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/hoophq/hoop/claude-mdgit clone --depth 1 https://github.com/hoophq/hoopWrote 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/hoophq/hoop/claude-md)<a href="https://agentmods.dev/instructions/hoophq/hoop/claude-md"><img src="https://agentmods.dev/badge/instructions/hoophq/hoop/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 | $0.07260 | $0.07260 |
| Opus 5 | $0.03630 | $0.03630 |
| Sonnet 5 | $0.01452 | $0.01452 |
| Haiku 4.5 | $0.00726 | $0.00726 |
Grade A, and why
hoop 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 — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
A Go workspace (go.work) for the hoop gateway, agent, and CLI.
- Product modules:
gateway/,agent/,client/,common/,tunnel/. sidecar/adds seven more workspace entries (the module plus six nested ones). It washoopinspect/until the CLI command becamehoop start sidecar.agentrs/— Rust companion binary for RDP/TLS proxy workloads.webapp/— legacy ClojureScript SPA; seewebapp/CLAUDE.mdfor its own conventions.webapp_v2/— React frontend that is replacing it.libhoopis not in this repo. It is one private module,github.com/hoophq/libhoop, resolved from the module proxy like any other dependency. Builds needGOPRIVATE=github.com/hoophq/libhoopand credentials for it. To work against a local clone,make libhoop-dev.
Toolchain & Prerequisites
- Go >= 1.26, Rust +
cross(for cross-compiledagentrs), Docker, Node/npm, Clojure/Java. - PostgreSQL is the default state store (
POSTGRES_DB_URI).POSTGRES_DB_URI=pglite:///<data-dir>starts the embedded PGlite instead (gateway/pglite). golang-migrateCLI for creating new SQL migration files.swag(v1.16.3) for regenerating OpenAPI docs.- See
DEV.mdfor full setup walkthrough.
Architecture
┌────────┐ gRPC :8010 ┌─────────┐ gRPC :8010 ┌───────┐
│ Client │ ─────────────> │ Gateway │ <──────────── │ Agent │
│ (CLI) │ Packet stream │ (API+ │ Packet stream│ │
└────────┘ │ gRPC) │ └───────┘
│ :8009 HTTP/UI
└─────────┘
│
PostgreSQL
Module Breakdown
Client (client/)
- Entrypoint:
client/hoop.go→client/cmd/root.go(Cobra CLI). - Key commands:
connect.go,exec.go,login.go,run.go,start.go,proxymanager.go, etc. - User commands send packetized messages over a
Transport.Connectbidirectional gRPC stream. - Local proxy manager (
client/cmd/proxymanager.go) opens local ports for protocol proxying (PG, SSH, etc).
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 Changed · +2 tokens per session 91677cd1147b
- 6d ago First seen · 389 lines · 7,258 tokens per session scan A f746b8ede71b
hoop CLAUDE.md is an instructions file published in the GitHub repository hoophq/hoop (807 stars, last pushed today), licensed MIT. It adds 7,260 tokens to every session, about $0.0363 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
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
rome CLAUDE.md
Claude Code instructions for rome-os/rome, covering rome, playbook and traps.
zapcode CLAUDE.md
Instructions for TheUncharted/zapcode, covering claude.md, git, read agents.md first, codebase orientation and how to add a new language feature.
MathModelAgent CLAUDE.md
Claude Code instructions for jihe520/MathModelAgent, covering claude.md, 项目概述, commands, 后端 and 安装依赖.
ralph CLAUDE.md
Claude Code instructions for SantanderAI/ralph, covering ralph — instrucciones del proyecto and paridad bash ↔ powershell (importante).
memory-bridge AGENTS.md
AGENTS.md instructions for jiabaobei/memory-bridge, covering agents.md — 记忆桥项目规约(ai 协作会话必读), 版本与发布(硬性规则,所有者 2026-08-29 定), 架构铁律 and 工程习惯.