shipbook-tools

shipbook-tools is a cursor rule for coding agents from ShipBook/shipbook-mcp. It costs 753 tokens per session, scanned A, original, MIT.

A set of guidelines for using Shipbook, a cloud service for app logs, to investigate errors and user sessions. It describes searches by message, code location, device, user, app version, and recurring error.

In plain words
What is it for?
Use it to list Shipbook apps, find individual logs, group recurring errors, filter by users or devices, and inspect warnings and errors.
Why use it?
It gives the coding agent a consistent way to choose the right app, search logs, and narrow down recurring or user-specific problems.

Cursor rule

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 rules/shipbook/shipbook-mcp/shipbook-tools
Clone the repo
git clone --depth 1 https://github.com/ShipBook/shipbook-mcp

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.

agentmods badge for shipbook-tools

README.md
[![agentmods](https://agentmods.dev/badge/rules/shipbook/shipbook-mcp/shipbook-tools.svg)](https://agentmods.dev/rules/shipbook/shipbook-mcp/shipbook-tools)
Your own site
<a href="https://agentmods.dev/rules/shipbook/shipbook-mcp/shipbook-tools"><img src="https://agentmods.dev/badge/rules/shipbook/shipbook-mcp/shipbook-tools.svg" alt="Measured on agentmods" height="20"></a>
Per session 753 This file is loaded in full into every session.
When invoked 753 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.

ModelPer sessionOnce invoked
Fable 5 $0.00753 $0.00753
Opus 5 $0.00377 $0.00377
Sonnet 5 $0.00151 $0.00151
Haiku 4.5 $0.00075 $0.00075

Measured 5d ago against content hash 2549e3c62c95, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipbook-tools 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.

rules/shipbook-tools.mdc · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shipbook Tools Usage Guide

You have access to Shipbook MCP tools for cloud log analysis.

Available Tools

  1. get-account-apps — Lists all apps in the account (name, appId, platform, key, integration). Call this first to get the appId and key needed by other tools and for SDK initialization.

  2. create-app — Creates a new app in the account. Returns name, appId, and key. Platform is detected automatically on first SDK session.

    • Required: name
  3. get-loglytics-errors — Returns grouped/classified recurring errors for an app. Shows occurrence count, affected devices, sessions, app versions, and OS versions.

    • Required: appId
    • Optional: severity (Error, Warning), appVersion
  4. get-logs — Searches and retrieves individual log entries.

    • Required: appId
    • Severity: severity — Error, Warning, Info, Debug, Verbose
    • Text search: msg (free text in messages)
    • Code location: tag, fileName, lineNumber
    • Device: udid (unique device ID), deviceModel, manufacturer
    • User: userId, userName, fullName, email, phoneNumber
    • App: appVersion
    • Loglytics: key (error key from get-loglytics-errors — finds all logs for a specific classified error)
    • Session: session (session ID — retrieves all logs from that session)
    • Pagination: minOrderId (logs after this order), maxOrderId (logs before this order)
    • Time range: fromTime, toTime (ISO format)
    • Limit: limit (default: 50)

Investigation Workflow

  1. Start with get-account-apps to identify the target app and get its appId
  2. Use get-loglytics-errors to see grouped errors — identifies the most frequent and impactful issues
  3. Use get-logs with severity=Error and relevant filters (udid, userId, email) to find specific error instances
  4. Get context around a specific log: call get-logs again with the same session ID, set maxOrderId to the log's orderId + 10, and remove the severity filter. This shows what happened leading up to that log.
  5. Every log has fileName and lineNumber — always use these to locate and read the actual code in the project. This is the best way to understand what the log means and find the root cause.
  6. Use key from loglytics errors in get-logs to find all instances of a specific classified error
  7. Use minOrderId/maxOrderId to paginate within a session (get logs before/after a specific log entry)

Read the full file on GitHub · 56 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.

  1. 5d ago First seen · 56 lines · 753 tokens per session scan A 2549e3c62c95

Subscribe to this mod's changes

shipbook-tools is a cursor rule published in the GitHub repository ShipBook/shipbook-mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 753 tokens to every session, about $0.0038 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 2026-08-31.