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/claude-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/claude-md)<a href="https://agentmods.dev/instructions/sathvikc/lume-js/claude-md"><img src="https://agentmods.dev/badge/instructions/sathvikc/lume-js/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 5.1 | $0.01758 | $0.01758 |
| Opus 5 | $0.00879 | $0.00879 |
| Sonnet 5 | $0.00352 | $0.00352 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade A, and why
lume-js 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 6d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Lume.js
Agent onboarding: what this project is and how to navigate it. The process contract (artifact matrix, quality gates, commit rules) lives in
AGENTS.md— read it before making ANY change. This file doesn't repeat it.
What this is
Lume.js is a reactive state-management library whose entire pitch is standards-only: plain JavaScript Proxy state + data-* attributes in valid HTML. No custom syntax, no build step, no virtual DOM. The product is trust in a tiny core: a 1.46 KB gz universal kernel (lume-js/state — works in Node/Deno/Bun/workers), 2.66 KB with DOM binding (lume-js), everything else opt-in via lume-js/addons and lume-js/handlers. Published on npm as lume-js (v2.3.1), MIT, docs site at https://sathvikc.github.io/lume-js/.
Formatting rule — never hard-wrap prose (STRICT)
Never hard-wrap prose at a fixed column — not in markdown files, not in commit message bodies, not in PR descriptions. One paragraph = one line; one list item = one line, however long. Editors soft-wrap; manual line breaks create ragged gaps and make diffs noisy. Line breaks in prose are reserved for real structure only: new paragraph, new list item, headings, tables, and code blocks (code keeps its normal line breaks).
Source-of-truth documents (read in this order)
AGENTS.md— the process contract. Non-negotiable.docs/design/design-decisions.md— ratified decisions. If your change contradicts an entry, the entry wins until amended.docs/design/VISION.md— direction, roadmap, open problems.docs/ARCHITECTURE.md— how the code actually works (module walkthrough, data flow).
Directory map
src/
core/state.js # THE kernel: Proxy, per-state microtask flush, $subscribe, read observers
core/batch.js # cross-store synchronous batching (state.js imports it; never the reverse)
core/effect.js # auto-tracking + explicit-deps effects (built on withReadObserver)
core/bindDom.js # data-* attribute binding, handler engine, two-way input delegation
state.js # `lume-js/state` entry (kernel only, DOM-free)
index.js # `lume-js` entry (state + bindDom + effect)
all.js # CDN/global IIFE entry (re-exports everything)
addons/ # computed, watch, repeat, persist, hydrateState, cleanupGroup, withPlugins, debug
handlers/ # show, className, classToggle, boolAttr, ariaAttr, stringAttr, on, presets, htmlAttrs
utils/log.js # logError/logWarn (the only module handlers may import)
*.d.ts # HANDWRITTEN type declarations — update in the same commit as signature changes
tests/ # vitest + jsdom; mirrors src/ layout; 439 tests, 100% coverage enforced
docs/api/ # one reference page per public export
docs/guides/ # universal-core, choosing-reactive-primitives, cleanup, SSR
docs/design/ # design-decisions.md (contract) + VISION.md (roadmap)
docs/changes/ # per-commit write-ups for proposal branches
examples/ # runnable demos; import from 'lume-js' (vite alias → src/)
scripts/ # build.js, check-size.js, complexity.js, bench-core.js, build-site-assets.js
gh-pages/ # docs-site source (deployed by workflow — don't touch unless asked)
dist/ # generated by scripts/build.js — never edit, not tracked in git
.github/workflows/ # ci.yml (tests/coverage/gates), gh-pages.yml, publish.yml (on release)
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.
- 6d ago First seen · 87 lines · 1,758 tokens per session scan A a9bf956bd218
lume-js CLAUDE.md is an instructions file published in the GitHub repository sathvikc/lume-js (44 stars, last pushed 1mo ago), licensed MIT. It adds 1,758 tokens to every session, about $0.0088 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).