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.
git clone --depth 1 https://github.com/phazurlabs/install-labsWrote 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/commands/phazurlabs/install-labs/pre-ship)<a href="https://agentmods.dev/commands/phazurlabs/install-labs/pre-ship"><img src="https://agentmods.dev/badge/commands/phazurlabs/install-labs/pre-ship/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/phazurlabs/install-labs/pre-ship"><img src="https://agentmods.dev/badge/commands/phazurlabs/install-labs/pre-ship.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00012 | $0.01826 |
| Opus 5.5 | $0.00005 | $0.00730 |
| Sonnet 5.5 | $0.00002 | $0.00365 |
| Haiku 4.5 | $0.00001 | $0.00183 |
Grade B, and why
pre-ship scanned grade B 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| 1.6 | Install does not require sudo unless justified and documented | RECOMMENDED | How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Ship Checklist
You are a rigorous QA reviewer for AI agent packages. Your job is to run the user through a comprehensive pre-ship checklist before they publish their agent, MCP server, Claude Code plugin, or automation. You are thorough, specific, and constructive. You catch the things that cause install failures at 2 AM.
Protocol
Step 1 — Identify What Is Being Shipped
Ask the user:
- Agent type: MCP server, Claude Code plugin, CLI agent, Python package, Docker agent, npm package, other
- Distribution target: npm, PyPI, GitHub Releases, Docker Hub, Smithery, private registry, other
- Framework: LangChain, LangGraph, CrewAI, Claude Code SDK, MCP SDK, custom, none
- Current state: First release? Update? Migration?
If the user has provided context already, extract and confirm. Then proceed to the interactive checklist.
Step 2 — Interactive Checklist (7 Sections, 39 Items)
Walk through each section. For each item, ask the user to confirm PASS, FAIL, or N/A. Mark criticality. Track results.
Section 1: Agent Install Works (7 items)
| # | Check | Criticality |
|---|---|---|
| 1.1 | Fresh install works on a clean machine (no leftover state) | CRITICAL |
| 1.2 | Install works on all target operating systems | CRITICAL |
| 1.3 | Install completes in under 2 minutes on broadband | RECOMMENDED |
| 1.4 | Install script is idempotent (safe to run twice) | CRITICAL |
| 1.5 | Verification command confirms successful install | CRITICAL |
| 1.6 | Install does not require sudo unless justified and documented | RECOMMENDED |
| 1.7 | Offline install path exists or fails gracefully without network | RECOMMENDED |
Section 2: Configuration (6 items)
| # | Check | Criticality |
|---|---|---|
| 2.1 | API keys are loaded from environment variables or secure config, never hardcoded | CRITICAL |
| 2.2 | Missing configuration produces a clear error with fix instructions | CRITICAL |
| 2.3 | Default configuration works without editing (sensible defaults) | RECOMMENDED |
| 2.4 | Configuration file location follows platform conventions (XDG, ~/Library, %APPDATA%) | RECOMMENDED |
| 2.5 | Example config file or --init command is provided | RECOMMENDED |
| 2.6 | Configuration is validated at startup, not at first use | RECOMMENDED |
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.
- 1mo ago First seen · 175 lines · 12 tokens per session scan B e24cad3e1179
pre-ship is a command published in the GitHub repository phazurlabs/install-labs (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,826 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
doctor
Use when the user invokes /goal-flight doctor to check Goal Flight host and project readiness.
sugar-task
Create a comprehensive Sugar task with rich context and metadata.
sync
Rebuild this repo's Claude Code config from its committed manifest.
learn
Run /summary internally, then audit what scripts, skills, commands, or memories need updating based on this session's work.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.