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/rob-balfre/dryui/agents-mdgit clone --depth 1 https://github.com/rob-balfre/dryuiWrote 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/rob-balfre/dryui/agents-md)<a href="https://agentmods.dev/instructions/rob-balfre/dryui/agents-md"><img src="https://agentmods.dev/badge/instructions/rob-balfre/dryui/agents-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 | $0.01210 | $0.01210 |
| Opus 5 | $0.00605 | $0.00605 |
| Sonnet 5 | $0.00242 | $0.00242 |
| Haiku 4.5 | $0.00121 | $0.00121 |
Grade A, and why
dryui AGENTS.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 4d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repo-wide instructions for AI coding agents working in this repository.
Canonical Docs
- Public overview:
README.md - Contributor workflow:
CONTRIBUTING.md - CSS discipline and token rules:
skills/dryui-build/SKILL.md - Accessibility policy:
ACCESSIBILITY.md - Release flow:
RELEASING.md
Canonical Sources
- Editor install snippets and MCP config examples live in
apps/docs/src/lib/ai-setup.ts. Do not duplicate them elsewhere. - Public docs copy and positioning should match
apps/docs/src/lib/site-meta.tsand the docs homepage: human-led, agent-assisted UI for reusable components, themes, and route patterns. Avoid positioning DryUI as a full automation tool, an "agent-built apps" product, or a Svelte-only message. - The public docs route surface is intentionally small:
/,/getting-started, and/components/[slug]. Do not re-add removed exploration pages (/tools,/how-it-works,/how-we-work,/grid-rules,/theme-wizard, logo option pages,/componentsindex pages, or similar samples) unless explicitly requested. - Skill sources live in top-level
skills/(dryui-build,dryui-feedback,dryui-live-feedback,dryui-init). One source of truth. - Recommended install path for end users:
npx skills add rob-balfre/dryui(skills.sh standard). bun run validate:skillslints every SKILL.md (frontmatter present, name=dirname, description length)./pluginsin this repo refers to the in-app Claude or Codex install flow (sunset for DryUI; users install vianpx skills add rob-balfre/dryui), not a repo directory.
Repo Rules
- DryUI is pre-alpha. Prefer the current shape over compatibility shims unless a task explicitly asks for backwards compatibility.
- Use DryUI skills as the default entry point. For any DryUI component, route, template, styling, layout, docs, or feedback task, load the relevant top-level
skills/*/SKILL.mdbefore planning or editing files. If the task also involves Svelte or SvelteKit, load thedryui-buildskill first, then use the Svelte MCP docs/autofixer flow. - Run the local feedback dashboard with
bunx dryui-feedback(bin shipped from@dryui/feedback-server). - Use package-level lint/build/test commands for deterministic validation: component contracts, a11y, tokens, CSS discipline.
- DryUI ships no layout component. Page/section structure lives as plain CSS Grid in root
src/layout.css, scoped under[data-layout="<name>"]. The file is imported last fromsrc/routes/+layout.svelteafter DryUI theme CSS and../app.css. - All
display: gridanddisplay: flexdeclarations in consumer code live insrc/layout.css(or@containerblocks within it). Mobile-first;@containerqueries for responsive shifts, never@mediafor layout breakpoints. @dryui/linthas two build-time surfaces:dryuiLint()insvelte.configfor component rules, anddryuiLayoutCss()invite.configforsrc/layout.css. The Vite plugin must run invite dev/HMR andvite build; missingsrc/layout.cssis warning-only, violations are hard errors.- The docs shell header is centralized in
apps/docs/src/routes/+layout.svelte: logo, search, GitHub, and theme toggle. Keep route pages focused on content and avoid duplicating header chrome. - The docs logo is the simple font-based
DryUIwordmark inapps/docs/src/lib/components/Logo.svelte. The favicon lives atapps/docs/static/favicon.svgand should stay black and white with no underline. - Keep root-level Markdown durable. One-off audits, scratch TODOs, and generated reports belong under
docs/,reports/, or ignored local directories, not the repo root. - Repo-local editor install output such as
.agents/skills/,.github/skills/,.opencode/, andopencode.jsonis not canonical source.
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.
- 4d ago First seen · 47 lines · 1,210 tokens per session scan A 408a8aa22b0a
dryui AGENTS.md is an instructions file published in the GitHub repository rob-balfre/dryui (9 stars, last pushed 3mo ago), licensed MIT. It adds 1,210 tokens to every session, about $0.0060 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 2026-08-31.
Other instructions, from other repositories
neo-svelte copilot-instructions.md
Instructions for dvcol/neo-svelte, covering examples old vs new, redirect and error handling, cookie path requirement, top-level promise handling and goto changes.
neo-svelte AGENTS.md
Instructions for dvcol/neo-svelte: Pick the guide that matches your task — load only the slice you need.
neo-svelte CLAUDE.md
Instructions for dvcol/neo-svelte: This project uses AGENTS.md as the single source of truth for AI agents. Open it and follow the link that matches your task.
pocketbase-sveltekit-starter AGENTS.md
Instructions for spinspire/pocketbase-sveltekit-starter, covering agents, project structure, dev mode, deployment and key commands.
ssgoi AGENTS.md
Instructions for meursyphus/ssgoi, covering ssgoi and releasing.
svelte-markdown CLAUDE.md
Claude Code instructions for humanspeak/svelte-markdown, covering claude.md, project overview, key technologies, project structure and development commands.