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/seite-sh/seiteWrote 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/seite-sh/seite/config-reference)<a href="https://agentmods.dev/rules/seite-sh/seite/config-reference"><img src="https://agentmods.dev/badge/rules/seite-sh/seite/config-reference/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/rules/seite-sh/seite/config-reference"><img src="https://agentmods.dev/badge/rules/seite-sh/seite/config-reference.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 | $0.00000 | $0.00920 |
| Opus 5.5 | $0.00000 | $0.00368 |
| Sonnet 5.5 | $0.00000 | $0.00184 |
| Haiku 4.5 | $0.00000 | $0.00092 |
Grade A, and why
config-reference 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 17d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optional Configuration
These sections in seite.toml enable additional features. Omit them entirely to disable.
Build Options
[build]
math = true # enable $inline$ and $$display$$ math rendering via KaTeX
mermaid = true # render fenced ```mermaid blocks as client-side Mermaid diagrams
When math = true, the build pipeline renders LaTeX math expressions to HTML using server-side KaTeX. KaTeX CSS is automatically loaded from CDN. Code blocks and inline code spans are skipped.
When mermaid = true, fenced ```mermaid code blocks in markdown are left intact and rendered client-side by an injected Mermaid script — no server-side rendering. Default: false.
Image Processing
[images]
widths = [480, 800, 1200] # generate resized copies at these pixel widths
quality = 80 # JPEG/WebP quality (1-100)
webp = true # generate WebP variants alongside originals
avif = true # generate AVIF variants (better compression than WebP)
avif_quality = 70 # AVIF quality (1-100, lower is fine — AVIF compresses better)
lazy_loading = true # add loading="lazy" to <img> tags
When enabled, the build pipeline auto-resizes images, generates WebP and/or AVIF variants, and rewrites <img> tags with srcset and <picture> elements. AVIF sources are emitted before WebP in <picture> elements for optimal compression. The first image on each page is excluded from loading="lazy" to avoid hurting Largest Contentful Paint (LCP) performance.
Analytics
[analytics]
provider = "plausible" # "google", "gtm", "plausible", "fathom", "umami"
id = "example.com" # measurement/tracking ID
cookie_consent = true # show consent banner and gate analytics on acceptance
# script_url = "..." # Plausible: paste your unique snippet URL from Settings → Installation
# extensions = ["tagged-events", "outbound-links"] # legacy: Plausible pre-Oct 2025 script only
Analytics scripts are injected into all HTML files at build time. When cookie_consent = true, a banner is shown and analytics only load after the user accepts. Consent is stored in localStorage.
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.
- 17d ago First seen · 72 lines · 0 tokens per session scan A f1bfaf71031e
config-reference is a cursor rule published in the GitHub repository seite-sh/seite (25 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 920 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 2026-09-29.
Other cursor rules, from other repositories
frontend-architecture
Cursor rule "frontend-architecture" from tomasz-tomczyk/crit, covering frontend architecture, two-paradigm page fork, module pattern, shared modules (used by both modes) and code-review modules (used only by code-review mode).
proxy-auth-transport
Every CLI command or browser UI action that calls a crit-web API must work in both modes.
frontend-js
Cursor rule "frontend-js" from tomasz-tomczyk/crit, covering frontend js rules (semantic — eslint handles syntax/style), dom & events, state management, persisted settings (cookies, not localstorage) and error handling.
go
Cursor rule "go" from tomasz-tomczyk/crit, covering go code rules (semantic — linters handle syntax/style), struct & state integrity, code organization, git operations and daemon/server.
frontend-css
Cursor rule "frontend-css" from tomasz-tomczyk/crit, covering css rules, responsive & touch and selectors.
ui-assets
Docker staging for symlinked SPA and documentation assets.