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 explyt/spring-plugin --skill develop-inspection-featuregit 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/develop-inspection-feature)<a href="https://agentmods.dev/skills/explyt/spring-plugin/develop-inspection-feature"><img src="https://agentmods.dev/badge/skills/explyt/spring-plugin/develop-inspection-feature/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/explyt/spring-plugin/develop-inspection-feature"><img src="https://agentmods.dev/badge/skills/explyt/spring-plugin/develop-inspection-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.02498 |
| Opus 5.5 | $0.00041 | $0.00999 |
| Sonnet 5.5 | $0.00021 | $0.00500 |
| Haiku 4.5 | $0.00010 | $0.00250 |
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 today.
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 — 95 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.
- today Changed · +3 lines e83e15f48e30
- 1mo 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 (164 stars, last pushed today), licensed Apache-2.0. It adds 103 tokens to every session and 2,498 once invoked, about $0.0004 per session on Opus 5.5. 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
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-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.
debug-rule
Debug a rule or approximation that behaves unexpectedly by tracing where taint is dropped. Use when its samples won't pass after repeated attempts, or it passes tests but is wrong on a real scan.
assemble-lib-rules
Connect the shared untrusted-data source group to new reusable OpenTaint sink groups. Use to wire new sink tags into security joins.
cosmos-run-integration-tests
Run azure-cosmos integration/customer-workflow tests locally, closely following the CI pipeline (build+install, then failsafe verify with a test profile) using one consistent JDK for both steps. USE WHEN: asked to run cosmos integration tests, customer-workflow tests (fi-customer-workflows / fi-sm-customer-workflows)…
tool-assistant
Tool-calling assistant with backend functions for time, city time, weather, and temperature conversion, plus cost metering and approval workflows. Use when a question needs real-time data via tool calls.