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 skills/explyt/spring-plugin/review-scope-resolvernpx skills add explyt/spring-plugin --skill review-scope-resolvergit clone --depth 1 https://github.com/explyt/spring-pluginWrote 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/explyt/spring-plugin/review-scope-resolver)<a href="https://agentmods.dev/skills/explyt/spring-plugin/review-scope-resolver"><img src="https://agentmods.dev/badge/skills/explyt/spring-plugin/review-scope-resolver.svg" alt="Measured on agentmods" 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 | $0.00083 | $0.01283 |
| Opus 5 | $0.00042 | $0.00642 |
| Sonnet 5 | $0.00017 | $0.00257 |
| Haiku 4.5 | $0.00008 | $0.00128 |
Grade A, and why
review-scope-resolver 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 5d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope resolver for code review
You do not perform the review itself. Your job is to turn the user's technical reference into an exact review target.
What to do
- Resolve the user's technical reference:
- PR;
- diff;
- commit;
- branch;
- issue;
- URL;
- list of files;
- directory or module (e.g.
modules/spring-core,modules/spring-web); - a specific file, class, or function.
- Determine:
- what exactly is part of the review target;
- which review mode is needed: diff-only, changed-files, full-file, module, commit range, etc.;
- which files, modules, tests, and related artifacts fall into scope;
- what is explicitly out of scope.
- Split the scope into semantic clusters:
- A cluster is a group of files united by one flow, one feature, or one contract.
- If all changes form one coherent flow (even across 40 files), produce one cluster.
- If the PR contains several independent features / unrelated bugfixes / modules without shared contracts, produce several clusters.
- Mechanical splitting by file count is forbidden.
- For each cluster state: name, included files, short essence of the changes.
- For each cluster count significant files and split into priorities when needed:
- Significant files: business logic, UI, services, inspections, completion/reference contributors, line markers.
- Not significant (do not count): tests (
*Test.kt,*Spec.kt), XML/plugin.xml,.gradle/.gradle.kts,.md, resources, icons. - If a cluster has 15 or fewer significant files, return a single
fileslist. - If a cluster has more than 15 significant files, you must split it into:
priority_core_files(15 or fewer): files carrying the main logic of the change — feature entry point, contracts, main classes;periphery_files: the remaining significant files — adapters, helper classes, minor adjustments.
- Produce routing signals for the domain reviewer subskills:
async-lifecyclepsi-vfs-indexingui-platformpersistence-security-resourcesui-leak-via-listenersstatistic-coveragefreeze-safety(add it if the target matches the freeze-safety routing matrix of the orchestrator)
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.
- 5d ago First seen · 149 lines · 83 tokens per session scan A 4f41ac77e72b
review-scope-resolver is a skill published in the GitHub repository explyt/spring-plugin (160 stars, last pushed yesterday), licensed Apache-2.0. It adds 83 tokens to every session and 1,283 once invoked, about $0.0004 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
spring-ecosystem-docs
Spring Boot 4.x + Framework 7.x — auto-configuration, DI, AOP, MVC, WebFlux, Security, Data JPA/MongoDB/Redis.
stove
Use when configuring, writing, or debugging Stove end-to-end tests; choosing JVM, process, container, or provided-application runners; wiring Stove systems; enabling tracing, dashboard, or MCP; or extending Stove with custom systems.
analyze-external-methods
Analyze an OpenTaint scan's dropped external methods and decide which of them are propagators and optionally sinks. Use when a dropped-external-methods.yaml needs classification for dropped method type.
create-rule
Author and verify an OpenTaint rule. Use whenever a rule creation is needed.
appsec-agent
Run an end-to-end OpenTaint application-security analysis while owning the long project build and scans and delegating each other pipeline stage. Use when the user asks to find vulnerabilities, or scan an application for security issues.
create-dataflow-approximation
Model a method's taint propagation as code-based dataflow approximation and refine it against a test project until the sample passes. Use for a dropped method that requires code-based approximation.