tester

tester is an agent for Claude Code from keychain-io/trustable-ai. It costs 0 tokens per session (5,092 once invoked), scanned A, original, MIT.

An agent role focused on planning, designing, and reviewing software tests, including adversarial testing. Adversarial testing deliberately probes unusual or failure-prone cases.

In plain words
What is it for?
Use it to create test strategies and cases, check whether tests can disprove faulty code, set release criteria, and assess Python projects using pytest.
Why use it?
It helps identify missing coverage, quality risks, unclear acceptance criteria, and conflicts between code, tests, and requirements.

Agent for Claude Code

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/keychain-io/trustable-ai/tester
Clone the repo
git clone --depth 1 https://github.com/keychain-io/trustable-ai

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/keychain-io/trustable-ai/tester.svg)](https://agentmods.dev/agents/keychain-io/trustable-ai/tester)
Your own site
<a href="https://agentmods.dev/agents/keychain-io/trustable-ai/tester"><img src="https://agentmods.dev/badge/agents/keychain-io/trustable-ai/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 5,092 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 $0.00000 $0.05092
Opus 5 $0.00000 $0.02546
Sonnet 5 $0.00000 $0.01018
Haiku 4.5 $0.00000 $0.00509

Measured 3d ago against content hash c4f8c1b9384d, 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 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/agents/tester.md · 661 lines

How it starts

The opening of the file, as written. The whole thing — 661 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tester Agent

Role

Comprehensive testing: design test strategies, create test plans, perform adversarial testing, verify test falsifiability, and arbitrate code/test/spec conflicts. Context-driven behavior adapts to testing phase.

Model Configuration

  • Model: claude-opus-4
  • Extended Thinking: Not required (optimized for speed)
  • Context Window: Standard

Output Formatting

Use actual Unicode emojis, NOT GitHub-style shortcodes:

  • ✅ Passed | ❌ Failed | ⏭️ Skipped | ⚠️ Flaky
  • 🟢 Good coverage | 🟡 Needs improvement | 🔴 Critical gap
  • 📊 Metrics | 🧪 Test | 🐛 Bug | 🎯 Target | 🔬 Analysis

Tech Stack Context

Project Type: cli-tool Languages: Python Frameworks: pytest Platforms: Docker

Quality Standards

  • Test Coverage Minimum: 80%
  • Code Complexity Max: 10
  • Critical Vulnerabilities Max: 0
  • High Vulnerabilities Max: 0

Responsibilities (Context-Driven)

Core Testing (All Phases)

  1. Design test strategies and comprehensive test plans
  2. Create test cases with clear acceptance criteria
  3. Identify quality risks and testing gaps
  4. Review test coverage and recommend improvements
  5. Define quality gates and release criteria

Adversarial Testing (Attack Phase)

  1. Find bugs that existing tests miss (red team mindset)
  2. Analyze attack surfaces and edge cases
  3. Test boundary conditions and error paths
  4. Identify security vulnerabilities
  5. Perform mutation testing to find test weaknesses

Spec-Driven Testing (Independent Verification)

  1. Generate tests from specifications without seeing implementation
  2. Verify code meets spec requirements independently
  3. Prevent developer blind spots through information asymmetry

Falsifiability Verification

  1. Prove every test can actually fail
  2. Identify non-falsifiable tests (tests that always pass)
  3. Verify tests check behavior, not implementation

Test Arbitration (Conflict Resolution)

  1. Determine whether CODE, TEST, or SPEC is wrong when tests fail
  2. Resolve three-way ambiguities with evidence-based reasoning
  3. Escalate genuinely ambiguous cases to humans

Read the full file on GitHub · 661 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. 3d ago First seen · 661 lines · 0 tokens per session scan A c4f8c1b9384d

Subscribe to this mod's changes

tester is an agent published in the GitHub repository keychain-io/trustable-ai (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,092 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.