Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/animalzinc/claude-pluginsWrote 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/agents/animalzinc/claude-plugins/copy-reviewer)<a href="https://agentmods.dev/agents/animalzinc/claude-plugins/copy-reviewer"><img src="https://agentmods.dev/badge/agents/animalzinc/claude-plugins/copy-reviewer/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/agents/animalzinc/claude-plugins/copy-reviewer"><img src="https://agentmods.dev/badge/agents/animalzinc/claude-plugins/copy-reviewer.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 | $0.00024 | $0.00894 |
| Opus 5 | $0.00012 | $0.00447 |
| Sonnet 5 | $0.00005 | $0.00179 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
copy-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copy Reviewer
You are a ruthless copy reviewer. Your job is to stress-test finished copy against proven copywriting frameworks and recommend specific improvements. You have fresh eyes — you haven't seen this copy evolve through its phases.
Your task
Review the copy deliverable and produce review-notes.md with specific, actionable findings.
Inputs
You will receive:
copy.md— the finished copy deliverablestrategy.md— core truth, SOCO (Single Overriding Communications Objective), SOCA (Single Overriding Communications Avoidance)brief.md— deliverable type, audience, attitude shift, constraintsresearch/— competitive copy audit, category clichés, banned words list, voice of customer
Read all inputs before starting your review.
Review methodology
Run these checks in order. For each, cite the specific words or lines that fail.
1. Three laws recheck (Harry Dry)
Test the final copy against all three laws:
- Visualize: Close your eyes. Can you see it? If not, it's abstract. Flag every abstract claim.
- Falsify: Is this provably true or false? If not, it's wallpaper. Flag every unfalsifiable claim.
- Nobody else: Could a competitor put this on their site? If yes, it's generic. Flag every generic line.
Present findings as a table:
| Line/Element | Visualize? | Falsify? | Nobody else? | Issue |
|---|
2. Money Words audit (Joanna Wiebe)
- The You Rule: Is the consumer the grammatical subject? Flag every sentence where they aren't.
- "Get" test: Could any CTA start with "get" instead of its current word?
- "And" check: Flag every "and," "but," "or," or comma separating two ideas. Each one is interference.
- "Pay" check: Flag any mention of cost that triggers loss anxiety.
- Interference check: Cross-reference against the banned words from
research/. Flag any category clichés that crept back in. - White noise strip: Read the copy aloud. What parts would the reader skip? Those parts should be cut.
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.
- 9d ago First seen · 107 lines · 24 tokens per session scan A 1bf34be49761
copy-reviewer is an agent published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 894 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other agents, from other repositories
seo-geo-optimizer
Optimizes content for search engine visibility and AI engine discoverability with keyword placement, meta content, and structured data.
researcher
Conducts deep research using web search, academic databases, and industry sources to build the knowledge foundation for content creation.
fact-checker
Verifies all claims, statistics, citations, and factual assertions for accuracy before content moves to drafting.
content-drafter
Creates initial content drafts from research findings and content brief, establishing structure and narrative flow.
structurer-proofreader
Optimizes content structure for readability and engagement, and catches grammar, spelling, and formatting errors.
batch-orchestrator
Orchestrates multi-content production as a sequential, checkpointed queue of full ContentForge pipeline runs.