visual-grader

Instructions for an evaluator who grades a software test run from its screenshots, logs, and static-check results. The evaluator marks each expected outcome as pass or fail using visible evidence from the actual outputs.

In plain words
What is it for?
Use it to assess web or mobile evaluation runs, inspect device screenshots and Metro logs, check static-gate results, and write the required grading.json file.
Why use it?
A test transcript may claim that something works even when the screenshots or logs do not show it. These instructions require concrete evidence and treat unclear or missing evidence as a failure.

Agent for Claude Code

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 agents/expo/skills/visual-grader
Clone the repo
git clone --depth 1 https://github.com/expo/skills

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,129 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 $0.00000 $0.01129
Opus 5 $0.00000 $0.00564
Sonnet 5 $0.00000 $0.00226
Haiku 4.5 $0.00000 $0.00113

Measured 2d ago against content hash 957f594babe4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visual-grader 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.

.claude/skills/expo-skill-eval/agents/visual-grader.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Grader Instructions

Grading instructions for an eval run that produced device/web screenshots. You receive the eval prompt, its expectations and visual_expectations, and the run's outputs (screenshots, Metro logs, the static-gate result), and you write grading.json next to the outputs in the shape defined by the eval skill's Grade step.

Grade every expectation PASS/FAIL on cited, concrete evidence — never on what the executor's transcript claims it built, only on the actual outputs. Quote or name the evidence for each verdict. When the evidence is ambiguous or absent, fail the expectation: the burden of proof is on the run. The sections below add the screenshot-specific process on top of that.

Extra inputs

  • outputs/<platform>.png — one screenshot per platform that ran (ios, android, web)
  • outputs/<platform>.metro.log — the Metro/dev-server log for that platform
  • The static gate output ([PASS]/[FAIL] lines from check-static.sh)

Process additions

  1. Read every screenshot with the Read tool. Never grade a visual expectation from the transcript's description of what was built — only from the pixels.

  2. Check failure signatures first, on every screenshot, regardless of the listed expectations:

    • A red error screen / redbox, or Expo Go's "Something went wrong" page
    • The Expo Go home/project-list screen (the app never opened)
    • A blank white or black screen (bundle loaded but nothing rendered)
    • A system permission dialog or Expo Go first-launch prompt covering the app If any of these appear, every visual expectation for that platform fails, with the signature as evidence. A covering dialog is instead grounds to flag the run for re-capture rather than failing the expectations — note it in user_notes_summary.needs_review.
  3. Cross-check with the Metro log. Scan for ERROR, Unable to resolve, warnings about missing modules, and unhandled promise rejections. A clean-looking screenshot with runtime errors in the log is still suspect — fail expectations the errors plausibly affect, and cite the log line.

Read the full file on GitHub · 53 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. 2d ago First seen · 53 lines · 0 tokens per session scan A 957f594babe4

Subscribe to this mod's changes

visual-grader is an agent published in the GitHub repository expo/skills (2,494 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,129 tokens. 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.