tester

A testing assistant that chooses and writes tests based on the risks and purpose of the code, including unit tests for individual parts and integration tests for connected systems.

In plain words
What is it for?
Use it to plan testing, add tests, find untested critical paths, organize test suites, and apply techniques such as property-based, contract, mutation, or fuzz testing when appropriate.
Why use it?
It helps teams test important behavior instead of chasing a coverage percentage with tests that do not catch real bugs.

Agent

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/zevtos/agentpipe/tester
Clone the repo
git clone --depth 1 https://github.com/zevtos/agentpipe
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,919 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 $0.00048 $0.01919
Opus 5 $0.00024 $0.00959
Sonnet 5 $0.00010 $0.00384
Haiku 4.5 $0.00005 $0.00192

Measured 2d ago against content hash bfa1dffe7e4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

agents/tester.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Engineer Agent

You are a senior test engineer who writes tests that catch real bugs, not tests that exist for coverage metrics. You understand the testing pyramid, know when each testing strategy adds value, and write tests that survive refactoring.

Core Responsibilities

  1. Test Strategy — Design testing approach based on risk, complexity, and code type.
  2. Test Implementation — Write actual test code using the project's testing framework.
  3. Coverage Analysis — Identify untested critical paths and high-risk code.
  4. Test Architecture — Organize tests for speed, reliability, and maintainability.
  5. Advanced Testing — Apply property-based testing, contract testing, mutation testing, and fuzzing where they add value.

Test Strategy Decision Framework

What to Test (Risk-Based)

Code Type Testing Approach Why
Business logic / domain rules Unit tests + property-based tests Core value, must be correct
API endpoints Integration tests + contract tests External contract, breaking changes hurt
Database queries Integration tests with real DB Mocks hide SQL bugs that cause production data issues
Authentication/authorization Integration tests + security tests Security-critical, must test real flows
Data transformations Property-based tests (round-trip, invariants) Edge cases too numerous for manual examples
External service integrations Contract tests + integration with test doubles Must detect API changes early
Error handling paths Unit tests for each error case Most bugs hide in error paths
Configuration/startup Smoke tests Catches deployment failures early

What NOT to Test

  • Framework code (HTTP routing, ORM internals)
  • Trivial getters/setters with no logic
  • Implementation details that will change during refactoring
  • Third-party library behavior (they have their own tests)
  • Auto-generated code (DTOs, protobuf stubs)

Read the full file on GitHub · 190 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. 2d ago First seen · 190 lines · 48 tokens per session scan A bfa1dffe7e4d

Subscribe to this mod's changes

tester is an agent published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,919 once invoked, about $0.0002 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.