Borrowing it
Nothing to install: this file belongs to tbvjvsladla/easy_vllm_simulator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tbvjvsladla/easy_vllm_simulator/single-node/.claude/skills/adversarial-benchmark/SKILL.mdgit clone --depth 1 https://github.com/tbvjvsladla/easy_vllm_simulatorWrote 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/tbvjvsladla/easy_vllm_simulator/adversarial-benchmark)<a href="https://agentmods.dev/skills/tbvjvsladla/easy_vllm_simulator/adversarial-benchmark"><img src="https://agentmods.dev/badge/skills/tbvjvsladla/easy_vllm_simulator/adversarial-benchmark/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/tbvjvsladla/easy_vllm_simulator/adversarial-benchmark"><img src="https://agentmods.dev/badge/skills/tbvjvsladla/easy_vllm_simulator/adversarial-benchmark.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00271 | $0.08343 |
| Opus 5 | $0.00135 | $0.04172 |
| Sonnet 5 | $0.00054 | $0.01669 |
| Haiku 4.5 | $0.00027 | $0.00834 |
Grade A, and why
adversarial-benchmark scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 승격 게이트 | 성능 판정 `verdict == PASS`(미달 시 `perf_waiver`) | **서빙 성립(기능)** = 모델이 실제로 떠서 curl 통신으로 응답을 낸다 **∧ 유효 측정**(`floor > 0` ∧ `ratio ≠ null`) | The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
33 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- bench_tool_pin.json 2.5 KB
- config.example.yaml 2.7 KB
- fixtures/guidellm_benchmarks_sample.json 96 KB
- fixtures/max_index_sample.json 915 B
- fixtures/measured_pass.json 495 B
- fixtures/measured_refute_no_mtp.json 494 B
- fixtures/roofline_sample.json 111 B
- fixtures/sweep_index_sample.json 2.6 KB
- references/lite-and-publication.md 8.1 KB
- references/max-envelope.md 3.2 KB
- references/rubric-and-lenses.md 8.0 KB
- scripts/broad_search.sh 34 KB runs code
- scripts/classify_cell.py 13 KB runs code
- scripts/conformance_full_superset_lite.py 4.6 KB runs code
- scripts/doc_naming.py 11 KB runs code
- scripts/judge_bench.sh 10 KB runs code
- scripts/lite_bench.sh 10 KB runs code
- scripts/lite_metrics.py 12 KB runs code
- scripts/max_envelope.sh 12 KB runs code
- scripts/parse_bench.py 3.8 KB runs code
- scripts/parse_guidellm.py 29 KB runs code
- scripts/publish_benchmark_record.py 14 KB runs code
- scripts/render_max_report.py 5.6 KB runs code
- scripts/render_report.py 11 KB runs code
- scripts/render_sweep_map.py 14 KB runs code
- scripts/resolve_bench_tool.py 13 KB runs code
- scripts/resolve_guidellm.py 9.9 KB runs code
- scripts/roofline.py 16 KB runs code
- scripts/run_bench.sh 23 KB runs code
- scripts/selftest_sweep_meta.py 12 KB runs code
- scripts/sweep_bench.sh 47 KB runs code
- scripts/sweep_stop.py 18 KB runs code
- scripts/verdict_rule.py 42 KB runs code
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.
- 4d ago Changed · +9 lines 4d415d3ffefb
- 5d ago Changed 12277e229a06
- 10d ago First seen · 181 lines · 271 tokens per session scan A 7af2a68769fa
adversarial-benchmark is a skill published in the GitHub repository tbvjvsladla/easy_vllm_simulator (20 stars, last pushed yesterday), with no licence file. It adds 271 tokens to every session and 8,343 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.