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/htest-dev/htest/claude-mdgit clone --depth 1 https://github.com/htest-dev/htestWhat 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 | $0.01199 | $0.01199 |
| Opus 5 | $0.00600 | $0.00600 |
| Sonnet 5 | $0.00240 | $0.00240 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
htest 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 2d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hTest
Declarative JS testing framework. Two modes: JS-first (logic, Node/browser, CI) and HTML-first (UI, browser only).
Package: htest.dev | Repo: https://github.com/htest-dev/htest | Site: https://htest.dev
Commands
| Command | Purpose |
|---|---|
npm test |
Run full test suite (self-hosted — hTest tests itself) |
npx htest tests/check.js |
Run a single test file |
npm run eslint |
Lint |
npm run eslint:fix |
Lint and auto-fix |
npm run build |
TypeDoc (API docs) + Eleventy (docs site) |
npm run dev |
Eleventy dev server for docs site |
npm run release |
Publish via release-it |
No Prettier, no EditorConfig — ESLint only (eslint.config.js).
Architecture
src/
index.js Main exports: Test, TestResult, map, check, render, env
cli.js CLI entry: arg parsing, calls run()
run.js Environment-agnostic runner: resolves env, creates Test + TestResult
check.js Assertion library: equals, subset, proximity, deep, range, and/or
config.js Config file discovery, loading, and setup script processing
map.js Value extraction utilities (extract, extractNumbers, trimmed)
format-console.js ANSI formatting with custom HTML-like tag syntax
render.js Browser-side: renders JS-first tests as HTML reftest tables
hooks.js Generic extensibility hooks singleton
content.js DEPRECATED — re-exports equals from check.js with warning
util.js General utilities (stringify, getType, interceptConsole, etc.)
objects.js Object utilities (children, walk, clone, join)
interactive-tree.js Interactive CLI: ASCII tree rendering, keyboard nav, viewport scrolling
classes/
Test.js Test tree: property inheritance, structure, auto-naming
TestResult.js Execution, evaluation, output formatting, event-driven stats
BubblingEventTarget.js EventTarget subclass with bubbling support
env/
node.js Node env: file resolution, --watch orchestration, CI mode
console.js Browser console env (console.group output)
auto.js Auto-detects Node vs browser
util/
format-diff.js ANSI-colored diff output for failed assertions
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.
- 2d ago First seen · 103 lines · 1,199 tokens per session scan A caf5a9808547
htest CLAUDE.md is an instructions file published in the GitHub repository htest-dev/htest (23 stars, last pushed 19d ago), licensed MIT. It adds 1,199 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 2026-08-30.
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.