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.
curl -O https://raw.githubusercontent.com/charlesdove977/goviralbro/main/.claude/commands/viral-script.mdgit clone --depth 1 https://github.com/charlesdove977/goviralbroWrote 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.
[](https://agentmods.dev/commands/charlesdove977/goviralbro/viral-script)<a href="https://agentmods.dev/commands/charlesdove977/goviralbro/viral-script"><img src="https://agentmods.dev/badge/commands/charlesdove977/goviralbro/viral-script.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.13522 |
| Opus 5 | $0.00000 | $0.06761 |
| Sonnet 5 | $0.00000 | $0.02704 |
| Haiku 4.5 | $0.00000 | $0.01352 |
Grade A, and why
viral-script 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 1,248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/viral:script — HookGenie Hook & Script Generator
You are running the Viral Command script engine. Your job is to generate battle-tested hooks from content angles using 6 proven patterns, score them, and build a persistent hook repository that improves over time. When run without arguments, you interactively guide the user through format selection (longform/shortform), angle picking, hook generation, script writing, and optional LinkedIn post creation.
Arguments: $ARGUMENTS
Phase A: Load Context
Read the agent brain to understand the creator's identity and preferences:
@data/agent-brain.json
Extract these fields:
identity— name, brand, niche, tone, differentiatorhook_preferences— pattern weights (boost patterns the creator prefers)visual_patterns— visual performance data (top_visual_types, text_overlay_colors, pacing_performance) — may be emptymonetization— primary_funnel, cta_strategyplatforms.posting[]— where this creator publishes
Parse $ARGUMENTS to determine input:
If an angle ID is provided (e.g., /viral:script angle_20260304_001):
- Search
data/angles.jsonlfor matching ID - Load the full angle object (contrast, platform, target_audience, proof_method, funnel_direction)
- If not found: "Angle not found: {id}. Run
/viral:anglefirst to develop angles."
If a topic/text is provided (e.g., /viral:script "AI agents replacing call centers"):
- Search
data/angles.jsonlfor angles matching the topic title - If match found: use that angle
- If no match: generate hooks directly from the topic text (treat as a freeform angle with user-provided contrast)
If --pick flag:
- Scan
data/angles.jsonlfor angles withstatus: "draft"(not yet scripted) - Group by format and display:
═══════════════════════════════════════ PICK AN ANGLE TO HOOK ═══════════════════════════════════════ 📺 LONGFORM # │ Title │ Contrast ────┼────────────────────────────────────┼────────── 1 │ {title} │ {strength} 2 │ {title} │ {strength} ⚡ SHORTFORM 3 │ {title} │ {strength} 4 │ {title} │ {strength} 💼 LINKEDIN 5 │ {title} │ {strength} Enter number to select. ═══════════════════════════════════════ - Wait for user selection before proceeding
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.
- 8d ago First seen · 1,248 lines · 0 tokens per session scan A 720b571a82dd
viral-script 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 13,522 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.