What is loopat CLAUDE.md?

A project instruction document for loopat, a self-hosted AI workspace with a server and web interface in one repository. It covers the Bun, Hono, React, Vite, Rust, container, and Playwright testing setup.

Use it to run the server or web app, build the Rust components, and run the full browser-based dogfood tests for the real application stack.

It tells contributors how the monorepo, meaning one repository containing multiple related workspaces, is developed and tested.

loopat CLAUDE.md — Instructions file by simpx

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/simpx/loopat/claude-md

Clone the repo

git clone --depth 1 https://github.com/simpx/loopat

Per session 708 This file is loaded in full into every session.

When invoked 708 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	$0.00708	$0.00708
Opus 5	$0.00354	$0.00354
Sonnet 5	$0.00142	$0.00142
Haiku 4.5	$0.00071	$0.00071

Measured yesterday against content hash 9c1d1d47271c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loopat 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.

CLAUDE.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

loopat

Self-hosted AI workspace built around context management. Monorepo with two workspaces: server/ (Hono + Bun) and web/ (React 19 + Vite + Tailwind v4).

Tech stack

Runtime: Bun (server + build tooling)
Server: Hono, TypeScript, Claude Agent SDK, podman (sandbox containers)
Web: React 19, Vite 8, Tailwind CSS v4, Zustand, assistant-ui, xterm.js, CodeMirror, Milkdown
Infra: Docker (oven/bun base), rootless podman inside container
Tests: Playwright (e2e + dogfood)
Rust: Two small binaries in server/src/serve-rs and server/src/port-proxy-rs, built as part of web build

Development

bun run dev          # start server + web concurrently (localhost)
bun run dev:host     # same but bind 0.0.0.0
bun run dev:server   # server only
bun run dev:web      # web only

Server default port: 10001. Vite dev default port: 5173.

Push directly to main — no PR workflow for daily development.

Testing

The must-run test suite is the dogfood e2e tests — they boot a real stack (podman sshd container + backend + Vite + real AI) and drive a browser through it.

# Full dogfood suite (requires podman + ANTHROPIC_API_KEY)
bun run dogfood

# Smoke subset (first-5-minutes scenarios)
bun run dogfood:smoke

# Individual suites
bun run dogfood:first-run
bun run dogfood:journey
bun run dogfood:sync

Prerequisites: podman installed, ANTHROPIC_API_KEY exported. Missing either = hard fail (never skip).

There's also a lighter e2e/ suite that uses mocked backends:

bun run test:e2e

Build

bun run build        # install deps + build web (includes Rust binaries)
bun run build:web    # web only (cargo + tsc + vite)

Release

Versions follow 0.1.x. Release flow:

npm version patch    # bumps package.json, commits, tags v0.1.x
git push origin main --tags

Pushing a v* tag triggers two GitHub Actions:

publish.yml — publishes to npm
docker.yml — builds multi-arch (amd64 + arm64) Docker image to ghcr.io/simpx/loopat

Read the full file on GitHub · 85 lines

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.

yesterday First seen · 85 lines · 708 tokens per session scan A 9c1d1d47271c

Subscribe to this mod's changes

loopat CLAUDE.md is an instructions file published in the GitHub repository simpx/loopat (81 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 708 tokens to every session, about $0.0035 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.

Frontend Memory and context Testing agentic-ai ai-agent claude coding-agent context-management developer-tools

loopat CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

loopat

Tech stack

Development

Testing

Build

Release

What this file has done since we first saw it

Other instructions, from other repositories

Tianshu-harness CLAUDE.md

code-assistant AGENTS.md

nori-skillsets AGENTS.md

sortie copilot-instructions.md

open-plan-annotator AGENTS.md

copperhead AGENTS.md