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 nimbly-dev/mcp-java-dev-tools --skill mcp-java-dev-tools-regression-suitegit clone --depth 1 https://github.com/nimbly-dev/mcp-java-dev-toolsWrote 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/nimbly-dev/mcp-java-dev-tools/mcp-java-dev-tools-regression-suite)<a href="https://agentmods.dev/skills/nimbly-dev/mcp-java-dev-tools/mcp-java-dev-tools-regression-suite"><img src="https://agentmods.dev/badge/skills/nimbly-dev/mcp-java-dev-tools/mcp-java-dev-tools-regression-suite/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/nimbly-dev/mcp-java-dev-tools/mcp-java-dev-tools-regression-suite"><img src="https://agentmods.dev/badge/skills/nimbly-dev/mcp-java-dev-tools/mcp-java-dev-tools-regression-suite.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.04766 |
| Opus 5.5 | $0.00021 | $0.01906 |
| Sonnet 5.5 | $0.00010 | $0.00953 |
| Haiku 4.5 | $0.00005 | $0.00477 |
Grade A, and why
mcp-java-dev-tools-regression-suite scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. HTTP execution uses `transport_execute` (wrapped-only); no raw curl fallback. The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
20 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.
- README.md 533 B
- references/artifact-contract.md 1.9 KB
- references/execution-contract.md 761 B
- references/execution-fsm.md 588 B
- references/output-contract.md 676 B
- references/probe-verification-policy.md 411 B
- references/project-context-and-preflight.md 1.9 KB
- references/reason-codes.md 631 B
- references/runtime-policy.md 1.2 KB
- references/strict-probe-gate.md 2.2 KB
- references/synthesis-and-routing.md 1.4 KB
- scripts/cleanup-runtime.js 404 B runs code
- scripts/preflight-resolve.js 637 B runs code
- scripts/probe-gate-check.js 579 B runs code
- scripts/runtime-converge.js 998 B runs code
- scripts/step-execution-check.js 392 B runs code
- scripts/summarize-run.js 399 B runs code
- templates/fail-closed.result.json 129 B
- templates/needs-user-input.result.json 154 B
- templates/run-summary.result.json 204 B
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.
- 1mo ago First seen · 345 lines · 52 tokens per session scan A 96a44ffd6178
mcp-java-dev-tools-regression-suite is a skill published in the GitHub repository nimbly-dev/mcp-java-dev-tools (2 stars, last pushed yesterday), with no licence file. It adds 52 tokens to every session and 4,766 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
vs-ui-explore
Autonomously explore the UI of a Visual Studio debuggee via vs-mcp UIA tools (uisnapshot, uifindelements, uiwait) and produce a structured bug/coverage report. Use when the user asks to "test all screens", "crawl the UI", "find UI bugs autonomously", or similar.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
flutter-mcp-toolkit-control
Drive a running Flutter app — tap, scroll, type, fill forms, hot-reload, navigate. Use when you need to interact with the UI.
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
flutter-mcp-e2e-harness
Use this skill when writing or running repeatable E2E scenarios for Flutter apps as checked-in Dart with the fluttermcpharness package (packages/harness) — build/launch the app, attach to its VM service, drive widgets (snapshot/tap/enter text) and assert without MCP; also covers the repo showcase launcher (make…