goviralbro: Command for Claude Code

.claude/commands/viral-analyze.md

viral-analyze is a command for Claude Code from charlesdove977/goviralbro. It costs 0 tokens per session (16,446 once invoked), scanned A, original, MIT.

A command that collects performance data for published YouTube and Instagram content and prepares it for comparison.

In plain words
What is it for?
Use it to review recent posts, a specific piece of content, long videos, or short videos. It can also run without prompts for scheduled or automated analysis.
Why use it?
It brings results from multiple platforms into one analysis process, so you can look for patterns instead of reviewing each platform separately.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is charlesdove977/goviralbro's own configuration. It tells Claude Code how to work on goviralbro 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 goviralbro configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/fetch-yt-analytics.py --video-id ${VIDEO_ID} --json.

Reuse

Borrowing it

Nothing to install: this file belongs to charlesdove977/goviralbro. 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/charlesdove977/goviralbro/main/.claude/commands/viral-analyze.md
Clone the repo
git clone --depth 1 https://github.com/charlesdove977/goviralbro

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 viral-analyze

README.md
[![agentmods](https://agentmods.dev/badge/commands/charlesdove977/goviralbro/viral-analyze/github.svg)](https://agentmods.dev/commands/charlesdove977/goviralbro/viral-analyze)
Your own site
<a href="https://agentmods.dev/commands/charlesdove977/goviralbro/viral-analyze"><img src="https://agentmods.dev/badge/commands/charlesdove977/goviralbro/viral-analyze/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 viral-analyze

Your own site · 80×15
<a href="https://agentmods.dev/commands/charlesdove977/goviralbro/viral-analyze"><img src="https://agentmods.dev/badge/commands/charlesdove977/goviralbro/viral-analyze.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 16,446 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 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 $0.16446
Opus 5 $0.00000 $0.08223
Sonnet 5 $0.00000 $0.03289
Haiku 4.5 $0.00000 $0.01645

Measured 11d ago against content hash 99a7640191fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

viral-analyze scanned grade A with 2 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 11d 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.

import json, urllib.request, os

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

v = subprocess.check_output(['yt-dlp', '--version']).decode().strip()
.claude/commands/viral-analyze.md · 1,614 lines

How it starts

The opening of the file, as written. The whole thing — 1,614 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/viral:analyze — Multi-Platform Analytics Collection

You are the Analytics Collection Engine for the Viral Command system. You gather performance data for published content across all platforms, store it for pattern analysis, and prepare the feedback loop.

Arguments

$ARGUMENTS

Parse for:

  • --youtube — Analyze YouTube content only
  • --instagram — Analyze Instagram content only
  • --all — Analyze all supported platforms (default if no platform flag — YouTube + Instagram)
  • --content-id [ID] — Analyze a specific script by ID
  • --recent [N] — Analyze last N published pieces (default: 5)
  • --longform — Analyze YouTube longform (5+ min) only; skip Shorts and Instagram
  • --shorts — Analyze YouTube Shorts + Instagram Reels only; skip longform
  • --manual — Non-interactive mode for cron/automation (skips prompts, analyzes all published content, runs full pipeline A-H without pauses)
  • --deep-analysis — Skip straight to Phase G.6 top 10 ranking + transcript/visual analysis (no new analytics collection — uses existing data from analytics.jsonl)

Phase A: Initialization & Mode Selection

Step 1: Load Agent Brain

Read data/agent-brain.json and extract:

  • platforms.posting — which platforms the user posts to
  • platforms.api_keys_configured — which APIs are set up
  • performance_patterns.total_content_analyzed — how much data we have

Step 1.2: Analytics Connection Detection

Skip this step if --manual flag is present.

Using the brain data loaded in Step 1, check analytics connection status for each platform in platforms.posting:

YouTube Analytics:

  • Connected if: "youtube_analytics_v2" in api_keys_configured AND ~/.viral-command/yt-token.json exists
  • Missing if: either condition is false

Instagram Graph API:

  • Connected if: "instagram_graph_api" in api_keys_configured AND INSTAGRAM_ACCESS_TOKEN set in .env
  • Missing if: either condition is false

If all relevant connections are present (or platform not in scope): Skip to Step 1.5 silently. No output.

Read the full file on GitHub · 1,614 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. 11d ago First seen · 1,614 lines · 0 tokens per session scan A 99a7640191fe

Subscribe to this mod's changes

viral-analyze is a command published in the GitHub repository charlesdove977/goviralbro (264 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 16,446 tokens. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.