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 commands/jabrena/plinth/benchmarkgit clone --depth 1 https://github.com/jabrena/plinthWhat 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 | $0.00010 | $0.00438 |
| Opus 5 | $0.00005 | $0.00219 |
| Sonnet 5 | $0.00002 | $0.00088 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
benchmark 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.
What it actually says
benchmark
Select and coordinate an appropriate Java performance test with reproducible workload, environment, thresholds, and result artifacts.
Usage
/benchmark <target> [objective-or-threshold] [workload] [environment] [preferred-tool]
Accepted inputs
- Target application, endpoint, workflow, method, or component
- Performance objective or threshold
- Expected workload and environment
- Optional preferred tool
Owner and skills
- Owner:
@plinth-java-performance - Associated skills:
@151-java-performance-jmeter,@152-java-performance-gatling, and existing Maven/JMH guidance
Tool selection
| Need | Tool |
|---|---|
| HTTP/API load and performance test | JMeter or Gatling |
| Scenario-oriented load model and reports | Gatling |
| Isolated JVM method or component microbenchmark | JMH |
Workflow
- Clarify target boundary, objective, thresholds, workload, and environment.
- Select JMeter, Gatling, or JMH and record the rationale.
- Define warm-up, duration, concurrency, data setup, and result artifacts.
- Generate or coordinate the reproducible performance workflow using the selected skill or Maven/JMH guidance.
- Evaluate results against explicit thresholds.
- Report limitations, environment metadata, and whether results are comparable.
Output
- Selected tool and rationale
- Reproducible test configuration
- Baseline or result artifacts
- Threshold assessment
- Limitations and environment metadata
Safeguards
- Do not present non-equivalent runs as valid before/after comparisons.
- Do not use JMeter or Gatling for isolated JVM microbenchmarks when JMH is the correct boundary.
- Do not use JMH for end-to-end load behavior.
- Keep workload, environment, and threshold assumptions explicit.
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 · 66 lines · 10 tokens per session scan A d02a1835bec6
benchmark is a command published in the GitHub repository jabrena/plinth (435 stars, last pushed yesterday), licensed Apache-2.0. It adds 10 tokens to every session and 438 once invoked, about $0.0001 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 commands, from other repositories
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.
proof-driven-development
A disciplined workflow for ambiguous, high-stakes tasks — assess, post proof-tagged assumptions, lock a testable goal, plan as TDD, build via subagents with two-stage review, prove with a live end-to-end run, and flag gaps honestly. Use when starting a vague ticket or a feature that touches auth, identity, money, or…
build
Implement the next ready task from .forge/tasks.yaml using TDD discipline.
ai-do
You are a routing assistant for DSPy AI skills. Understand the user's problem, pick the best skill, and generate a ready-to-run prompt.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.