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.
npx agentmods add skills/generous-corp/pulp/screenshotnpx skills add Generous-Corp/pulp --skill screenshotgit clone --depth 1 https://github.com/Generous-Corp/pulpWrote 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/generous-corp/pulp/screenshot)<a href="https://agentmods.dev/skills/generous-corp/pulp/screenshot"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/screenshot.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.06975 |
| Opus 5 | $0.00037 | $0.03488 |
| Sonnet 5 | $0.00015 | $0.01395 |
| Haiku 4.5 | $0.00007 | $0.00698 |
Grade A, and why
screenshot 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.
How it starts
The opening of the file, as written. The whole thing — 480 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshotting Pulp UIs
Pulp has two headless capture surfaces plus the live-host capture. Picking the wrong one wastes time on renders that look broken but aren't.
Default to capture_view / --backend auto — it picks the backend for you
Don't hand-pick a backend unless you have a reason. capture_view(root, w, h, scale) (screenshot.hpp) and the CLI default pulp-screenshot --backend auto
inspect the view tree and do the right thing, and never return a silent blank:
| The view tree… | …gets | Why |
|---|---|---|
has a contains_native_overlay() subtree (a WebView / native NSView) |
the overlay's in-process snapshot (View::capture_native_overlay_png → e.g. WKWebView takeSnapshot); refused with a reason only if no snapshot is available |
A WebKit/native overlay is composited by the OS, NOT painted into the Pulp canvas — headless raster can't see it, but a backend that exposes an in-process snapshot can still be captured |
has a requires_gpu_host() view (GPU content, custom SkSL) |
the gpu path (render_to_png_gpu, offscreen Dawn+Skia via HeadlessSurface) |
CPU raster does NOT render GPU-required views correctly — they come out blank/wrong |
| neither | CPU raster (skia when Skia is built, else the platform default_backend / a registered provider) |
fast, faithful for vector + image widgets |
capture_view returns {png, ok, used, reason}; a blank/essentially-empty frame
sets ok=false. The CLI exits 3 (not a saved blank) on refuse/blank. This is the
"always-capturable" contract — if a UI didn't paint, you get told, not a blank PNG.
Wrappers must opt in. A WebView is only captured/refused correctly when the
owning Pulp View actually sets set_contains_native_overlay(true) and overrides
capture_native_overlay_png() to forward WebViewPanel::snapshot_png(). Without
that flag, auto rasters the (blank) overlay area silently — set it on any
wrapper that attaches a native child via attach_native_child_view (see
examples/webview-plugin WebViewEditorPane).
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 First seen · 480 lines · 74 tokens per session scan A 7e5454afe9e8
screenshot is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 6,975 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…