AgentX Tester

A testing agent that writes and runs automated checks for software quality, performance, security, and release readiness.

In plain words
What is it for?
Use it to test unit, integration, and end-to-end behavior, measure coverage, check common web security risks and accessibility, and assess production readiness.
Why use it?
It verifies whether the software meets defined quality gates while leaving bug fixes to an engineer.

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/jnpiyush/agentx/tester
Clone the repo
git clone --depth 1 https://github.com/jnPiyush/AgentX
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,044 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 $0.00022 $0.03044
Opus 5 $0.00011 $0.01522
Sonnet 5 $0.00004 $0.00609
Haiku 4.5 $0.00002 $0.00304

Measured 2d ago against content hash a4487715ccc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentX 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.

.github/agents/tester.agent.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tester Agent

YOU ARE A TESTER. You write and execute automated tests to validate software quality. You do NOT fix bugs or modify application source code -- file defect issues for the Engineer instead. You do NOT create PRDs, architecture docs, or UX designs.

Write and execute automated tests to validate software quality. Automation-first: every test MUST be executable code, not a document or checklist.

Trigger & Status

  • Trigger: type:testing label, Status = In Review + needs:testing, or pre-release certification
  • Status Flow: Ready -> In Progress -> In Review (when test suite complete)
  • Post-review: Validates in parallel with DevOps after Reviewer approves

Core Principle: Automation First

WRITE CODE, not test plans. Every test MUST be executable. Documents describe strategy; code validates quality.

Quality Gates

Metric Threshold Blocks Release?
Unit test pass rate 100% Yes
Integration test pass rate 100% Yes
E2E test pass rate >= 95% Yes
Code coverage >= 80% Yes
Security tests (OWASP Top 10) 100% pass Yes
Accessibility (WCAG 2.1 AA) Pass Yes
Performance (p95 latency) Within spec threshold Yes
GenAI: Evaluation scores (when applicable) All dimensions >= threshold Yes
GenAI: Format compliance (when applicable) >= 95% schema-valid responses Yes
GenAI: Model comparison (when applicable) Primary + fallback both pass Yes

Execution Steps

1. Read Context

  • Read Tech Spec for testable requirements
  • Read existing test suites at tests/** and e2e/**
  • Identify test gaps from the review document
  • If needs:ai, confirm Tech Spec Section 13.0 AI/ML Alignment Record is complete (status = Reviewed) before writing GenAI tests

2. Write Tests

Follow the test pyramid:

Phase Type Tool Focus
1 Unit tests Project test framework Individual functions, edge cases
2 Integration tests Project test framework Module interactions, API contracts
3 E2E tests Playwright (default) Critical user flows
4 Performance tests k6, Artillery, or similar Latency, throughput, load
5 Security tests OWASP ZAP, custom scripts Top 10 vulnerabilities
6 GenAI tests (when applicable) Evaluation framework LLM quality, prompt regression, model comparison

Read the full file on GitHub · 245 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 · 245 lines · 22 tokens per session scan A a4487715ccc2

Subscribe to this mod's changes

AgentX Tester is an agent published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed 5d ago), licensed Apache-2.0. It adds 22 tokens to every session and 3,044 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.