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 skills add rnett/gradle-mcp --skill using-gradlegit clone --depth 1 https://github.com/rnett/gradle-mcpWrote 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/rnett/gradle-mcp/using-gradle)<a href="https://agentmods.dev/skills/rnett/gradle-mcp/using-gradle"><img src="https://agentmods.dev/badge/skills/rnett/gradle-mcp/using-gradle.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.03414 |
| Opus 5 | $0.00026 | $0.01707 |
| Sonnet 5 | $0.00011 | $0.00683 |
| Haiku 4.5 | $0.00005 | $0.00341 |
Grade A, and why
using-gradle 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 3d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoritative Gradle Build Execution, Testing & Inspection
Inspects, executes, diagnoses, and researches existing Gradle builds using managed orchestration and structured diagnostics.
Positive Triggers (when to activate)
- Mapping the project hierarchy, discovering runnable tasks, or inspecting project properties.
- Executing Gradle tasks in foreground or background.
- Monitoring build progress or capturing isolated task output.
- Diagnosing build failures through filtered test execution or diagnostic tasks.
- Researching official Gradle documentation, release notes, or internal APIs.
- Auditing the dependency graph, resolving version conflicts, or discovering library updates.
- Searching and reading source code for dependencies, plugins, or Gradle itself.
- Performing trivial everyday dependency edits (adding a version-catalog entry + library, bumping a version).
Negative Triggers (when NOT to activate)
- Structural build authoring: adding/changing plugins, repositories, modules/subprojects, toolchains, publishing, CI wiring, compiler options, or testing frameworks (use
authoring-gradle-builds). - Executing arbitrary Kotlin/Java code via the REPL (use
interacting-with-project-runtime). - Rendering Compose UI components (use
verifying-compose-ui). - Advanced dependency engineering — variant-aware resolution diagnostics, dependency verification, component metadata rules, substitution/composite builds, or dependency governance (use
advanced-gradle-dependencies). Everyday dependency inspection, conflict analysis, and update discovery stay here.
More info: Search official guidance with gradle_docs(query="tag:userguide <term>"); read gradle/wrapper/gradle-wrapper.properties before version-sensitive research.
Constitution
- ALWAYS use the
gradletool instead of./gradlewvia shell. - ALWAYS prefer foreground execution; use background only for persistent (servers) or parallel work.
- STRONGLY PREFERRED: Use
query_buildfor all diagnostics; avoid raw console parsing. - ALWAYS use
query_build(kind="TESTS")for test output; NEVER usecaptureTaskOutputfor tests. - NEVER use
--rerun-tasksunless investigating project-wide cache corruption; prefer--rerunfor targeted task forcing. - ALWAYS read the task outcome (
UP-TO-DATE,FROM-CACHE,SKIPPED, etc.); a green result with zero execution is unproven. - ALWAYS read the wrapper version (
gradle/wrapper/gradle-wrapper.properties) before applying version-specific advice. - Before you start, prioritize structured problems. When diagnosing a FAILED build or a low-signal error, call
query_build(kind="PROBLEMS")BEFORE reading build files; PROBLEMS returns identifiers, severity, documentation, occurrence details, and potential solutions. Start file inspection only when structured problems do not resolve the diagnosis. - Handoff: Route structural build edits, compiler-option configuration, and testing-framework configuration to
authoring-gradle-builds; see Cross-Skill Handoffs.
What ships with it
9 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.
- references/build-environment.md 11 KB
- references/build-orientation.md 7.7 KB
- references/dependencies.md 8.1 KB
- references/diagnostic-tasks.md 6.4 KB
- references/included-builds.md 5.8 KB
- references/research.md 6.6 KB
- references/running-builds.md 11 KB
- references/testing.md 5.5 KB
- references/troubleshooting.md 11 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.
- 3d ago Changed · +3 lines 6b20b961714b
- 8d ago First seen · 127 lines · 53 tokens per session scan A d28c3e34f4c1
using-gradle is a skill published in the GitHub repository rnett/gradle-mcp (60 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 3,414 once invoked, about $0.0003 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 skills, from other repositories
post-mortem
Diagnose instruction defects and optionally submit Rosetta GitHub issue.
trace-mcp
Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. Activate whenever the agent needs to explore, understand, or modify a codebase that has trace-mcp indexed.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
solr-query
To build and debug Solr queries: eDisMax, block join, JSON facets, kNN, explain.
debugging
To investigate errors, test failures, and unexpected behavior — root cause before fix.
self-learning
MUST activate on: execution failure/error, mistake, wrong/unexpected result, expected≠actual mismatch, 2 consecutive mismatches, unhappy/upset user, user asks why something failed/didn't work.