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/rlaope/claude-code-savantWrote 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/commands/rlaope/claude-code-savant/savant-jvm)<a href="https://agentmods.dev/commands/rlaope/claude-code-savant/savant-jvm"><img src="https://agentmods.dev/badge/commands/rlaope/claude-code-savant/savant-jvm.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 | $0.00008 | $0.00167 |
| Opus 5 | $0.00004 | $0.00084 |
| Sonnet 5 | $0.00002 | $0.00033 |
| Haiku 4.5 | $0.00001 | $0.00017 |
Grade A, and why
savant-jvm 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 8d 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
JVM Optimization - JVM Developer
$ARGUMENTS
Your Task
Analyze the provided code or question using the JVM Developer (JVM Performance Expert) persona.
Execution
Delegate to JVM Developer agent:
Task tool:
- subagent_type: "claude-code-savant:jvm-developer"
- prompt: [User's JVM optimization request]
Response Requirements
JVM Developer will provide:
- Performance profiling analysis (GC logs, JFR, async-profiler)
- Bottleneck identification at JVM runtime level
- Before/after code with benchmark expectations
- GC tuning, JIT, memory, and concurrency recommendations
- Runtime-specific explanations (why at the JVM internals level)
Return the agent's analysis directly to the user.
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.
- 8d ago First seen · 33 lines · 8 tokens per session scan A ed0af26a75e1
savant-jvm is a command published in the GitHub repository rlaope/claude-code-savant (2 stars, last pushed 6mo ago), licensed MIT. It adds 8 tokens to every session and 167 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
profile
Coordinate a reproducible Java profiling and optimization lifecycle.
openrewrite-violations
Fix each violated OpenRewrite recipe in its own commit on an openrewrite-violations branch.
scaffold-spring-api
Scaffold a new Spring Boot 3.5.x WebFlux REST API project with standard structure, build config, and sample endpoint.
java-exercise-pattern
A command for creating a new exercise about software design patterns or SOLID principles. SOLID is a group of principles for structuring object-oriented code.
java-exercise-fix
A code-fixing command for a Java exercise that explains the correction and adds a memory aid.
checklist
Generate a custom checklist for the current feature based on user requirements.