run-evals

run-evals is a skill for Claude Code, Codex from lycorp-jp/sim-use. It costs 99 tokens per session (1,410 once invoked), scanned A, original, Apache-2.0.

A runner for end-to-end tests of coding-agent skills. It has an AI agent use a skill against sample apps, then checks whether the expected results happened.

In plain words
What is it for?
Use it before release to evaluate a skill, choose the program version under test, run the documented evaluation cases, and detect mismatches between instructions and behavior.
Why use it?
It tests whether an agent can follow the written instructions in realistic tasks, including problems that ordinary scripted tests may miss.

Skill for Claude CodeCodex

About the project

lycorp-jp/sim-use is a command-line tool that lets AI agents observe and control iOS simulators, Android emulators, and devices through accessibility information and input actions. It helps agents test mobile applications by reading compact screen descriptions and interacting with named elements, while the catalogue skills and instructions teach agents how to use those capabilities.

lycorp-jp/sim-use · 1,310 stars · on GitHub

Install

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.

agentmods
npx agentmods add skills/lycorp-jp/sim-use/run-evals
Any agent
npx skills add lycorp-jp/sim-use --skill run-evals
Clone the repo
git clone --depth 1 https://github.com/lycorp-jp/sim-use

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for run-evals

README.md
[![agentmods](https://agentmods.dev/badge/skills/lycorp-jp/sim-use/run-evals.svg)](https://agentmods.dev/skills/lycorp-jp/sim-use/run-evals)
Your own site
<a href="https://agentmods.dev/skills/lycorp-jp/sim-use/run-evals"><img src="https://agentmods.dev/badge/skills/lycorp-jp/sim-use/run-evals.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,410 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00099 $0.01410
Opus 5 $0.00049 $0.00705
Sonnet 5 $0.00020 $0.00282
Haiku 4.5 $0.00010 $0.00141

Measured 5d ago against content hash 9c6cd37f756f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run-evals 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 5d 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.

.agents/skills/run-evals/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This skill orchestrates the agent-eval suite: natural-language cases executed by a headless claude -p agent using the bundled skill (skills/sim-use/) against the Playground fixture apps, judged by deterministic post-condition checks. It verifies the layer the scripted E2E suites cannot: that an agent reading SKILL.md reaches for the right verbs and survives the documented pitfalls. A failure here with a green scripted layer usually means skill-prose drift, not a CLI bug.

Execution is delegated to scripts/eval.sh / e2e/agent-evals/run.py — do not reimplement their logic. Case anatomy, tags, and authoring rules live in e2e/agent-evals/README.md. Run from the repo root.

Step 1: Decide WHICH sim-use is under test

The whole run — device probing, the agent's commands, the verification layer — resolves sim-use from PATH unless overridden. Never let this be implicit:

  1. Ask (or infer from the user's request) which binary to evaluate:
    • Installed release (default): whatever sim-use resolves to on PATH.
    • A development build: pass -b <path>, e.g. -b .build/out/Products/Debug/sim-use (SwiftBuild layout) or -b .build/debug/sim-use (classic). Build it first with make build.
  2. Confirm the resolution and report it to the user before running:
    python3 -c 'import pathlib,shutil; print(pathlib.Path(shutil.which("sim-use")).resolve())'
    sim-use --version
    
    The wrapper prints sim-use under test: <real path> (<version>) and the run report records it under sim-use under test: — quote that line back in your summary so the human knows exactly what was evaluated.

Step 2: Prepare devices and fixtures

For each platform you intend to cover (the wrapper auto-detects reachable ones; use -p ios|android to restrict):

iOS

  1. Device Hub (Xcode 27) must be CLOSED — pgrep dtuhidd must be empty. A simulator booted while Device Hub is open has legacy HID disconnected; sim-use's guard will (correctly) fail every case on it. If dtuhidd is running: quit Device Hub, then shutdown && boot the simulator.
  2. Boot a simulator and wait: xcrun simctl boot <UDID> && xcrun simctl bootstatus <UDID>.
  3. The Playground fixture must be installed. Check: xcrun simctl listapps <UDID> | grep -c com.cameroncooke.SimUsePlayground — if missing, install with scripts/test-runner.sh -b (builds sim-use + Playground, ~2-3 min).

Read the full file on GitHub · 106 lines

Changes

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.

  1. 5d ago First seen · 106 lines · 99 tokens per session scan A 9c6cd37f756f

Subscribe to this mod's changes

run-evals is a skill published in the GitHub repository lycorp-jp/sim-use (1,310 stars, last pushed yesterday), licensed Apache-2.0. It adds 99 tokens to every session and 1,410 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

expect

Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…

yonatangross/orchestkit · 73 tokens

Accessibility Auditor

Comprehensive WCAG 2.1 AA compliance testing combining automated axe-core scans with manual keyboard navigation, screen reader compatibility, and focus management verification.

PramodDutta/qaskills · 32 tokens

accessibility

Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries…

yonatangross/orchestkit · 65 tokens

design-ship

One-shot pipeline turning a claude.ai/design link into a pull request: scaffold via /ork:design-import, stories and specs via /ork:cover, browser verification via /ork:expect, then open the PR. Use when a design link should come back as a PR with no intermediate steps; if all you need is the components written to…

yonatangross/orchestkit · 84 tokens

Axe-core Accessibility Testing

Accessibility testing skill using axe-core and Playwright for automated WCAG 2.1 compliance auditing, custom rules, and accessibility reporting.

PramodDutta/qaskills · 33 tokens

Testing Coach

Accessibility testing coach for web applications. Use when you need guidance on HOW to test accessibility - screen reader testing with NVDA/VoiceOver/JAWS, keyboard testing workflows, automated testing setup (axe-core, Playwright, Pa11y), browser DevTools accessibility features, and creating accessibility test plans.…

Community-Access/accessibility-agents · 76 tokens