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/sthamann/nyx-local-ai/webview-conventionsgit clone --depth 1 https://github.com/sthamann/nyx-local-aiWrote 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/sthamann/nyx-local-ai/webview-conventions)<a href="https://agentmods.dev/rules/sthamann/nyx-local-ai/webview-conventions"><img src="https://agentmods.dev/badge/rules/sthamann/nyx-local-ai/webview-conventions.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 | $0.00000 | $0.00341 |
| Opus 5 | $0.00000 | $0.00170 |
| Sonnet 5 | $0.00000 | $0.00068 |
| Haiku 4.5 | $0.00000 | $0.00034 |
Grade A, and why
webview-conventions 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 5d 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
Webview conventions
- Module boundaries:
dom.tsowns the HTML skeleton + element refs,state.tsowns shared state +post(),transcript.tsrenders messages and cards,composer.tsowns input/queue/attachments,main.tsis only the host-message dispatcher. New UI belongs in the matching module, not main.ts. - All host↔webview messages are typed in
src/types.ts(HostToWebview/WebviewToHost). Add the variant there first; the dispatcher switches must stay exhaustive (nevercheck in default). - Escape everything user- or model-provided with
escapeHtmlbeforeinnerHTML; markdown goes throughrenderMarkdown/renderMarkdownFinal. - Streaming renders are throttled (see
scheduleStreamingRender): never re-parse full markdown on every delta — that froze the UI on long generations once already. - No external resources: the CSP allows only bundled assets; libraries
(marked, highlight.js) are bundled via esbuild into
media/main.js. - Verify UI changes in the harness:
python3 -m http.server 8321+http://127.0.0.1:8321/.harness/index.html?scene=chat|approval|machinesrenders the real bundle with demo data (also used for README screenshots).
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.
- 5d ago First seen · 26 lines · 0 tokens per session scan A cf050a9957d7
webview-conventions is a cursor rule published in the GitHub repository sthamann/nyx-local-ai (137 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 341 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 cursor rules, from other repositories
agents
Единые правила и скиллы проекта (зеркало AGENTS.md).
general-ai-assistant-instructions
General instructions for the AI assistant to follow when executing tasks, including analysis, execution, quality control, and reporting.
fastapi-components-and-validation
Specifies the use of functional components and Pydantic models for input validation in FastAPI routes.
verify-information-rule
This rule ensures that the AI always verifies information before presenting it, avoiding assumptions and speculation.
accessibility
Rules for ensuring accessibility in Astro components, including semantic HTML and ARIA attributes.
check-x-md-content-rule
This rule reminds the AI to check the x.md file for the current file contents and implementations.