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 instructions/seite-sh/seite/claude-mdgit 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/instructions/seite-sh/seite/claude-md)<a href="https://agentmods.dev/instructions/seite-sh/seite/claude-md"><img src="https://agentmods.dev/badge/instructions/seite-sh/seite/claude-md.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 | $0.01733 | $0.01733 |
| Opus 5 | $0.00866 | $0.00866 |
| Sonnet 5 | $0.00347 | $0.00347 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
seite CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
seite — Static Site Generator with LLM Integration
What This Is
seite is a Rust CLI static site generator designed to be AI-native. Content and templates are structured for LLM generation and consumption. Sites ship with llms.txt, llms-full.txt, and markdown versions of every page alongside the HTML.
The seite agent command spawns Claude Code as a subprocess with full site context — no API keys needed, uses the user's Claude Code subscription directly.
Quick Commands
cargo build # Build the binary
cargo test # Run all tests
cargo fmt --all # Format — CI enforces this
cargo clippy # Lint — must be zero warnings
cargo run -- init mysite --title "My Site" --collections posts,docs,pages
cargo run -- build # Build site from seite.toml
cargo run -- serve # Dev server with REPL (live reload)
cargo run -- serve --open # Dev server + open browser
cargo run -- serve --host 0.0.0.0 # Bind to all interfaces
cargo run -- new post "My Post" --tags rust,web
cargo run -- agent "create a blog post about Rust"
cargo run -- theme create "coral brutalist with lime accents"
cargo run -- deploy # Commit, push, build, and deploy
cargo run -- skill install seomachine
cargo run -- upgrade # Upgrade project config to current binary
cargo run -- self-update
cargo run -- completions bash # Generate shell completions
Module Map
src/
main.rs CLI entrypoint (clap dispatch)
lib.rs, error.rs Module declarations, PageError enum (thiserror)
themes.rs 10 bundled themes + src/themes/*.tera
shortcodes/ ShortcodeRegistry, parser, builtins (youtube, vimeo, gist, callout, figure, contact_form)
build/ 15-step build pipeline (mod.rs), analytics, base_path, code_copy, links, markdown, feed, sitemap, discovery, images, math, mermaid
docs.rs Embedded docs (15 pages from seite-sh/content/docs/)
i18n.rs Language-map resolution + `i18n`/`localize` Tera filter (per-language data values)
meta.rs Project metadata (.seite/config.json)
mcp/ MCP server (JSON-RPC over stdio): mod.rs, resources.rs, tools.rs
cli/ 16 subcommands: init, new, build, serve, deploy, agent, theme, mcp, workspace, upgrade, contact, collection, skill, self_update, completions, perf
update_check.rs Background update check (24h cache)
scaffold/ Static markdown for generated CLAUDE.md + .claude/rules/ (include_str!)
config/ SiteConfig, CollectionConfig, defaults
data/ Data file loading (YAML/JSON/TOML)
content/ Frontmatter parsing, ContentItem, slug generation
deploy/ GitHub Pages + Cloudflare + Netlify
workspace/ Multi-site workspaces (config, build, server, deploy)
output/ CommandOutput trait, human (colored), json
server/ tiny_http dev server, file watcher, live reload
templates/ Tera template loading with embedded defaults
tests/integration.rs Integration tests (assert_cmd + tempfile)
build.rs Generates releases.md from changelog at compile time
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 · 154 lines · 1,733 tokens per session scan A b5a29080bac7
seite CLAUDE.md is an instructions file published in the GitHub repository seite-sh/seite (20 stars, last pushed 20d ago), licensed MIT. It adds 1,733 tokens to every session, about $0.0087 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 instructions, from other repositories
ai-dial-core CLAUDE.md
Claude Code instructions for epam/ai-dial-core, covering claude.md, build & run, set credentials via environment variables, build (skip tests) and run all tests.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.