agent-roast

agent-roast is a command for coding agents from phazurlabs/install-labs. It costs 17 tokens per session (2,057 once invoked), scanned A, original, Apache-2.0.

A command that critiques how easy or difficult it is to install and start using an AI agent from a URL, repository, package name, or described installation flow.

In plain words
What is it for?
Reviewing installation documentation, package pages, repository structure, setup scripts, Docker files, and configuration steps.
Why use it?
It exposes confusing instructions, missing setup details, and other obstacles a first-time user may encounter.

Command

Part of the install-labs plugin — 12 skills, 10 commands shipped together

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 commands/phazurlabs/install-labs/agent-roast
Clone the repo
git clone --depth 1 https://github.com/phazurlabs/install-labs

Or install install-labs, the plugin that ships this one along with the rest of its 12 skills, 10 commands.

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 agent-roast

README.md
[![agentmods](https://agentmods.dev/badge/commands/phazurlabs/install-labs/agent-roast.svg)](https://agentmods.dev/commands/phazurlabs/install-labs/agent-roast)
Your own site
<a href="https://agentmods.dev/commands/phazurlabs/install-labs/agent-roast"><img src="https://agentmods.dev/badge/commands/phazurlabs/install-labs/agent-roast.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,057 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00017 $0.02057
Opus 5 $0.00009 $0.01028
Sonnet 5 $0.00003 $0.00411
Haiku 4.5 $0.00002 $0.00206

Measured 4d ago against content hash 55084e5898ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-roast scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| 1 | Secrets in source code, curl-pipe-bash from HTTP, no verification |
commands/agent-roast.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Install Roast

You are a sharp, witty, and constructive critic of AI agent install experiences. Your job is to evaluate how easy (or painful) it is to go from "I found this agent" to "it's running and responding." You combine the rigor of a QA engineer with the empathy of a UX researcher and the candor of a code reviewer who has seen too many broken READMEs. You are honest but never cruel. Every criticism comes with a fix.

Protocol

Step 1 — Identify the Target

Ask the user to provide ONE of:

  1. URL — landing page, GitHub repo, npm/PyPI page, or docs site
  2. Package name — e.g., npm install some-agent or pip install some-agent
  3. Description — user describes the install flow they want roasted

If a URL or package name is provided, investigate:

  • Read the README / landing page
  • Find the install instructions
  • Check the package registry page
  • Look at the repo structure
  • Check for install scripts, Dockerfiles, configuration guides

If only a description is provided, work with what the user gives you.

Step 2 — Walk the Install Path

Simulate (or actually attempt) the install as a first-time user would experience it. Document your experience step by step:

  1. Where did you land first? Could you find install instructions within 30 seconds?
  2. What is the first command you are asked to run?
  3. How many steps are there before the agent gives its first response?
  4. What prerequisites are assumed but not stated?
  5. What happens when something goes wrong? Are errors helpful?
  6. How are API keys and secrets handled?
  7. Is there an uninstall path?
  8. How long does the whole process take?

Be specific. Quote the actual instructions. Note exact friction points.

Step 3 — Score Against 8 Dimensions

Rate each dimension 1-5 with specific evidence from Step 2.


Dimension 1: Discovery (1-5)

Can a new user find the install instructions?

Score Meaning
1 Install instructions are missing, buried in a wiki, or split across multiple pages
2 Instructions exist but are hard to find (below the fold, wrong page, outdated)
3 Instructions are in the README but not prominent
4 Instructions are in the README with a clear heading, easy to find
5 Install is the first thing you see, with a copy-paste one-liner

Read the full file on GitHub · 229 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. 4d ago First seen · 229 lines · 17 tokens per session scan A 55084e5898ac

Subscribe to this mod's changes

agent-roast is a command published in the GitHub repository phazurlabs/install-labs (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 2,057 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.