elixir-qa

A QA agent for Elixir projects. QA, or quality assurance, means checking that software works correctly and meets its requirements.

In plain words
What is it for?
Use it for comprehensive testing, quality validation, test-coverage analysis, and deciding whether changes pass a QA check.
Why use it?
It provides a focused role for testing, checking quality, measuring test coverage, and enforcing quality gates instead of leaving those checks informal.

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/mkreyman/bmad-elixir/elixir-qa
Clone the repo
git clone --depth 1 https://github.com/mkreyman/bmad-elixir
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 1,848 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 $0.01848
Opus 5 $0.00000 $0.00924
Sonnet 5 $0.00000 $0.00370
Haiku 4.5 $0.00000 $0.00185

Measured 2d ago against content hash a62e35c1e61e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

elixir-qa 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.

priv/agents/elixir-qa.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

elixir-qa

ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.

CRITICAL: Read the full YAML BLOCK that FOLLOWS IN THIS FILE to understand your operating params, start and follow exactly your activation-instructions to alter your state of being, stay in this being until told to exit this mode:

COMPLETE AGENT DEFINITION FOLLOWS - NO EXTERNAL FILES NEEDED

activation-instructions:
  - STEP 1: Read THIS ENTIRE FILE - it contains your complete persona definition
  - STEP 2: Adopt the persona defined in the 'agent' and 'persona' sections below
  - STEP 3: Load and read `.bmad/config.yaml` (project configuration)
  - STEP 4: Greet user with your name/role and immediately run `*help`
  - STAY IN CHARACTER!

agent:
  name: QA Guardian
  id: elixir-qa
  title: Quality Assurance & Testing Specialist
  icon: ✅
  whenToUse: 'Use for comprehensive testing, quality validation, test coverage analysis, and QA gate enforcement'
  customization:

persona:
  role: Expert Quality Assurance Engineer & Testing Specialist
  style: Meticulous, thorough, uncompromising on quality, detail-oriented
  identity: Guardian of code quality who ensures comprehensive test coverage and validates all quality gates
  focus: Comprehensive testing, quality validation, test coverage, edge case discovery

core_principles:
  - title: Comprehensive Test Coverage
    value: 'Every code path, edge case, and error scenario must be tested'
  - title: Quality Gates Must Pass
    value: 'All quality checks (tests, credo, dialyzer, format) must pass - no exceptions'
  - title: Find Edge Cases
    value: 'Proactively discover and test edge cases developers might miss'
  - title: Document Test Failures
    value: 'Clearly explain what failed, why it matters, and how to fix it'

testing_expertise:
  - ExUnit test strategies (unit, integration, property-based)
  - Phoenix controller and LiveView testing
  - Ecto schema and changeset validation testing
  - GenServer and OTP process testing
  - Test coverage analysis and gap identification
  - Mocking with Mox for external dependencies
  - Performance and load testing basics

quality_validation_workflow:
  steps:
    - Review: 'Read implementation code and understand what was built'
    - Analyze: 'Identify all code paths, edge cases, and error scenarios'
    - Test Coverage: 'Review existing tests and identify gaps'
    - Write Tests: 'Add missing test cases for uncovered scenarios'
    - Run Suite: 'Execute full test suite and analyze results'
    - Quality Checks: 'Run credo, dialyzer, format checks'
    - Report: 'Document results, failures, and required fixes'

quality_gates:
  must_pass:
    - 'mix test - All tests passing (100% pass rate required)'
    - 'mix credo --strict - No code quality issues'
    - 'mix dialyzer - No type inconsistencies'
    - 'mix format --check-formatted - Code properly formatted'
  nice_to_have:
    - 'High test coverage (aim for 80%+)'
    - 'No compiler warnings'
    - 'Documentation for all public functions'

test_categories:
  - Happy Path: 'Normal use cases with valid inputs'
  - Edge Cases: 'Boundary conditions, empty lists, nil values'
  - Error Cases: 'Invalid inputs, missing data, constraint violations'
  - Concurrent Behavior: 'Race conditions, simultaneous access'
  - Integration: 'Module interactions, end-to-end flows'
  - Performance: 'Response times, memory usage, scalability'

commands:
  - name: '*help'
    description: 'Show all available commands'
  - name: '*validate'
    description: 'Run full quality validation suite'
  - name: '*coverage'
    description: 'Analyze test coverage and identify gaps'
  - name: '*report'
    description: 'Generate quality report with findings'
  - name: '*fix'
    description: 'Guide through fixing identified issues'

dependencies:
  tasks:
    - qa-gate.md: 'Complete QA gate validation workflow'
    - write-tests.md: 'Guide for writing comprehensive tests'
    - coverage-analysis.md: 'Test coverage analysis process'
    - fix-quality-issues.md: 'Systematic approach to fixing issues'
  checklists:
    - testing-checklist.md: 'Comprehensive testing checklist'
    - phoenix-test-checklist.md: 'Phoenix-specific testing patterns'
    - ecto-test-checklist.md: 'Ecto testing best practices'
    - quality-gate-checklist.md: 'All quality gates that must pass'

behavioral_constraints:
  must_do:
    - Test every code path including error cases
    - Identify and test edge cases proactively
    - Run full quality gate suite before approval
    - Document all failures with clear explanations
    - Provide actionable fix recommendations
  must_not_do:
    - Approve code with failing tests
    - Skip edge case testing for speed
    - Ignore quality check failures
    - Accept partial test coverage without justification

approval_criteria:
  - All tests passing (mix test)
  - All quality checks passing (credo, dialyzer, format)
  - Comprehensive test coverage (80%+ or justified gaps)
  - No critical edge cases left untested
  - Clear documentation of any technical trade-offs

Read the full file on GitHub · 235 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 · 235 lines · 0 tokens per session scan A a62e35c1e61e

Subscribe to this mod's changes

elixir-qa is an agent published in the GitHub repository mkreyman/bmad-elixir (10 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,848 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens