Borrowing it
Nothing to install: this file belongs to dzhng/duet-agent. 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/dzhng/duet-agent/main/.agents/skills/screenshot-critique/SKILL.mdgit clone --depth 1 https://github.com/dzhng/duet-agentWrote 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/dzhng/duet-agent/screenshot-critique)<a href="https://agentmods.dev/skills/dzhng/duet-agent/screenshot-critique"><img src="https://agentmods.dev/badge/skills/dzhng/duet-agent/screenshot-critique/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/dzhng/duet-agent/screenshot-critique"><img src="https://agentmods.dev/badge/skills/dzhng/duet-agent/screenshot-critique.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 | $0.00052 | $0.02242 |
| Opus 5.5 | $0.00021 | $0.00897 |
| Sonnet 5.5 | $0.00010 | $0.00448 |
| Haiku 4.5 | $0.00005 | $0.00224 |
Grade A, and why
screenshot-critique 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 13d 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.
This is a copy
88% identical to screenshot-critique — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshot Critique
Use an unprimed sub-agent as a second set of eyes before accepting visual work.
This is for visual defects, not pixel metrics; pair it with
compare-screenshots when you also need numbers — including on a single shot
with nothing to compare against, whose scene metrics say whether the frame has
any content in it at all.
Workflow
- Capture or locate the exact PNGs/GIF frames under review.
- Keep native-size evidence and create supplementary 2x-4x crops for every key feature, plus the full screenshot. Include complete endpoints and fades; recheck crop bounds after geometry changes. Crop selected units, city/town stacks, flags/poles, shadows, selection rings, labels/icons, roads, terrain features, water, and any artifact-prone area. If the complaint is about "too faint", "wrong order", or "not in perspective", the crop is mandatory.
- Spawn one fresh explorer with
fork_context: false; pass only the full images, the crops, and a short neutral task. Include the approved reference and user requirements when judging fidelity; withhold history, implementation details, prior verdicts and the expected answer. - Ask for concrete visible defects with confidence levels. Name likely risk categories: unit/prop depth ordering, layering, shadows, selection-marker contrast, ground-plane perspective, flag/pole attachment, label style and icon readability, blur, scale, lighting, artifacts, missing models, terrain feature readability, roads, water, and overall scan readability.
- Run the returned critique through
scripts/receipts.mjs. Every number it flags is a claim the critique cannot show a command for, and every file it flags is one the critique named but never wrote; strike those claims or re-measure them yourself before any of them reach a decision. - Compare the sub-agent's critique against your own inspection. Treat overlap as high-priority evidence. Treat novel high-confidence findings as bugs to inspect, not as taste notes to dismiss.
- Record actionable findings in the spec, visual report, or next task plan before claiming the screenshot is accepted.
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.
- 13d ago Changed · +58 lines eb7f20c4735d
- 25d ago Changed · +18 lines 4d40d601e035
- 1mo ago First seen · 92 lines · 52 tokens per session scan A b5ac771eb25f
screenshot-critique is a skill published in the GitHub repository dzhng/duet-agent (52 stars, last pushed 7d ago), licensed Apache-2.0. It adds 52 tokens to every session and 2,242 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to screenshot-critique, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
web-design
Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.
a2ui
Make a reply easier to read and act on with rich blocks inside ordinary Markdown — a choice the user picks from, a form that collects several answers, a procedure as steps with warnings in place, a callout, a Mermaid diagram, a weather card, a live clock or countdown, a dashboard of gauges for a quota, a budget or a…
bento-slides
Create and edit Bento presentations — self-contained .bento.html decks whose document is JSON. Use whenever the user wants a slide deck or presentation: from scratch, from source material, or by improving an existing file.
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, UI mockups, product shots, or transparent-background cutouts. Use when the result should be an image asset rather than repo-native SVG, HTML/CSS, or canvas.
ui-ux-pro-max
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design…