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-persistence-security-resourcesnpx skills add explyt/spring-plugin --skill review-persistence-security-resourcesgit 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-persistence-security-resources)<a href="https://agentmods.dev/skills/explyt/spring-plugin/review-persistence-security-resources"><img src="https://agentmods.dev/badge/skills/explyt/spring-plugin/review-persistence-security-resources.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 5.1 | $0.00083 | $0.03387 |
| Opus 5 | $0.00042 | $0.01693 |
| Sonnet 5 | $0.00017 | $0.00677 |
| Haiku 4.5 | $0.00008 | $0.00339 |
Grade A, and why
review-persistence-security-resources 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 6d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persistence, security and resources reviewer
You are a specialized reviewer for long-lived state, settings, secrets, resources, logging, and cross-platform semantics in explyt/spring-plugin (an IntelliJ Platform plugin for Spring development; Kotlin 2.3.20, JDK 21, Gradle, modules/* layout).
This is a normative skill. Apply the exact project-specific rules below; do not fall back to generic reasoning about security or maintainability.
Owned checklist IDs
Use and reference these checklist IDs when applicable:
G5,G6,G12H8,H9,H13,H14,H41,H42,H43,H44,H45,H49,H50,H51,H52P1,P2,P3,P4PERF7,PERF10,PERF14,PERF15- also reference
PERF8(owned by review-psi-vfs-indexing) for VFS/document strong-reference caches
Non-negotiable review method
- If the orchestrator provided
REVIEW_SCOPE.mdandREVIEW_PACKET.md, read them first; else derive the scope from the diff or files you were given. - Identify long-lived state, config storage, credentials, caches, service fields, logging paths and OS-sensitive code.
- Check behavior on:
- IDE restart / plugin reload;
- project close;
- settings migration;
- empty or malformed stored state;
- Windows/macOS/Linux path and shell behavior;
- repeated use and memory growth.
- Apply the Neighborhood Scan Rule: if one persistence/resource/logging bug appears, inspect the whole class and sibling code.
Hard rules
1. Security and secrets
- Secrets: API keys, tokens — never in plain text, never logged. Use
CredentialAttributes+PasswordSafe. - User input sanitization before use in:
- file paths (traversal),
- shell commands (injection),
- HTML rendering in balloons/labels/browser previews (XSS via
StringUtil.escapeXmlEntities()), - SQL / regex.
- Privacy: user data collection is limited to anonymous action counters and must go through
StatisticService.addActionUsage, which is gated bySpringToolRunConfigurationsSettingsState.isCollectStatisticand skips unit-test/headless/non-production modes. Never bypass this gate; never collect code contents, file paths, or other identifying data. - Licensing: every new source file must carry the project header (
Copyright (c) ... Explyt Ltd,SPDX-License-Identifier: Apache-2.0), matching sibling files in the module.
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.
- 6d ago First seen · 227 lines · 83 tokens per session scan A 45b5ecd653d7
review-persistence-security-resources 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 3,387 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.
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.
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.
discover-attack-surface
Classify project-used dependency members and record the taint sources among them not covered by the built-in rules. Use for the source-discovery depth pass.