agent-orchestrator-ts: Command for Claude Code

.claude/commands/pr-media.md

pr-media is a command for Claude Code from jleechanorg/agent-orchestrator-ts. It costs 0 tokens per session (1,001 once invoked), scanned A, original, MIT.

A command that runs a script to capture a terminal screenshot, GIF, or video and attach it to a pull request. A pull request is a proposed code change submitted for review before it is merged.

In plain words
What is it for?
Use it to capture terminal screenshots, short recordings, or GIFs and post them to pull requests, including a dry-run mode that skips the comment.
Why use it?
It replaces written claims about a change with visual evidence that reviewers can inspect. It can also make terminal-based test or workflow results easier to verify.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is jleechanorg/agent-orchestrator-ts's own configuration. It tells Claude Code how to work on agent-orchestrator-ts 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 agent-orchestrator-ts configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/pr-media.sh.

Reuse

Borrowing it

Nothing to install: this file belongs to jleechanorg/agent-orchestrator-ts. 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/jleechanorg/agent-orchestrator-ts/main/.claude/commands/pr-media.md
Clone the repo
git clone --depth 1 https://github.com/jleechanorg/agent-orchestrator-ts

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 pr-media

README.md
[![agentmods](https://agentmods.dev/badge/commands/jleechanorg/agent-orchestrator-ts/pr-media/github.svg)](https://agentmods.dev/commands/jleechanorg/agent-orchestrator-ts/pr-media)
Your own site
<a href="https://agentmods.dev/commands/jleechanorg/agent-orchestrator-ts/pr-media"><img src="https://agentmods.dev/badge/commands/jleechanorg/agent-orchestrator-ts/pr-media/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 pr-media

Your own site · 80×15
<a href="https://agentmods.dev/commands/jleechanorg/agent-orchestrator-ts/pr-media"><img src="https://agentmods.dev/badge/commands/jleechanorg/agent-orchestrator-ts/pr-media.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,001 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 $0.00000 $0.01001
Opus 5.5 $0.00000 $0.00400
Sonnet 5.5 $0.00000 $0.00200
Haiku 4.5 $0.00000 $0.00100

Measured 9d ago against content hash ac3609948ea4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-media 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 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.

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.

.claude/commands/pr-media.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pr-media — Capture and attach terminal media to PRs

Run the actual capture script, not prose guidance.

# Capture screenshot of current tmux pane + upload to Gist + post to PR
bash scripts/pr-media.sh

# Dry-run (capture + upload, skip PR comment)
bash scripts/pr-media.sh --test

# With options
bash scripts/pr-media.sh --type screenshot --pr 281 --caption "AO worker showing test pass"
bash scripts/pr-media.sh --type gif           # 5-second clip → GIF (requires ffmpeg + gifski)
bash scripts/pr-media.sh --type video         # 10-second recording (requires ffmpeg)

The script (scripts/pr-media.sh) implements the Terminal media requirement of Evidence Bundle v2 (CLAUDE.md).

Philosophy (Cursor-style evidence)

Cursor's cloud agents produce artifacts (videos, screenshots, and logs) and merge-ready PRs with artifacts so reviewers can validate work without trusting prose alone. The /pr-media command automates the capture step so agents attach real terminal proof to every PR.

Evidence Bundle v2 requires (CLAUDE.md Evidence Gate strong proof):

  • Terminal media: screenshot or video URL + caption mentioning tmux or terminal
  • Caption outside the label line — the caption must describe what the media shows, not just repeat the label

Usage

/pr-media [--type screenshot|video|gif] [--pr N] [--caption "text"]

Arguments

Flag Default Description
--type screenshot Media type: screenshot, video, or gif
--pr auto-detect PR number; auto-detected from current branch
--caption auto Caption text; auto-generates if omitted

Examples

/pr-media
/pr-media --type screenshot
/pr-media --type video --caption "AO worker session showing PR merge confirmation"
/pr-media --type gif
/pr-media --pr 281

Workflow

  1. Capture — screencapture (screenshot) or ffmpeg (video/gif) captures the tmux pane
  2. Upload — file is uploaded to GitHub Gist via gh gist create (authenticated, secret by default)
  3. Attach — GitHub comment is posted on the target PR with the media URL in markdown
  4. Output — prints the markdown snippet to stdout for copy-paste into PR body

Read the full file on GitHub · 105 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 · 105 lines · 0 tokens per session scan A ac3609948ea4

Subscribe to this mod's changes

pr-media is a command published in the GitHub repository jleechanorg/agent-orchestrator-ts (8 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,001 tokens. 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 2026-10-02.