Borrowing it
Nothing to install: this file belongs to tabato/viral-ops. 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/tabato/viral-ops/main/CLAUDE.mdgit clone --depth 1 https://github.com/tabato/viral-opsWrote 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/instructions/tabato/viral-ops/claude-md)<a href="https://agentmods.dev/instructions/tabato/viral-ops/claude-md"><img src="https://agentmods.dev/badge/instructions/tabato/viral-ops/claude-md/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.
<a href="https://agentmods.dev/instructions/tabato/viral-ops/claude-md"><img src="https://agentmods.dev/badge/instructions/tabato/viral-ops/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00398 | $0.00398 |
| Opus 5.5 | $0.00159 | $0.00159 |
| Sonnet 5.5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
viral-ops CLAUDE.md 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 1mo 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.
What it actually says
Claude Setup (Anthropic)
Use Claude if you're already on an Anthropic plan or want the most nuanced AI copy angles. Claude tends to write in a more natural, voice-forward style than other providers — good if your content has a strong personal brand.
Model
viral-ops uses claude-sonnet-4-6 — Anthropic's current flagship model.
Pricing
Claude is a paid API. Pricing at time of writing:
| Cost | |
|---|---|
| Input tokens | $3 / 1M tokens |
| Output tokens | $15 / 1M tokens |
A full viral-ops run (10 videos analyzed) uses roughly 20,000–30,000 tokens total. That's well under $0.50 per run.
Check current pricing at anthropic.com/pricing.
Setup
1. Create an Anthropic account
2. Add credits
Go to Billing → add a minimum amount (usually $5) to activate API access.
3. Generate an API key
Go to API Keys → Create Key → copy it.
4. Add it to your .env
ANTHROPIC_API_KEY=your_key_here
5. Set it in profile.yml
ai_provider: claude
Troubleshooting
ANTHROPIC_API_KEY not set — check your .env file exists and is in the project root.
401 Authentication error — your key may have been rotated or is invalid. Generate a new one at the console.
529 Overloaded — Anthropic's API is under load. Retry in a moment; viral-ops will show the error per-video so you won't lose your whole run.
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.
- 1mo ago First seen · 55 lines · 398 tokens per session scan A 021ba9d08c5a
viral-ops CLAUDE.md is an instructions file published in the GitHub repository tabato/viral-ops (7 stars, last pushed 5mo ago), licensed MIT. It adds 398 tokens to every session, about $0.0016 per session on Opus 5.5. 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 2026-10-02.
viral-ops CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| viral-ops CLAUDE.mdtabato/viral-ops | Instructions file | 7 | 5mo ago | MIT | A | 398 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |