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.
npx agentmods add rules/shadowaqueduct/watermark-remover/clean-user-facing-textgit clone --depth 1 https://github.com/ShadowAqueduct/watermark-removerWrote 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/rules/shadowaqueduct/watermark-remover/clean-user-facing-text)<a href="https://agentmods.dev/rules/shadowaqueduct/watermark-remover/clean-user-facing-text"><img src="https://agentmods.dev/badge/rules/shadowaqueduct/watermark-remover/clean-user-facing-text.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 | $0.00166 | $0.00166 |
| Opus 5 | $0.00083 | $0.00083 |
| Sonnet 5 | $0.00033 | $0.00033 |
| Haiku 4.5 | $0.00017 | $0.00017 |
Grade A, and why
clean-user-facing-text 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 6d 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
Clean user-facing text
Before you ship substantial prose meant for readers, invoke the clean-user-facing-text skill.
- Only process content the user owns or is authorized to handle. Keep required disclosures.
- Applies to articles, papers, reports, docs, mail, product copy, UI strings, Markdown prose, and HTML prose.
- Keep facts, numbers, names, citations, requirements, language, tone, and layout.
- Leave fenced/inline code, commands, paths, URLs, identifiers, APIs, formulas, and verbatim quotes alone.
- Statistical-watermark reduction is best-effort. Never claim the result is certified undetectable or proves human authorship.
- Skip this skill on code-only work.
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.
- 6d ago First seen · 16 lines · 166 tokens per session scan A 8081b179d4b2
clean-user-facing-text is a cursor rule published in the GitHub repository ShadowAqueduct/watermark-remover (835 stars, last pushed 13d ago), licensed MIT. It adds 166 tokens to every session, about $0.0008 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 cursor rules, from other repositories
java-backend
Java Backend Execution Agent (Spring Boot / Quarkus).
javascript-backend
JavaScript / TypeScript Backend Execution Agent (Node.js / Express / Fastify / NestJS).
api-design
REST API Design Standards Agent.
observability
Observability Standards — Logging, Tracing & Metrics.
scala-backend
Scala Backend Execution Agent (Cats Effect / Tapir / Doobie).
context-delegate
Context Gatherer & External LLM Prompt Generator.