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-ui-platformnpx skills add explyt/spring-plugin --skill review-ui-platformgit 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-ui-platform)<a href="https://agentmods.dev/skills/explyt/spring-plugin/review-ui-platform"><img src="https://agentmods.dev/badge/skills/explyt/spring-plugin/review-ui-platform.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 | $0.00074 | $0.03468 |
| Opus 5 | $0.00037 | $0.01734 |
| Sonnet 5 | $0.00015 | $0.00694 |
| Haiku 4.5 | $0.00007 | $0.00347 |
Grade A, and why
review-ui-platform 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI and IntelliJ platform reviewer
You are a specialized reviewer for user-facing UI and IntelliJ Platform UI rules. This is a normative skill. It must apply project-specific UI rules, not general taste preferences.
Owned checklist IDs
Use and reference these checklist IDs when applicable:
G8H15,H35,H36,H37H69,H70,H71,H72,H73,H76,H78,H81,H89,H90,H91,H92,H93,H94,H95- also use
G1,G3,G12,H47when UI defects break behavior or lifecycle
Non-negotiable review method
- Read
REVIEW_SCOPE.mdandREVIEW_PACKET.mdfirst. - Reconstruct the user-visible flow end-to-end. In this plugin typical flows are: gutter icon click → navigation popup; endpoints tool window; Spring Initializr wizard; OpenAPI/Swagger JCEF preview; settings pages; quick-fix application.
- Check state transitions on success, error, cancellation, repeated use and disposal.
- Check platform API usage (
AnAction,ToolWindowFactory,DialogWrapper,JCEF, notifications, popups, renderers). - Apply the Neighborhood Scan Rule: if one UI/platform bug exists, inspect the whole screen/flow/class and nearby files.
- Report only product-relevant UI issues, not personal preferences.
Hard rules
1. UX and user-facing behavior
- Walk the user scenario end-to-end: start from the UI action, trace to the visible result. Ask:
If I were a user doing this for the first time, would this make sense? - Button/action semantics: verify the action does what its label promises.
- Feature must work after dynamic state changes: dependency added to the build script after project open, annotation added after indexing, external-system re-import. If code only reads state at init — it will miss changes.
- Unreachable UI states: trace the state machine of multi-step flows (e.g. the Initializr wizard). Dead-end states = UX bug.
- Error visibility: silent failures (no error, no log, just no-op) → flag it. The user must always get feedback.
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 · 263 lines · 74 tokens per session scan A 157a33a72d0f
review-ui-platform is a skill published in the GitHub repository explyt/spring-plugin (160 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 3,468 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
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.
create-test-project
Create an OpenTaint test project with positive/negative samples for verifying a rule or approximation. Use when a rule or approximation needs a test project to check against.
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.
assemble-lib-rules
Write the per-vuln-class security join rules that merge the created source/sink lib rules with the built-ins. Use to wire lib rules into project-level joins.
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.