Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/google-ai-edge/litert-samplesnpx agentmods add skills/google-ai-edge/litert-samples/benchmark-on-ddpWrote 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/google-ai-edge/litert-samples/benchmark-on-ddp)<a href="https://agentmods.dev/skills/google-ai-edge/litert-samples/benchmark-on-ddp"><img src="https://agentmods.dev/badge/skills/google-ai-edge/litert-samples/benchmark-on-ddp/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/google-ai-edge/litert-samples/benchmark-on-ddp"><img src="https://agentmods.dev/badge/skills/google-ai-edge/litert-samples/benchmark-on-ddp.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 | $0.00124 | $0.01748 |
| Opus 5.5 | $0.00050 | $0.00699 |
| Sonnet 5.5 | $0.00025 | $0.00350 |
| Haiku 4.5 | $0.00012 | $0.00175 |
Grade A, and why
benchmark-on-ddp 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 9d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Benchmark on DDP
A board row is done when three things hold:
- it comes from the
results.pbof one benchmark job, with the delegate and the nodes it replaced (N/M) from that job'sruntime_info.pb, or from the log'sReplacing N out of Mline where a session has no such file, - it names the model file, the platform, the device id, the accelerator and the
benchmark_modelrelease, data/board.jsonwas rebuilt fromdata/measurements.jsonland the page shows it.
A number without those is not a row. This skill covers .tflite models on LiteRT; a LiteRT-LM
bundle is one litert benchmark <bundle>.litertlm --ddp session per backend, collected by collect_lm.py (the board README, step 5). Every DDP session consumes device time billed to the Google Cloud project; the dry run prints every command it would run, so read it first. A run on the Mac you are on bills nothing.
Before you start
python3with PyYAML, andprotocon PATH (brew install protobuf, orapt install protobuf-compiler).- For new DDP sessions:
gcloud auth application-default login, a project with the Device Run API enabled (run_matrix.py --gcp-projectorLITERT_GCP_PROJECT), and thelitertCLI of LiteRT-CLI with the--ddptarget (release 0.2.1 or newer;litert-cli-nightlyhas it too). Its DDP runs default to the LiteRT 2.2.0benchmark_model(0.2.1); a row carries the version the job ran:
pip install litert-cli
- For rows from a macOS host (Apple silicon;
run_local.pyexits on any other machine): nothing more; it fetches the macOS binary of the pinned release.
Loop
Work from the board folder, cd benchmark/leaderboard; every command below is relative to it, and the driver sits in ../driver/.
1. One model, one matrix entry. In ../driver/matrix.yaml add repo (the Hugging Face repo), file (one .tflite; a repo with several variants gets one entry per
variant you want on the board), task (the repo's pipeline tag) and accelerators. Platforms and DDP devices are listed once under platforms.
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.
- 9d ago Changed 01387cc72e20
- 23d ago Changed e9ae6626c200
- 28d ago Changed 3d00a0718729
- 29d ago First seen · 86 lines · 124 tokens per session scan A 2b7b4dbf6ab4
benchmark-on-ddp is a skill published in the GitHub repository google-ai-edge/litert-samples (464 stars, last pushed yesterday), licensed Apache-2.0. It adds 124 tokens to every session and 1,748 once invoked, about $0.0005 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 2026-09-18.
Other skills, from other repositories
flutter-idioms
Flutter idioms: Riverpod 3 state management, Freezed immutable models, gorouter navigation, const widget optimization, and repository patterns. Use when developing, refactoring, or reviewing Flutter mobile applications.
swift-idioms
Swift idioms and best practices: value types, Optionals hygiene, protocol-oriented design, async/await and Actor concurrency, and XCTest. Use when writing, refactoring, or reviewing Swift iOS, macOS, or server-side code.
mobile-testing
Mobile E2E testing patterns — Flutter integrationtest, Patrol, Maestro, golden testing, device matrix, and test data management. Use when writing E2E tests for mobile applications.
mobile-design
Generates distinctive, production-grade mobile interfaces for Flutter and React Native. Prioritizes platform-native patterns, adaptive layouts, and fluid motion. Use when building mobile apps, screens, widgets, or when the user requests to style or create visually striking mobile UI.
test-e2e
Plans, authors, and executes end-to-end tests for mobile and web platforms. User-invoked entry point via /test-e2e; not for autonomous or subagent use.
dart-expert
Expert-level Dart, Flutter, mobile development, and cross-platform apps. Use when the user mentions Flutter, mobile, cross platform, or widgets, or when the task involves Dart Language or Flutter Framework.