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/sathvikc/lume-js/agents-mdgit clone --depth 1 https://github.com/sathvikc/lume-jsWrote 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/sathvikc/lume-js/agents-md)<a href="https://agentmods.dev/instructions/sathvikc/lume-js/agents-md"><img src="https://agentmods.dev/badge/instructions/sathvikc/lume-js/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 | $0.01941 | $0.01941 |
| Opus 5 | $0.00971 | $0.00971 |
| Sonnet 5 | $0.00388 | $0.00388 |
| Haiku 4.5 | $0.00194 | $0.00194 |
Grade A, and why
lume-js 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — How to work on Lume.js
Process contract for AI agents and humans. Follow it for every change. (Most agent tooling, including Claude Code, picks this file up automatically.)
What this library is
Standards-only reactivity: data-* attributes, plain JavaScript, no build step, no custom syntax. The product is trust in a tiny core — 1.46 KB universal kernel (lume-js/state), 2.66 KB with DOM (lume-js), everything else opt-in.
Two documents are the source of truth — read them before designing anything:
docs/design/design-decisions.md— ratified decisions (the contract). If your change contradicts an entry, the entry wins until it is amended.docs/design/VISION.md— direction, roadmap, open problems.
Hard constraints (never violate)
- Standards-only. No custom syntax beyond
data-*attributes. No expressions in attributes (state-key/path references only). No build-step requirement for users. - Explicit over magic. No hidden behavior, no auto-registration.
- No import side effects.
package.jsondeclares"sideEffects": false— module top-levels must be pure (no global mutation, no registration on import). This is what sank the old pluggable-scheduler branch. - Dependency directions.
core/state.jsimports nothing upward (no DOM, no effect, no addons). Addons import core only. No addon → addon imports. Handlers import nothing (orutils/log.js). - Browser floor: Chrome 80+, Firefox 74+, Safari 13.1+, Edge 80+ (ES2020: the source already uses
?.and??, shipped un-transpiled). Nothing newer than ES2020 insrc/— noObject.hasOwn,.at(),??=/||=/&&=,structuredClone,replaceAll. Check MDN before using any API newer than 2020, and update the README support table if the floor ever moves. - Source is plain JS + handwritten
.d.ts. When you change a public signature, update the matching.d.tsin the same commit. - Never bump the package version unless explicitly asked.
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 · 93 lines · 1,941 tokens per session scan A 658cd047216a
lume-js AGENTS.md is an instructions file published in the GitHub repository sathvikc/lume-js (44 stars, last pushed 1mo ago), licensed MIT. It adds 1,941 tokens to every session, about $0.0097 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
ui-components AGENTS.md
AGENTS.md instructions for starc007/ui-components, covering beui v2 — agent guide, commands, layout, component catalog and components (motion category — primitives).
react-seed AGENTS.md
Instructions for guokaigdg/react-seed, covering agents.md, 目录, 1. 项目概览, 2. 技术栈 and 3. 目录结构.
walkerOS CLAUDE.md
Claude Code instructions for elbwalker/walkerOS, covering claude.md and important: use agent.md.
webiny-js CLAUDE.md
Claude Code instructions for webiny/webiny-js, covering context, claude project guidelines, reading code, development commands and install dependencies (suppress all output – it's noise).
monochrome-ui AGENTS.md
AGENTS.md instructions for vaneenige/monochrome-ui, covering agents.md, north stars (non-negotiables), why the core looks weird (and should stay weird), clever tricks and code style.
Kokoro-Engine CLAUDE.md
Instructions for chyinan/Kokoro-Engine, covering claude.md, git 规范, 项目概述, 常用命令 and 安装依赖.