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.
git clone --depth 1 https://github.com/brody-0125/my-claude-skillsWrote 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/plugins/brody-0125/my-claude-skills/sub-kopring-engineer)<a href="https://agentmods.dev/plugins/brody-0125/my-claude-skills/sub-kopring-engineer"><img src="https://agentmods.dev/badge/plugins/brody-0125/my-claude-skills/sub-kopring-engineer/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/plugins/brody-0125/my-claude-skills/sub-kopring-engineer"><img src="https://agentmods.dev/badge/plugins/brody-0125/my-claude-skills/sub-kopring-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sub-kopring-engineer 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 10d 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.
What it actually says
{
"name": "sub-kopring-engineer",
"description": "Kotlin/Java Spring Boot workflow agent with convention verification",
"version": "3.0.0",
"hooks": {
"PostToolUse": [
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "file=$(echo \"$CLAUDE_TOOL_INPUT\" | jq -r '.file_path // .path // empty' 2>/dev/null); if [ -n \"$file\" ] && echo \"$file\" | grep -qE '\\.(kt|kts|java)$'; then echo \"[Hook] Lint: $file\"; cd \"$(git rev-parse --show-toplevel 2>/dev/null || echo .)\" && relfile=$(echo \"$file\" | sed \"s|^$(pwd)/||\" ) && if echo \"$file\" | grep -qE '\\.java$'; then ./gradlew checkstyleMain -PcheckstyleIncludes=\"**/${relfile##*/}\" --quiet 2>&1 | tail -20 || true; else ./gradlew ktlintCheck --include \"**/${relfile##*/}\" --quiet 2>&1 | tail -20 || true; fi; fi"
}
]
}
],
"PreToolUse": [
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "file=$(echo \"$CLAUDE_TOOL_INPUT\" | jq -r '.file_path // .path // empty' 2>/dev/null); if [ -n \"$file\" ] && echo \"$file\" | grep -qiE '(application-prod|secrets|credentials|private-key)'; then echo '{\"decision\":\"block\",\"reason\":\"Production secret file edit blocked\"}'; exit 2; fi"
}
]
}
],
"Stop": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "root=$(git rev-parse --show-toplevel 2>/dev/null); if [ -n \"$root\" ] && [ -f \"$root/gradlew\" ]; then changed=$(git -C \"$root\" diff --name-only HEAD -- '*.kt' '*.kts' '*.java' 2>/dev/null); if [ -z \"$changed\" ]; then echo '[Hook] No source changes — skipping test gate'; exit 0; fi; cd \"$root\" && ./gradlew test --quiet 2>&1 | tail -5; result=$?; if [ $result -ne 0 ]; then echo 'Tests failed. Fix before ending session.'; exit 2; fi; fi"
}
]
}
]
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 108 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 10d ago First seen · 41 lines scan A 24e83cd6cf6c
sub-kopring-engineer is a plugin published in the GitHub repository brody-0125/my-claude-skills (2 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
shipwithai-java-backend-toolkit
Guardrail-first Spring Boot + JPA toolkit for Claude Code. Just-in-time hooks catch missing @Version, broken @Transactional proxies, entity-in-controller leaks, N+1, and query injection at the moment you write them; scaffold skills generate correct-by-default entities, endpoints, and migrations; a tuned reviewer agent.
android-dev-skills
Android, Kotlin, Java, Gradle, testing, and release workflows.
kora-v1
Kora Framework development skill for building production-grade Java/Kotlin services — with compile-time DI, HTTP, Database, Kafka, gRPC, SOAP, OpenAPI, Telemetry, AOP. Zero reflection, zero proxies, AI agent friendly. For Kora version 1.x.
kora-v2
Kora Framework development skill for building production-grade Java/Kotlin services — with compile-time DI, HTTP, Database, Kafka, gRPC, SOAP, OpenAPI, Telemetry, AOP. Zero reflection, zero proxies, synchronous contracts on virtual threads, AI agent friendly. For Kora version 2.x.
java-spring
Spring Boot scaffold skill and Spring expert agent for Java 8+ projects.
devco-agent-skills
Adaptive 5-layer workflow Claude Code plugin for Java Spring backend — 1% pre-flight discovery, triage routing, two-stage review, subagent dispatch, auto-evolution.