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/uncfreak1255-code/hostaway-mcp/agents-mdgit clone --depth 1 https://github.com/uncfreak1255-code/hostaway-mcpWrote 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/uncfreak1255-code/hostaway-mcp/agents-md)<a href="https://agentmods.dev/instructions/uncfreak1255-code/hostaway-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/uncfreak1255-code/hostaway-mcp/agents-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 | $0.01297 | $0.01297 |
| Opus 5 | $0.00648 | $0.00648 |
| Sonnet 5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade C, and why
hostaway-mcp AGENTS.md scanned grade C with 1 finding 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
npm run build # rm -rf dist && tsc -p tsconfig.build.json How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hostaway MCP — Agent Instructions (Canonical)
This is the canonical agent kernel for the hostaway-mcp repo. CLAUDE.md is a
thin Claude-specific delta that points back here. Any unique operating signal
lives in this file.
This repo owns the open-source Hostaway MCP server: the operator product
only — local/npm stdio, a small set of read-only, hospitality-shaped tools.
Scope & Write-Safety Contract (READ FIRST)
This is the safety-critical part of this repo. Get it exactly right.
mainis read-only. There are no write paths and no "safe" exceptions.src/server.tsregisters six read tools and nothing else:list_unread_guest_threads,get_conversation_context,get_reservation_brief,get_listing_brief,search_reservations,search_conversations. There is no write-tool registration, noHOSTAWAY_MCP_READONLYflag, and nosrc/write-infra/onmain.- No PMS mutation. Sending guest messages and mutating reservations or
listings are explicit V1 Non-Goals (see
README.md). The server only reads from Hostaway; it never writes to a guest, a reservation, or a listing. - The only credential is
HOSTAWAY_API_TOKEN(required, secret) with an optionalHOSTAWAY_BASE_URLoverride for testing. The token authenticates read requests. Never print, echo, or commit token values, and never read or echo the contents of.mcp.local.jsonor.mcpregistry_*files. - Introducing any write path is a [SENSITIVE CHANGE]. If a future plan adds guest messaging, reservation/listing mutation, or any other write surface, it must be an explicit, approved scope change with: a confirmation/dry-run guard so writes never execute by default, an audit trail for every write, rate limiting, and regression tests covering the guard. Do not add write tools as an incidental part of unrelated work, and do not weaken the read-only default. Default to read-only.
- No booking/distribution Worker in this repo. Cloudflare Worker transport
and Seascape booking/distribution flows are Non-Goals. Do not add a Worker,
wrangler.toml, webhook ingestion, or background sync pipelines here.
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.
- 4d ago First seen · 115 lines · 1,297 tokens per session scan C 964a274d8933
hostaway-mcp AGENTS.md is an instructions file published in the GitHub repository uncfreak1255-code/hostaway-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 1,297 tokens to every session, about $0.0065 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
hostaway-mcp CLAUDE.md
Instructions for prosperkartik/hostaway-mcp, covering claude.md, hard rules (read these first), tech stack (locked — don't change without good reason), file layout and auth flow (don't trip on this).
hostaway-mcp CLAUDE.md
Claude Code instructions for mattlong-plux/hostaway-mcp, covering hostaway mcp server — project brief, goal, tech stack, project structure and authentication.
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).
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.
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.
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).