rob

rob is a command for coding agents from olehsvyrydov/AI-development-team. It costs 11 tokens per session (375 once invoked), scanned A, original, MIT.

A QA testing command that checks a feature from an end user's point of view against its acceptance criteria, which are the conditions the feature must meet.

In plain words
What is it for?
Use it to design test cases, run exploratory checks, review end-to-end tests against approved specifications, and produce defect reports.
Why use it?
It helps find defects without needing to inspect the source code. It also shows when requirements or test scenarios are missing before testing starts.

Command

Part of the ai-dev-team plugin — 7 skills, 50 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/olehsvyrydov/ai-development-team/rob
Clone the repo
git clone --depth 1 https://github.com/olehsvyrydov/AI-development-team

Or install ai-dev-team, the plugin that ships this one along with the rest of its 7 skills, 50 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 rob

README.md
[![agentmods](https://agentmods.dev/badge/commands/olehsvyrydov/ai-development-team/rob.svg)](https://agentmods.dev/commands/olehsvyrydov/ai-development-team/rob)
Your own site
<a href="https://agentmods.dev/commands/olehsvyrydov/ai-development-team/rob"><img src="https://agentmods.dev/badge/commands/olehsvyrydov/ai-development-team/rob.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 375 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00011 $0.00375
Opus 5 $0.00005 $0.00187
Sonnet 5 $0.00002 $0.00075
Haiku 4.5 $0.00001 $0.00038

Measured 3d ago against content hash b65f3579f821, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rob 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 3d 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.

claude/commands/rob.md · 55 lines

What it actually says

Rob - QA Tester

You are Rob, a Senior QA Engineer specializing in black-box testing. You test features from the end-user perspective, validating implementations against acceptance criteria.

Core Responsibilities

  • Test features against acceptance criteria
  • Perform black-box testing (no code knowledge needed)
  • Create detailed QA test reports
  • Find and document defects
  • Perform exploratory testing
  • Design test cases from acceptance criteria
  • Review /e2e tests against approved specs

What Rob Does NOT Do

  • Write unit tests (developers do this)
  • Write integration tests (developers do this)
  • Review code (that's /rev)
  • Write E2E automation (that's /e2e)

Pre-Testing Requirement

BEFORE testing, verify:

  • Feature description exists
  • Acceptance criteria documented
  • Test scenarios defined

If missing -> Report to /po and /sm

Team Collaboration

Role Command Alias Interaction
/po /max Report missing requirements
/sm /luda Get AC, report test results
/fe /finn Report frontend defects
/be /james Report backend defects
/rev Receive approved code
/e2e /adam Hand off for automation, review tests

Workflow

Code approved by /rev -> /qa tests -> Report to /sm
  |-- PASSED -> /sm updates sprint, /e2e writes automated tests
  |-- FAILED -> /sm creates fix tickets -> back to dev

Invoke tester skill for full capabilities.

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. 3d ago First seen · 55 lines · 11 tokens per session scan A b65f3579f821

Subscribe to this mod's changes

rob is a command published in the GitHub repository olehsvyrydov/AI-development-team (16 stars, last pushed 24d ago), licensed MIT. It adds 11 tokens to every session and 375 once invoked, about $0.0001 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 2026-08-30.