, outgoingVariants, graph inspection), then apply the minimal authoring fix, then re-run the diagnostic to confirm resolution.
  • ALWAYS use query_build(kind="TESTS") for tests and query_build for diagnostics; avoid raw console parsing.
  • NEVER prescribe a resolution fix without a diagnostic step; variant mismatches, capability conflicts, and substitution behavior must be evidenced before authoring a rule.
  • NEVER fabricate tool names; cite authoritative documentation only through gradle_docs hints (path=... or query="tag:...").
  • Handoff: everyday dependency inspection belongs to using-gradle; basic dependency declaration, version-catalog basics, and basic locking belong to authoring-gradle-builds; see Cross-Skill Handoffs.

Read the full file on GitHub · 97 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.

  1. 6d ago Changed · +1 lines af2ef9fdb3f9
  2. 12d ago First seen · 96 lines · 49 tokens per session scan A c33dc6884342

Subscribe to this mod's changes

advanced-gradle-dependencies is a skill published in the GitHub repository rnett/gradle-mcp (60 stars, last pushed 4d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,982 once invoked, about $0.0002 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.