github-screenshot

github-screenshot is a skill for Claude Code from jerseycheese/agent-skills. It costs 67 tokens per session (1,261 once invoked), scanned A, original, MIT.

A coding-agent skill that turns screenshots into Markdown image links using raw GitHub file URLs. It also describes where temporary screenshots for GitHub discussions should be stored.

In plain words
What is it for?
Use it when adding screenshots to GitHub pull requests, issues, or Markdown documentation.
Why use it?
It avoids manually constructing image links and gives screenshot files a consistent, easy-to-clean location for pull requests, issues, and documentation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is <!-- Local path: ./github-screenshots/dashboard-before.png -->.

Part of the workflow-skills plugin — 34 skills shipped together

Good fit Use it when adding screenshots to GitHub pull requests, issues, or Markdown documentation.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/jerseycheese/agent-skills
agentmods
npx agentmods add skills/jerseycheese/agent-skills/github-screenshot

Made for: Claude Code.

Or install workflow-skills, the plugin that ships this one along with the rest of its 34 skills.

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 github-screenshot

README.md
[![agentmods](https://agentmods.dev/badge/skills/jerseycheese/agent-skills/github-screenshot/github.svg)](https://agentmods.dev/skills/jerseycheese/agent-skills/github-screenshot)
Your own site
<a href="https://agentmods.dev/skills/jerseycheese/agent-skills/github-screenshot"><img src="https://agentmods.dev/badge/skills/jerseycheese/agent-skills/github-screenshot/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.

agentmods 80×15 button for github-screenshot

Your own site · 80×15
<a href="https://agentmods.dev/skills/jerseycheese/agent-skills/github-screenshot"><img src="https://agentmods.dev/badge/skills/jerseycheese/agent-skills/github-screenshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,261 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00067 $0.01261
Opus 5.5 $0.00027 $0.00504
Sonnet 5.5 $0.00013 $0.00252
Haiku 4.5 $0.00007 $0.00126

Measured 4d ago against content hash b26bda358dfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github-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 4d 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.

skills/github-screenshot/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Screenshot Helper

When to Use This Skill

Use this skill when:

  • Adding screenshots to PR descriptions
  • Including images in GitHub issues
  • Documenting features with screenshots
  • Creating visual documentation in markdown

Setup

This skill wraps a local generate-github-image-markdown.sh script. Update the path below to match your own installation before using.

Directory convention

When the image is being committed purely so it can render in an issue/PR body (not an existing app asset the user is pointing you at), commit it under a top-level github-screenshots/<topic-or-issue>/ directory — e.g. github-screenshots/hover-text-invisible/before-hover.png. The name says what these files are for: throwaway evidence for a GitHub body, not app screenshots or fixtures, so they're easy to find and prune later without touching anything else in the repo. Don't reuse a generic screenshots/ dir for this — that name doesn't self-document, and it collides with whatever ad-hoc convention a given repo might already have for actual app screenshots.

If the target repo already has an established convention for this (check with the user or look for precedent — e.g. git log --diff-filter=A --name-only --all | grep -iE 'screenshot'), follow that instead of introducing a second one.

What This Skill Does

Runs your generate-github-image-markdown.sh script to:

  • Generate proper raw.githubusercontent.com URLs
  • Create markdown with alt text and captions
  • Handle git repository detection automatically
  • Include helpful comments with local paths

Usage Flow

Step 1: Gather Information

Ask the user for:

  1. Image path (required) - relative or absolute
  2. Alt text (optional) - defaults to "Screenshot"
  3. Caption (optional) - italicized description below image

Step 2: Run the Script

Execute:

~/tools/screenshots/generate-github-image-markdown.sh \
  "$IMAGE_PATH" \
  "$ALT_TEXT" \
  "$CAPTION"

Permission pattern needed (update path to match your setup):

Bash(~/tools/screenshots/generate-github-image-markdown.sh:*)

Read the full file on GitHub · 189 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. 4d ago Changed · -1 lines · -15 tokens per session b26bda358dfa
  2. 1mo ago First seen · 190 lines · 82 tokens per session scan A 3e58ae619bfc

Subscribe to this mod's changes

github-screenshot is a skill published in the GitHub repository jerseycheese/agent-skills (3 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,261 once invoked, about $0.0003 per session on Opus 5.5. 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.