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 ktwu01/benchmark-radar --skill benchmark-radar-replygit clone --depth 1 https://github.com/ktwu01/benchmark-radarWrote 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/ktwu01/benchmark-radar/benchmark-radar-reply)<a href="https://agentmods.dev/skills/ktwu01/benchmark-radar/benchmark-radar-reply"><img src="https://agentmods.dev/badge/skills/ktwu01/benchmark-radar/benchmark-radar-reply/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/ktwu01/benchmark-radar/benchmark-radar-reply"><img src="https://agentmods.dev/badge/skills/ktwu01/benchmark-radar/benchmark-radar-reply.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 | $0.00028 | $0.00319 |
| Opus 5.5 | $0.00011 | $0.00128 |
| Sonnet 5.5 | $0.00006 | $0.00064 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
benchmark-radar-reply 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 Radar replies
The customer is the email sender. Answer their question first, then make these asks:
- Cite and credit Benchmark Radar, with a link, everywhere they use it.
- If they publish a paper, cite our paper: https://arxiv.org/abs/2609.11115
- Share Benchmark Radar with friends and colleagues.
- Join our Discord to promote and sell their open-source tools: https://discord.gg/rXqS38mkN
Ask 4 is the hook. Make it specific to their tools.
License
Read the terms from upstream main, not a local copy: git fetch origin main, then git show origin/main:LICENSE-CONTENT.md. If you cannot, tell the user the terms are unverified.
As of 2026-10-13:
- Software: MIT.
- Report and editorial content: CC BY-NC-SA 4.0. Commercial reuse needs written permission from Koutian Wu.
- Third-party data: its original terms.
Do not grant new permissions. The Discord invite does not grant commercial reuse of our content.
Deliver
Return a short, sendable email. See the Dave example. Do not send it unless the user asks.
Links: https://benchmark-radar.org/ · cite formats https://benchmark-radar.org/cite/
What ships with it
1 file 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.
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 · 34 lines · 28 tokens per session scan A a1b53d784b03
benchmark-radar-reply is a skill published in the GitHub repository ktwu01/benchmark-radar (294 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 319 once invoked, about $0.0001 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 2026-10-14.
Other skills, from other repositories
ai-prompt-regression-testing
Use when comparing prompt changes against a fixed evaluation set: record actual model settings, required checks, missing results, judge limitations and case-level regression evidence.
evaluating-code-models
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
nemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
connect-agent
Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
api-transports
Declare a REST route, a tRPC procedure or an SSE/subscription stream on a module: defineRestRouter, defineTrpcRouter, defineTrpcContract, .withInput/.withOutput/.withPermission/.withDocs, /api/ paths (/v1 optional), framework-owned validation (malformedrequest 400 vs validationerror 422), throwing a HandledError, why…