What is agentbnb CLAUDE.md?

Project instructions for AgentBnB, a service where people rent access to a mature AI agent for a fixed time. Its main pieces are an agent profile, a time-limited shared workspace, and a shareable outcome page.

Use them when building AgentBnB's web room, rental sessions, outcome pages, or Hermes plugin. They also describe the product's current terminology and technical boundaries.

They clarify the product's current direction and which integrations and interfaces are considered official, preventing work based on outdated plans.

How Xiaoher-C/agentbnb configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Xiaoher-C/agentbnb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Xiaoher-C/agentbnb/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Xiaoher-C/agentbnb

Made for: Claude Code.

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/xiaoher-c/agentbnb/claude-md.svg)](https://agentmods.dev/instructions/xiaoher-c/agentbnb/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/xiaoher-c/agentbnb/claude-md"><img src="https://agentmods.dev/badge/instructions/xiaoher-c/agentbnb/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 5,397 This file is loaded in full into every session.

When invoked 5,397 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	$0.05397	$0.05397
Opus 5	$0.02698	$0.02698
Sonnet 5	$0.01079	$0.01079
Haiku 4.5	$0.00540	$0.00540

Measured 6d ago against content hash 5331fb637e6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agentbnb 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 6d 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.

CLAUDE.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — AgentBnB

⚡ v10 Pivot — Agent Maturity Rental (2026-05-04)

READ THIS FIRST when starting any new session on this repo.

AgentBnB has pivoted from "skill marketplace" to Agent Maturity Rental. The unit of trade is no longer an atomic skill — it is a session of access to a long-tuned agent (a renter borrows another user's mature Hermes / OpenClaw agent for a fixed time window).

One-line product: 「租一個別人調校了半年的 AI 員工 60 分鐘」.

Three primitives (replaced the old "Capability Card" centric model):

Agent Profile — public page for a rentable agent: Maturity Evidence + past outcomes + tools + price
Rental Session — time-boxed shared workspace with threads, files, mode toggle
Outcome Page — auto-generated shareable artifact at /o/:share_token (virality + portfolio)

Canonical integrations (v1):

Web room at /s/{id} is the canonical UI (NOT Discord/Telegram/Liveblocks/Next.js — all v2)
Hermes plugin (hermes-plugin/ — Python, intended for the Hermes ecosystem; upstream PR plan retired 2026-06-07 — see docs/maintenance/2026-06-07-reposition/REPOSITION-DECISION.md) is the canonical supply integration. Two-command onboarding: hermes plugin install agentbnb && hermes agentbnb publish. OpenClaw skill (skills/agentbnb/) preserved for backward compat but not actively pushed.

Privacy contract (ADR-024 — three-layer enforcement, MUST be honoured by all new code):

「租用執行能力，不租用 agent 的腦與鑰匙」

Tools execute on owner machine, renter only sees results
Session conversation per-sessionId isolated, NEVER pollutes owner agent's main memory
request_log skips persistence when session_mode=true (verified by src/session/privacy.test.ts)
Curated Rental Runner spawns isolated subagent loaded with owner-curated RENTAL.md (NOT main SOUL/SPIRIT)

Maturity Evidence > Maturity Score: never collapse maturity into a single number (would be gamed and lossy). Show evidence categories: platform-observed sessions / completed tasks / repeat renters / artifact examples / verified tools / response reliability / renter rating.

Read the full file on GitHub · 300 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.

6d ago First seen · 300 lines · 5,397 tokens per session scan A 5331fb637e6b

Subscribe to this mod's changes

agentbnb CLAUDE.md is an instructions file published in the GitHub repository Xiaoher-C/agentbnb (32 stars, last pushed 2mo ago), licensed MIT. It adds 5,397 tokens to every session, about $0.0270 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.

agent-network agent-skills ai-agent-skill claude-code codex cursor

data-scientist copilot-instructions.md

Instructions for realnghon/data-scientist, covering github copilot — 项目指令：data scientist 工作流 and 共享核心 — 回答前请阅读.

realnghon/data-scientist · 373 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

agentbnb: Instructions file for Claude Code