github-screenshots

A workflow for adding screenshots, diagrams, images, GIFs, and recordings to GitHub pull requests and issues.

In plain words
What is it for?
Uploading an attachment, getting paste-ready Markdown, preparing a comment of collected files, or sharing a durable visual link.
Why use it?
GitHub’s command-line tools do not directly upload images for these pages, so visual files need a public link first.

Skill for Claude CodeCodex

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 skills/buildinternet/uploads/github-screenshots
Any agent
npx skills add buildinternet/uploads --skill github-screenshots
Clone the repo
git clone --depth 1 https://github.com/buildinternet/uploads

Made for: Claude Code, Codex.

Per session 278 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,118 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 $0.00278 $0.04118
Opus 5 $0.00139 $0.02059
Sonnet 5 $0.00056 $0.00824
Haiku 4.5 $0.00028 $0.00412

Measured yesterday against content hash e7d2dde1c9b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-screenshots 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 yesterday.

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-screenshots/SKILL.md · 326 lines

How it starts

The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Screenshots and recordings in GitHub PRs and issues

Why this exists

GitHub's native image hosting (github.com/user-attachments/…) only works from an authenticated browser session — there is no gh CLI or REST endpoint for it. Any image URL in a PR/issue body written with gh … --body-file must already point at something publicly hosted. The uploads CLI and the hosted MCP at https://agents.uploads.sh/mcp both host the file on uploads.sh and return a stable public URL plus ready-to-paste markdown.

Which surface

Pick one transport and stay on it. This skill is the workflow. The uploads-cli skill owns flags and MCP tool contracts.

You have Use
No shell (ChatGPT, or any host without a checkout) Hosted MCP put with (contentBase64 + filename, or contentUrl) + repo + (pr or branch). Filename is optional with contentUrl when the URL path has a leaf. Embed the returned markdown / embedUrl. Never imply you can run uploads attach ./shot.png.
A checkout and the uploads binary The CLI examples below. Git can fill repo / branch.
A localhost page or a selector annotate CLI only (uploads screenshot --via local). Remote render cannot reach your machine.
Neither MCP nor the CLI Stop and say so. Do not treat npm install -g as the ChatGPT path.

Read the full file on GitHub · 326 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. yesterday First seen · 326 lines · 278 tokens per session scan A e7d2dde1c9b1

Subscribe to this mod's changes

github-screenshots is a skill published in the GitHub repository buildinternet/uploads (19 stars, last pushed yesterday), licensed Apache-2.0. It adds 278 tokens to every session and 4,118 once invoked, about $0.0014 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 2026-08-30.