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/develop-inspection-featurenpx skills add explyt/spring-plugin --skill develop-inspection-featuregit clone --depth 1 https://github.com/explyt/spring-pluginWhat 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 | $0.00103 | $0.02244 |
| Opus 5 | $0.00051 | $0.01122 |
| Sonnet 5 | $0.00021 | $0.00449 |
| Haiku 4.5 | $0.00010 | $0.00224 |
Grade A, and why
develop-inspection-feature 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 2d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop an Inspection Feature (explyt/spring-plugin)
Produce a working, registered, tested inspection (with optional quick-fix) on its own branch with a PR to main, following the lessons learned from the Spring Boot 3/4 migration inspection series.
Critical constraints
- Call the
coding-guardskill first and follow it for style, threading, SPDX headers, bundles, and PR hygiene. - Never trust migration guides or wiki summaries for FQNs or API moves. Verify every class/annotation FQN against the authoritative javadoc or the actual artifact before hardcoding it (lesson:
EnvironmentPostProcessordid NOT move in Boot 4 despite the guide summary implying it). - Never highlight import statements — the IDE folds them and users never see the warning. Highlight the visible element: the annotation usage, the declaration type reference (field / parameter / return type), the property key, or the class name identifier.
- Never do per-PSI-element availability checks (library version, class presence). All gating belongs in
LocalInspectionTool#isAvailableForFile, which runs once per file and short-circuits the whole inspection. - Do not duplicate an existing inspection. Check first (see Algorithm step 1).
- Do not push feature branches to
origin(internal GitLab). Push to thepublicremote (explyt/spring-plugin); PRs target itsmain. - Use the
ghCLI for GitHub operations (issues, PRs, review replies), not the GitHub MCP tools. - After any
git checkout/rebase/stashvia terminal, do not trust cached file reads: verify each file edit landed on disk (grep -c), and verify staged content viagit show :<path>before committing.
Inputs
Resolve before starting:
- Feature definition: what the inspection detects, the exact old→new mapping (FQNs, property keys), and the quick-fix behavior.
- Version gate: which framework/library version enables the check (e.g. Spring Boot 4+), if any.
- Target module: usually
spring-core; feature modules (spring-web,spring-data, …) per their area. - Branch name:
username/feature-name(e.g.imuromtsev/boot4-mockbean-migration), branched offpublic/main.
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.
- 2d ago First seen · 92 lines · 103 tokens per session scan A d148c015c7b5
develop-inspection-feature is a skill published in the GitHub repository explyt/spring-plugin (160 stars, last pushed 4d ago), licensed Apache-2.0. It adds 103 tokens to every session and 2,244 once invoked, about $0.0005 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.
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.