What is loophaus AGENTS.md?

Project instructions for loophaus, a TypeScript project that runs task workflows through platform adapters, commands, skills, and a stop hook. They describe its folders, coding conventions, tests, and build commands.

Use them when adding core modules, platform support, commands, skills, hooks, or tests, and when running type checks, builds, or coverage.

They reduce mistakes caused by putting code in the wrong area or using incompatible file and module formats.

loophaus AGENTS.md — Instructions file for Codex and OpenCode by vcz-Gray: Project instructions for loophaus, a TypeScript project that runs

Install

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.

agentmods

npx agentmods add instructions/vcz-gray/loophaus/agents-md

Clone the repo

git clone --depth 1 https://github.com/vcz-Gray/loophaus

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vcz-gray/loophaus/agents-md.svg)](https://agentmods.dev/instructions/vcz-gray/loophaus/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/vcz-gray/loophaus/agents-md"><img src="https://agentmods.dev/badge/instructions/vcz-gray/loophaus/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 380 This file is loaded in full into every session.

When invoked 380 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00380	$0.00380
Opus 5	$0.00190	$0.00190
Sonnet 5	$0.00076	$0.00076
Haiku 4.5	$0.00038	$0.00038

Measured 5d ago against content hash 062dab043d28, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

loophaus 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 5d 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.

AGENTS.md · 39 lines

What it actually says

AGENTS.md

Instructions for AI agents working on the loophaus codebase.

Project Structure

core/ — Pure TypeScript modules (engine, scoring, cleanup, etc.)
store/ — State persistence (atomic JSON writes)
lib/ — Shared utilities (paths, stop-hook-core)
bin/ — CLI entry point (loophaus.ts)
platforms/ — Platform adapters (Claude Code, Codex CLI, Kiro CLI)
commands/ — Slash command definitions (.md)
skills/ — Platform-specific skill definitions
hooks/ — Stop hook (stays as .mjs, not TypeScript)
tests/ — Vitest test files (.test.mjs)

Conventions

All source is TypeScript strict mode
Imports use .js extension (NodeNext module resolution)
Tests use .mjs extension (vitest runs them directly)
No external runtime dependencies (zero-dep)
hooks/ and platforms/ stay as .mjs (copied to user dirs, must run standalone)

Testing

npm test — run all tests
npm run typecheck — TypeScript strict check
npm run build — compile to dist/
npm run test:coverage — coverage report

Adding a new core module

Create core/your-module.ts
Add types to core/types.ts if shared
Create tests/your-module.test.mjs
Update bin/loophaus.ts if CLI-facing

Adding a new platform

Create platforms/your-platform/installer.mjs
Add detection in bin/loophaus.ts detectHosts()
Add install/uninstall handlers

Changes

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.

5d ago First seen · 39 lines · 380 tokens per session scan A 062dab043d28

Subscribe to this mod's changes

loophaus AGENTS.md is an instructions file published in the GitHub repository vcz-Gray/loophaus (23 stars, last pushed 4mo ago), licensed MIT. It adds 380 tokens to every session, about $0.0019 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.

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

loophaus AGENTS.md