Borrowing it
Nothing to install: this file belongs to udecode/plate. 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/udecode/plate/next/.agents/skills/benchmark/SKILL.mdgit clone --depth 1 https://github.com/udecode/plateWrote 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/udecode/plate/benchmark)<a href="https://agentmods.dev/skills/udecode/plate/benchmark"><img src="https://agentmods.dev/badge/skills/udecode/plate/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/udecode/plate/benchmark"><img src="https://agentmods.dev/badge/skills/udecode/plate/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 | $0.00078 | $0.02853 |
| Opus 5.5 | $0.00031 | $0.01141 |
| Sonnet 5.5 | $0.00016 | $0.00571 |
| Haiku 4.5 | $0.00008 | $0.00285 |
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 today.
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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
9 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.
- references/autoresearch.md 4.9 KB
- references/methodology.md 10 KB
- references/performance-review.md 15 KB
- scripts/benchmark-contract.test.mjs 40 KB runs code
- scripts/paired-timing.mjs 17 KB runs code
- scripts/paired-timing.test.mjs 26 KB runs code
- scripts/validate-benchmark-plan.mjs 44 KB runs code
- templates/benchmark.md 6.7 KB
- templates/performance-observability.md 3.7 KB
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.
- today Changed · +5 lines 56047f311cae
- 3d ago Changed · +1 lines 1641acc37af1
- 4d ago Changed · +1 lines · +1 tokens per session 321497a7cf33
- 11d ago Changed · +159 lines · +41 tokens per session d47eced311ee
- 12d ago Changed · +1 lines 1325517793ee
- 16d ago First seen · 43 lines · 36 tokens per session scan A f6a96ce3dd51
benchmark is a skill published in the GitHub repository udecode/plate (16,680 stars, last pushed today), with no licence file. It adds 78 tokens to every session and 2,853 once invoked, about $0.0003 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 2026-10-13.
Other skills, from other repositories
testing
Skill "testing" from udecode/plate-playground-template, covering testing goal, core rules, seam selection, fixtures and assertions and quick reference.
server-side-calls
Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.
walkeros-using-cli
Use when bundling walkerOS flows, testing events with simulate/push, running or deploying a built flow (runneros, the walkeros/flow image), validating configs, or configuring Flow JSON files.
walkeros-using-step-examples
Use when writing, simulating, validating, or testing with walkerOS step examples. Covers the complete lifecycle from authoring examples to CI integration.
walkeros-testing-strategy
Use when writing tests, reviewing test code, or discussing testing approach for walkerOS packages. Covers env pattern, dev examples, and package-specific strategies.
creating-online-evaluations
Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified. Use when the user wants evaluations that automatically score new generations or whole traces going forward — "create an eval to catch X", "continuously check that responses do Y", "turn these…