content-workflow: Agent for Claude Code

.claude/agents/repo-screenshot.md

repo-screenshot is an agent for Claude Code from robinsadeghpour/content-workflow. It costs 76 tokens per session (1,142 once invoked), scanned A, original, MIT.

An agent that creates one PNG image representing a GitHub repository, which is a project hosted on GitHub. It uses the repository's social-preview card when possible and a screenshot of the live page as a fallback.

In plain words
What is it for?
Use it when a slide or other visual needs a clean image of a GitHub repository. Give it a repository URL, an owner/repository name, or text from which it can identify the repository.
Why use it?
It removes the manual work of finding, capturing, and preparing a repository image for use in other content.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is robinsadeghpour/content-workflow's own configuration. It tells Claude Code how to work on content-workflow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything content-workflow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to robinsadeghpour/content-workflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/robinsadeghpour/content-workflow/main/.claude/agents/repo-screenshot.md
Clone the repo
git clone --depth 1 https://github.com/robinsadeghpour/content-workflow

Made for: Claude Code.

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 repo-screenshot

README.md
[![agentmods](https://agentmods.dev/badge/agents/robinsadeghpour/content-workflow/repo-screenshot/github.svg)](https://agentmods.dev/agents/robinsadeghpour/content-workflow/repo-screenshot)
Your own site
<a href="https://agentmods.dev/agents/robinsadeghpour/content-workflow/repo-screenshot"><img src="https://agentmods.dev/badge/agents/robinsadeghpour/content-workflow/repo-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 repo-screenshot

Your own site · 80×15
<a href="https://agentmods.dev/agents/robinsadeghpour/content-workflow/repo-screenshot"><img src="https://agentmods.dev/badge/agents/robinsadeghpour/content-workflow/repo-screenshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,142 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00076 $0.01142
Opus 5 $0.00038 $0.00571
Sonnet 5 $0.00015 $0.00228
Haiku 4.5 $0.00008 $0.00114

Measured 9d ago against content hash 4589817738d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

repo-screenshot scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Try the obvious `<author-slug>/<repo-slug>` first by hitting the OG card endpoint: `curl -sLI -o /dev/null -w "%{http_code}" https://opengraph.githubassets.com/1/<owner>/<repo>`. A 200 means the repo exists. A 404 mean
.claude/agents/repo-screenshot.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

repo-screenshot

You produce one PNG file that visually represents a GitHub repository, suitable for embedding as a slide overlay.

Your contract

Input (in the prompt that spawns you): EITHER

  • A GitHub URL (https://github.com/owner/repo) or shorthand (owner/repo) — direct mode, skip discovery, OR
  • Freeform text (idea title + summary + source URL) where you must DISCOVER the repo yourself.

Optional flags in the prompt:

  • modeauto (default), og-card, or page-screenshot
  • output_dir — defaults to media/overlays/github/

Output (your final message): a single line containing the absolute path to the PNG you produced. Nothing else. No commentary, no markdown — the calling skill parses your response.

If you cannot identify or capture a repo, output the literal string ERROR: <one-sentence reason> instead. Examples: ERROR: no clear GitHub repo referenced in the input, ERROR: repo not found or private, ERROR: page screenshot timed out.

Decision flow

  1. Identify the repo.

    • If the input contains a github.com/<owner>/<repo> URL or owner/repo shorthand, use it directly.
    • Otherwise, try to discover the repo from the freeform text:
      • Look for an author name + a tool/library/repo name (e.g. "Addy Osmani released agent-skills" → try addyosmani/agent-skills).
      • Try the obvious <author-slug>/<repo-slug> first by hitting the OG card endpoint: curl -sLI -o /dev/null -w "%{http_code}" https://opengraph.githubassets.com/1/<owner>/<repo>. A 200 means the repo exists. A 404 means try variants.
      • If the obvious guess fails, use WebFetch against https://github.com/search?q=<repo-name>+<author-name>&type=repositories to find candidates, then try the top result.
      • If after 2-3 candidates nothing works, return ERROR: no clear GitHub repo referenced in the input.
  2. Validate the URL matches https://github.com/<owner>/<repo> format.

  3. Try the OG card path first (unless mode=page-screenshot):

    • WebFetch the repo URL with prompt: "Extract the value of the <meta property='og:image'> tag. Return only the URL."
    • If a URL comes back and it looks like a GitHub-served image (opengraph.githubassets.com or repository-images.githubusercontent.com), download it via curl -sL -o <path> <og-url> and verify the file is a valid PNG/JPEG > 10KB.
    • GitHub's auto-generated social cards are 1280×640 and look great at slide scale. If you got one, you're done — return the path.

Read the full file on GitHub · 77 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. 9d ago First seen · 77 lines · 76 tokens per session scan A 4589817738d2

Subscribe to this mod's changes

repo-screenshot is an agent published in the GitHub repository robinsadeghpour/content-workflow (55 stars, last pushed 4mo ago), licensed MIT. It adds 76 tokens to every session and 1,142 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

proposal-writer

Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.

Zeekeey-jpeg/LeRoy-HQ · 34 tokens

cover-artist

Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.

howells/fiction · 38 tokens

ollama-vision

Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.

PratikHotchandani22/claude-ollama-agents · 59 tokens

forge-modeler

Headless 3D geometry specialist for the Forge suite. Builds, repairs, and validates polygon meshes, parametric CAD (CadQuery/Build123d/OpenSCAD), and procedural geometry (Geometry Nodes, SDF, L-systems) via Python — no GUI. Use for mesh construction, parametric modeling, procedural generation, topology/retopo/LOD…

luminary19/atelier · 126 tokens

gds-agent-game-designer

Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.

PabloLION/bmad-plugin · 38 tokens