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 rules/shipbook/shipbook-mcp/shipbook-toolsgit clone --depth 1 https://github.com/ShipBook/shipbook-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/rules/shipbook/shipbook-mcp/shipbook-tools)<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>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 | $0.00753 | $0.00753 |
| Opus 5 | $0.00377 | $0.00377 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00075 | $0.00075 |
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.
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
-
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.
-
create-app — Creates a new app in the account. Returns name, appId, and key. Platform is detected automatically on first SDK session.
- Required:
name
- Required:
-
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
- Required:
-
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)
- Required:
Investigation Workflow
- Start with get-account-apps to identify the target app and get its
appId - Use get-loglytics-errors to see grouped errors — identifies the most frequent and impactful issues
- Use get-logs with severity=Error and relevant filters (udid, userId, email) to find specific error instances
- Get context around a specific log: call get-logs again with the same
sessionID, setmaxOrderIdto the log's orderId + 10, and remove the severity filter. This shows what happened leading up to that log. - Every log has
fileNameandlineNumber— 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. - Use
keyfrom loglytics errors in get-logs to find all instances of a specific classified error - Use
minOrderId/maxOrderIdto paginate within a session (get logs before/after a specific log entry)
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.
- 5d ago First seen · 56 lines · 753 tokens per session scan A 2549e3c62c95
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.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.