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/bklit/bklit-ui/agents-mdgit clone --depth 1 https://github.com/bklit/bklit-uiWrote 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/bklit/bklit-ui/agents-md)<a href="https://agentmods.dev/instructions/bklit/bklit-ui/agents-md"><img src="https://agentmods.dev/badge/instructions/bklit/bklit-ui/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 | $0.00589 | $0.00589 |
| Opus 5 | $0.00295 | $0.00295 |
| Sonnet 5 | $0.00118 | $0.00118 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
bklit-ui 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide (bklit-ui contributors)
This repo uses Agent Skills in .agents/skills/ for monorepo-specific workflows. Read the relevant skill before acting — do not guess at file layout.
Building or editing a chart
Always read and follow .agents/skills/bklit-studio/SKILL.md first.
Develop and preview charts in Studio at http://localhost:3000/studio (pnpm dev from repo root). Use ?chart=<slug> for a specific chart (slugs in packages/studio/src/chart-slugs.ts).
The local /playground route is deprecated (redirects to Studio). Do not scaffold apps/web/app/playground/ or apps/web/components/playground/ for new work.
Committed building blocks (do not reimplement):
| Area | Path |
|---|---|
| Studio app shell | apps/web/app/studio/page.tsx → @bklitui/studio StudioShell |
| Chart registry + preview render | packages/studio/src/lib/registry.tsx |
| Layer tree (components panel) | packages/studio/src/lib/studio-components.ts |
| Control groups | packages/studio/src/lib/registry-control-groups.ts |
| URL state | packages/studio/src/lib/studio-parsers.ts |
| Chart primitives | packages/ui/src/charts/ |
Pane rules: left = layers + data + motion; right = selected layer properties; visibility = layer eye toggles.
Shipping a chart to production
Read .agents/skills/bklit-ship/SKILL.md when the chart API is stable in packages/ui and Studio.
Other contributor skills
| Skill | When |
|---|---|
bklit-studio |
New or existing chart — prototype and edit in /studio |
bklit-ship |
Ship chart to docs, gallery, shadcn registry |
bklit-studio-chart-performance |
Studio chart FPS audit, pan/zoom jank, Motion subscription cleanup |
pr-open |
Commit, push, open PR (bklit-ui checklist) |
unit-tests |
Adding tests — avoid over-testing |
turborepo |
Monorepo tasks, turbo.json, caching |
shadcn |
shadcn/ui components in this repo |
add-x-tweet |
Homepage testimonial from an X URL |
wiki-llms-text |
Generate llms.txt for docs |
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 · 45 lines · 589 tokens per session scan A c1547e826a1b
bklit-ui AGENTS.md is an instructions file published in the GitHub repository bklit/bklit-ui (1,590 stars, last pushed 1mo ago), licensed MIT. It adds 589 tokens to every session, about $0.0029 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
ns-ui AGENTS.md
Instructions for nikolas-sapa/ns-ui, covering agents.md — working inside this repo, structure, autoplay — how a card demonstrates itself, descriptor schema and driver constraints (don't regress these).
mcp-charts CLAUDE.md
Instructions for bonnard-data/mcp-charts, covering claude.md — bonnard-mcp-charts, layout, build / test, dev loop (pick by what you're editing) and release (publish to npm).
nice-figures AGENTS.md
Instructions for Mapika/nice-figures, covering nice-figures — instructions for ai agents, get the style helper, or copy the single file (matplotlib + numpy only), workflow and hard rules of the register.
unovis AGENTS.md
AGENTS.md instructions for f5/unovis, a project described as: Modular data visualization framework for React, Angular, Svelte, Vue, and vanilla TypeScript or JavaScript.
unovis CLAUDE.md
Claude Code instructions for f5/unovis: The full AI contributor guide lives in ai/AGENTS.md and is shared by Claude, Codex, and Cursor. It is imported below; the skills in ai/skills/ are available as /commit, /open-pr, /add-component, and /add-gallery-example.
joint CLAUDE.md
Claude Code instructions for clientIO/joint, covering claude.md, project overview, common commands, install dependencies and build distribution files (runs grunt).