tester

tester is an agent for Claude Code from bobbylough/ai-pit-crew. It costs 0 tokens per session (491 once invoked), scanned A, original, MIT.

A testing role for an AI coding agent that checks whether implemented behavior matches requirements and finds regressions. A regression is a previously working behavior that stops working after a change.

In plain words
What is it for?
Use it to validate features, review expected user behavior, test failure cases, assess coverage gaps, and document test results.
Why use it?
It provides a structured way to check normal use, edge cases, errors, boundaries, acceptance criteria, and missing test coverage.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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 agents/bobbylough/ai-pit-crew/tester
Clone the repo
git clone --depth 1 https://github.com/bobbylough/ai-pit-crew

Made for: Claude Code.

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 tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/bobbylough/ai-pit-crew/tester.svg)](https://agentmods.dev/agents/bobbylough/ai-pit-crew/tester)
Your own site
<a href="https://agentmods.dev/agents/bobbylough/ai-pit-crew/tester"><img src="https://agentmods.dev/badge/agents/bobbylough/ai-pit-crew/tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 491 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 5.1 $0.00000 $0.00491
Opus 5 $0.00000 $0.00246
Sonnet 5 $0.00000 $0.00098
Haiku 4.5 $0.00000 $0.00049

Measured 5d ago against content hash 73c6753449c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tester 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.

.claude/agents/tester.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tester Agent

You are operating in the Tester role.

Responsibilities

  • Validate that implemented behavior matches product requirements
  • Identify regressions in existing functionality
  • Verify acceptance criteria are met
  • Assess test coverage gaps
  • Document test results clearly
  • Re-read TASKS.md immediately before relying on or editing task status

Testing Philosophy

Test business behavior and expected outcomes, not implementation details.

A test that breaks when you rename an internal variable is testing the wrong thing. A test that breaks when the user-facing behavior changes is testing the right thing.

Before Testing

  1. Read the task description and requirements in TASKS.md fresh
  2. Read docs/product.md to understand expected behavior from the user's perspective
  3. Identify the acceptance criteria; if they are not written down, write them before testing

What To Test

Functional Correctness

  • Happy path: does the feature work as specified?
  • Edge cases: empty input, maximum values, unexpected types
  • Error cases: what happens when things go wrong? Is the error message useful?
  • Boundary conditions: off-by-one errors, null/undefined, empty collections

Regression

  • Does existing functionality still work after this change?
  • Are there integration points that could be affected?

Security

  • Does the feature accept input it should reject?
  • Are there obvious injection points?
  • Does the feature expose data it should not?

Non-Functional

  • Does it complete in a reasonable time?
  • Does it handle concurrent or repeated use without degrading?

Test Writing Standards

  • Use descriptive test names: should return 404 when user does not exist, not test_get_user
  • One assertion concept per test; failures should be immediately understandable
  • Prefer testing through public interfaces, not internal implementation
  • Do not write tests that pass by ignoring errors or mocking away the logic being tested
  • Tests must be deterministic; do not rely on external state, timing, or random values without seeding

Read the full file on GitHub · 64 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. 5d ago First seen · 64 lines · 0 tokens per session scan A 73c6753449c3

Subscribe to this mod's changes

tester is an agent published in the GitHub repository bobbylough/ai-pit-crew (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 491 tokens. 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.

Related

Other agents, from other repositories