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 skills/voidmatcha/ui-clone-skills/benchmarknpx skills add voidmatcha/ui-clone-skills --skill benchmarkgit clone --depth 1 https://github.com/voidmatcha/ui-clone-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/skills/voidmatcha/ui-clone-skills/benchmark)<a href="https://agentmods.dev/skills/voidmatcha/ui-clone-skills/benchmark"><img src="https://agentmods.dev/badge/skills/voidmatcha/ui-clone-skills/benchmark.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 | $0.00152 | $0.08531 |
| Opus 5 | $0.00076 | $0.04265 |
| Sonnet 5 | $0.00030 | $0.01706 |
| Haiku 4.5 | $0.00015 | $0.00853 |
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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 678 lines — stays where its author put it; the contents beside it link to each section on GitHub.
benchmark — local regression / benchmark skill
⚡ Activation sentinel (READ FIRST)
The FIRST RESPONSE you generate after reading this file in reaction to a "run benchmark" / "regression benchmark" / "benchmark clone" trigger MUST begin with the exact line below — no decoration, no preamble, no header above it:
[BENCHMARK-SKILL-ACTIVE v1 / skills/benchmark/SKILL.md]
Concretely: the response that comes right after the tool-result of your
Read(skills/benchmark/SKILL.md). Reading this file IS the start of
execution; do not defer the sentinel to a later "more real" response, do
not announce the rule in prose instead of emitting the token, do not
prepend a step heading. The first line of that response is the token
itself, and only the token. Anything else (Step 1 announcement,
bash skills/benchmark/scripts/setup.sh call, status notes) goes
below it on subsequent lines.
Only that one response needs the sentinel — later responses in the same session do not need to repeat it. Empirically, LLMs drop a per-message prepend after a few turns even when the rule says "every response," so a single emission anchored to the post-read response is the reliable signal the maintainer checks.
Edge case — tool-only first turn. If the response immediately after the
SKILL.md Read would otherwise contain only a tool call with no text (e.g.
you decide to dispatch bash skills/benchmark/scripts/setup.sh without
saying anything), prefix that turn with the sentinel as a one-line text
message before the tool call. The text-only line is the sentinel; the
tool dispatch follows on the next line. Do not skip the sentinel just
because the turn would have been silent.
Maintainer-shell note. In some maintainer environments ls is aliased
to eza, where ls -t fails with -t needs a value (modified|...).
Inside benchmark commands prefer the portable forms \ls -1t,
/bin/ls -t, or find ... -printf '%T@ %p\n' | sort -rn instead of
bare ls -t so the pipeline doesn't break on the maintainer's shell.
What ships with it
2 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.
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 First seen · 678 lines · 152 tokens per session scan A 46331b10e05c
benchmark is a skill published in the GitHub repository voidmatcha/ui-clone-skills (8 stars, last pushed 4d ago), licensed Apache-2.0. It adds 152 tokens to every session and 8,531 once invoked, about $0.0008 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 skills, from other repositories
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes. Use for smoke, e2e, Playwright, or pre-ship browser verification.
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…
browser-use
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.
unit-test
기능 단위 테스트 오케스트레이터. Git Diff/사용자 지정 범위에서 테스트 대상을 결정하고, 사용자 시나리오 스토리보드 → 테스트케이스 생성 → Playwright MCP 실행 → 결과 보고. '/unit-test', '단위테스트', '테스트해줘', '기능 테스트' 등 언급 시 호출. 시나리오 단위 회귀 검증(PASS/FAIL/WARN)에 사용하며, 버그 원인 특정·로그 삽입 디버깅이 필요하면 debugger 계열 스킬을 쓴다.
test-fixture-creation
Guidelines for creating unbiased test fixtures that integrate with project infrastructure. Use when creating fixtures for manual testing, setting up E2E test scenarios, or building code samples with deliberate issues for LLM review. Ensures fixtures work with hook automation and pass Phase 1 checks.
e2e-route
Pure dispatcher: picks the right E2E executor for a Swift test request from context (platform × intent × verification kind) and hands off. Routes to the scaffold/MCP-sim/QA/design-review skills.