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/codetalcott/hyperscript-tools/claude-mdgit clone --depth 1 https://github.com/codetalcott/hyperscript-toolsWhat 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 | $0.01471 | $0.01471 |
| Opus 5 | $0.00736 | $0.00736 |
| Sonnet 5 | $0.00294 | $0.00294 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
hyperscript-tools 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 yesterday.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
Tooling for original _hyperscript (hyperscript.org, from Big Sky Software). An npm-workspaces monorepo; the only package today is @hyperscript-tools/mcp-server — an MCP server that gives AI agents a parser-backed understanding of _hyperscript (validation, parsing, docs, editor assist).
The governing invariant: verdicts come from _hyperscript's own parser, not from regex approximations. Depend only on the canonical hyperscript.org npm package — never a fork.
Commands
Run from the repo root (npm workspaces fan out to each package):
npm install # install all workspaces
npm run build # build all packages
npm run test # run all test suites (vitest run)
npm run typecheck # tsc --noEmit across packages
Inside packages/mcp-server-hyperscript/:
npm run dev # run the server from source via tsx (stdio transport)
npm run build # bundle with tsup (ESM + .d.ts) to dist/
npm test # vitest in watch mode
npm run test:run # vitest single run
npm run typecheck # tsc --noEmit
Run a single test file or by name (from the package dir):
npx vitest run src/__tests__/golden.test.ts
npx vitest run -t "validates correct hyperscript"
Node 20+ required (CI runs on Node 24). There is no lint step.
Architecture
Everything hangs off one seam and one invariant.
The loader is the only door to _hyperscript
src/hyperscript-loader.ts is the single place that touches the canonical library. All language knowledge flows through it; there is deliberately no second, hand-rolled grammar to drift from upstream. It exposes parse/safeParse/tokenize/registryProbe/hyperscriptVersion.
Two non-obvious things it handles:
- Awkward import.
hyperscript.org'sexportsmap points the package root at the IIFE build, which exports nothing to an ESM importer in Node. The loader resolves the package, then imports the sibling_hyperscript.esm.jsby absolute file URL. - Headless safety. It only ever calls
parse/tokenize(which never execute hyperscript), and the library's DOM bootstrap istypeof document-guarded, so importing in bare Node touches no DOM.
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.
- yesterday First seen · 90 lines · 1,471 tokens per session scan A 708181d3a621
hyperscript-tools CLAUDE.md is an instructions file published in the GitHub repository codetalcott/hyperscript-tools (0 stars, last pushed 6d ago), licensed MIT. It adds 1,471 tokens to every session, about $0.0074 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
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.
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).
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.