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 skills add vosslab/vosslab-skills --skill screenshot-docsgit clone --depth 1 https://github.com/vosslab/vosslab-skillsWrote 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/vosslab/vosslab-skills/screenshot-docs)<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/screenshot-docs"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/screenshot-docs/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/vosslab/vosslab-skills/screenshot-docs"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/screenshot-docs.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 | $0.00054 | $0.03087 |
| Opus 5 | $0.00027 | $0.01543 |
| Sonnet 5 | $0.00011 | $0.00617 |
| Haiku 4.5 | $0.00005 | $0.00309 |
Grade A, and why
screenshot-docs 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 8d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshot docs
Overview
Capture static screenshots or short animated demonstrations of an app and embed them
into README.md and docs/ files to make GitHub landing pages informative for
first-time visitors.
This skill runs in Wave 2 of the docset-updater refresh, after readme-docs
writes an empty managed screenshot block. It detects the app kind, chooses whether a
static state or short interaction best proves the project's value, captures with the
matching backend, stores the result under docs/screenshots/, and rewrites the inside
of that block with real embed lines.
Behavioral contract
This skill writes to:
- PNG and GIF files under
docs/screenshots/. - The managed screenshot block in
README.mdanddocs/files (the lines between the begin and end sentinels). - Reproducible capture infrastructure in the target repository's established support
location, such as
scripts/ortests/visual/.
Scope changes to documentation visuals, managed embed blocks, and their capture infrastructure. Treat app implementation code as read-only throughout. Prepare a changelog-ready summary for the caller or human maintainer to apply after capture.
Run the embed step idempotently: rewriting the block with the same captures yields identical output, so a repeat run against matching UI leaves files untouched. See the "Managed screenshot block" section in references/embedding.md for the exact format and replace algorithm.
In a headless or unavailable capture environment:
- Add a "Known gaps" line to the verification report noting that capture was skipped.
- Preserve existing screenshots and the existing managed block in place.
- Preserve both block sentinels for the next run.
- Continue with metadata, freshness, and verification steps supported by the current environment.
Wave role
In the docset-updater refresh, readme-docs runs in Wave 1 and screenshot-docs
runs in Wave 2:
readme-docsruns first and writes the empty managed block:<!-- screenshots:begin (managed by screenshot-docs) --><!-- screenshots:end -->
screenshot-docsruns as a second pass: captures visuals, writes PNGs or GIFs todocs/screenshots/, and rewrites the lines between the two sentinels with real embed lines, keeping the sentinels intact.
What ships with it
16 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.
- agents/openai.yaml 299 B
- references/capture_animation.md 6.1 KB
- references/capture_local.md 3.1 KB
- references/capture_web.md 4.3 KB
- references/detection.md 2.9 KB
- references/embedding.md 8.6 KB
- references/postprocess.md 4.7 KB
- scripts/capture_cli.sh 1.6 KB runs code
- scripts/capture_local.sh 1.7 KB runs code
- scripts/capture_region.sh 1.7 KB runs code
- scripts/install_playwright_capture.sh 1011 B runs code
- scripts/make_gif.sh 2.2 KB runs code
- scripts/mini_capture_window.sh 2.0 KB runs code
- scripts/render_artifact_libreoffice.sh 3.7 KB runs code
- scripts/screenshot_age.py 2.4 KB runs code
- scripts/screenshot_web.mjs 2.5 KB runs code
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.
- 8d ago First seen · 281 lines · 54 tokens per session scan A f1e4580b1ce8
screenshot-docs is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 12d ago), licensed MIT. It adds 54 tokens to every session and 3,087 once invoked, about $0.0003 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 2026-08-31.
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…