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 skills add phazurlabs/install-labs --skill agent-pre-ship-checklistgit 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/skills/phazurlabs/install-labs/agent-pre-ship-checklist)<a href="https://agentmods.dev/skills/phazurlabs/install-labs/agent-pre-ship-checklist"><img src="https://agentmods.dev/badge/skills/phazurlabs/install-labs/agent-pre-ship-checklist/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/skills/phazurlabs/install-labs/agent-pre-ship-checklist"><img src="https://agentmods.dev/badge/skills/phazurlabs/install-labs/agent-pre-ship-checklist.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 | $0.00076 | $0.05393 |
| Opus 5 | $0.00038 | $0.02697 |
| Sonnet 5 | $0.00015 | $0.01079 |
| Haiku 4.5 | $0.00008 | $0.00539 |
Grade A, and why
agent-pre-ship-checklist 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 9d 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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Pre-Ship Checklist
A quality gate specifically for AI agents and automations. Every item is about the experience of installing, configuring, running, and maintaining an agent -- not generic software quality. Work through each section before publishing.
Severity levels:
- CRITICAL -- Must fix. Shipping without this will cause install failures, security issues, or broken first runs.
- RECOMMENDED -- Should fix. Skipping this creates friction that drives users away.
- NICE -- Polish. Improves the experience for power users and edge cases.
1. Agent Install Works
The install is the first impression. If it fails, nothing else matters.
- [CRITICAL] Agent tested on a clean machine (not your dev machine)
- Use a fresh VM, container, or a colleague's laptop. Your dev machine has tools, paths, and env vars that mask broken installs.
- Quick test: spin up a Docker container (
docker run -it python:3.12-slim bash) and try your install steps from scratch.
- [CRITICAL] Install works without prerequisites not listed in docs
- If it needs Python 3.11+, say so. If it needs
ffmpeg, say so. Do not assume anything is pre-installed. - Audit your implicit dependencies:
lddon Linux,otool -Lon macOS, or check import errors in a bare environment.
- If it needs Python 3.11+, say so. If it needs
- [CRITICAL] First run produces a response (not a crash or silent failure)
- Run the agent immediately after install with no additional setup beyond what the install docs describe. It must produce output.
- Test the exact commands from your README. Copy-paste them. Do not type from memory.
- [CRITICAL] API key handling: clear error if missing, guided setup if needed
- If the agent needs an API key and one is not set, the error must say: what key is missing, where to get it, and how to set it. Never print a raw traceback or generic "unauthorized" error.
- Test this: unset the key (
unset ANTHROPIC_API_KEY) and run the agent. Read the error message as a new user would.
- [RECOMMENDED] Install is 1-2 steps (not 10+)
- Ideal:
pipx install my-agentthenmy-agent --help. Anything beyond 3 steps needs strong justification. - Count your steps honestly. "Clone the repo" is step 1. "cd into it" is step 2. "Create a venv" is step 3. You are already at 3 and the agent is not installed yet.
- Ideal:
- [RECOMMENDED] Time from install command to first successful agent response: under 2 minutes
- Measure this with a stopwatch. Start when the user types the install command. Stop when the agent produces its first useful output. Under 2 minutes is the target.
- If dependency installation alone takes 90 seconds, you need to reduce the dependency footprint or pre-build wheels.
- [NICE] Works behind corporate firewalls and proxies
- Respect
HTTPS_PROXYandHTTP_PROXYenvironment variables. Do not hard-fail on certificate verification without a clear message. - Test with:
HTTPS_PROXY=http://localhost:9999 my-agent ask "test"-- it should fail with a clear proxy/network error, not a cryptic SSL exception.
- Respect
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.
- 9d ago First seen · 305 lines · 76 tokens per session scan A c3cbc4d917e2
agent-pre-ship-checklist is a skill published in the GitHub repository phazurlabs/install-labs (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 5,393 once invoked, about $0.0004 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 skills, from other repositories
local-ci
Run GitHub Actions workflows locally with pause-on-failure for AI-agent-driven CI iteration.
local-ci
Run GitHub Actions CI locally with Local CI to validate changes before pushing. Use when testing, running checks, or validating code changes.
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
generate-run-commands
Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
memory
Retrieve relevant durable BB memories or save verified knowledge useful to future threads.