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 interacting-with-project-runtimegit 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/interacting-with-project-runtime)<a href="https://agentmods.dev/skills/rnett/gradle-mcp/interacting-with-project-runtime"><img src="https://agentmods.dev/badge/skills/rnett/gradle-mcp/interacting-with-project-runtime/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.
<a href="https://agentmods.dev/skills/rnett/gradle-mcp/interacting-with-project-runtime"><img src="https://agentmods.dev/badge/skills/rnett/gradle-mcp/interacting-with-project-runtime.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00049 | $0.00972 |
| Opus 5 | $0.00024 | $0.00486 |
| Sonnet 5 | $0.00010 | $0.00194 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
interacting-with-project-runtime 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 9d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persistent JVM/Kotlin REPL for Project Runtime Probing
Executes Kotlin code interactively within the project's full runtime classpath, enabling rapid logic verification and state inspection without a full build cycle.
Positive Triggers (when to activate)
- Verifying dynamic behavior of a class or function in the project runtime.
- Probing internal state or executing experimental logic without a full build cycle.
- Rapidly prototyping logic changes within the JVM classpath.
Negative Triggers (when NOT to activate)
- Operating a Gradle build (use
using-gradle). - Modifying build definitions (use
authoring-gradle-builds). - Rendering Compose UI components (use
verifying-compose-ui).
Constitution
- ALWAYS prefer reading source code over running it when the question is about API shape, signatures, or static behavior.
- Use the REPL when you need to verify runtime behavior: dynamic dispatch, state mutations, side effects, or complex logic that is hard to reason about statically.
- ALWAYS call
stopafter finishing a session to release JVM resources. - NEVER run code that modifies project files, deletes data, or has irreversible side effects without explicit user approval.
- After modifying project source code, call
stopthenstartto pick up classpath changes.
Directives
Starting a Session
Call kotlin_repl(command="start", projectPath=":module", sourceSet="main") to initialize a REPL session. The session runs in a dedicated worker process with the project's full classpath.
For session parameters, lifecycle management, and environment troubleshooting, see REPL Session Setup.
Running Code
Call kotlin_repl(command="run", code="...") to execute a Kotlin snippet. Session state (variables, imports, class definitions) persists between calls.
// Example: Verify a utility function
val result = MyUtils.parseDate("2024-01-15")
println("Parsed: $result, type: ${result::class.simpleName}")
What ships with it
1 file 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.
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.
- 9d ago First seen · 117 lines · 49 tokens per session scan A 8d318a53dfc7
interacting-with-project-runtime is a skill published in the GitHub repository rnett/gradle-mcp (60 stars, last pushed yesterday), licensed Apache-2.0. It adds 49 tokens to every session and 972 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.
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.