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/karthikrshet/claudemark/clean-user-facing-textgit clone --depth 1 https://github.com/karthikrshet/ClaudeMarkWrote 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/karthikrshet/claudemark/clean-user-facing-text)<a href="https://agentmods.dev/rules/karthikrshet/claudemark/clean-user-facing-text"><img src="https://agentmods.dev/badge/rules/karthikrshet/claudemark/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 | $0.00000 | $0.00242 |
| Opus 5 | $0.00000 | $0.00121 |
| Sonnet 5 | $0.00000 | $0.00048 |
| Haiku 4.5 | $0.00000 | $0.00024 |
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
Cursor Rule: Clean User-Facing Text Hygiene
When writing or editing user-facing copy, documentation, and manuscripts:
- Never emit invisible Unicode formatting carriers: Disallow zero-width spaces (
U+200B), zero-width non-joiners (U+200C), word joiners (U+2060), and byte order marks (U+FEFF) in ordinary prose. - Standardize Spaces: Use regular ASCII spaces (
U+0020) instead of non-breaking spaces (U+00A0), thin spaces (U+2009), or mathematical spaces unless explicitly required for typography. - Preserve Valid Code and Syntax: Do not strip syntax tokens from code blocks or formula strings.
- Use ClaudeMark For Verification: Verify clean text with
python claudemark.py unicode inspect <file>orpython claudemark.py unicode visualize <file>.
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 · 14 lines · 0 tokens per session scan A 5b23b3b37cff
clean-user-facing-text is a cursor rule published in the GitHub repository karthikrshet/ClaudeMark (9 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 242 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 2026-08-31.
Other cursor rules, from other repositories
case-uco-sdk
CASE/UCO SDK usage patterns for building digital forensics investigation graphs.
mcpnuke-development
Core mcpnuke development standards and superpowers workflow integration.
cursorrules
Read AGENTS.md for shared project conventions and local Skill requirements. Use the root README and package documentation for current setup and host support. Do not treat an older three-package description as the current architecture.
mcpnuke-tests
Test conventions for mcpnuke — enforces TDD workflow.
cursorrules
When the user asks about owasp agentic, use owasp-agentic-mcp tools: assessagentsecurity, checkpromptinjection, checktoolpoisoning, checkexcessiveagency, checkdataleakage.
cursorrules
When the user asks about EU AI Act Article 50 watermarking, C2PA content provenance, AI-generated synthetic content disclosure, deepfake detection, or content authenticity verification, use watermarking-authenticity-mcp tools.