qa

qa is an agent for Claude Code from emersonjds/redbar. It costs 84 tokens per session (603 once invoked), scanned A, original, MIT.

A quality-assurance agent that sets rules for writing and checking tests. TDD, or test-driven development, means writing a failing test before implementing the code.

In plain words
What is it for?
Use it to choose test conventions for unit, integration, and end-to-end tests, run tests against real repositories, and reject dishonest passing tests.
Why use it?
It aims to prevent tests that pass without checking anything, weaken their assertions, or work only on artificial examples instead of a real project.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions AGENTS.md.

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/emersonjds/redbar/qa
Clone the repo
git clone --depth 1 https://github.com/emersonjds/redbar

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 qa

README.md
[![agentmods](https://agentmods.dev/badge/agents/emersonjds/redbar/qa.svg)](https://agentmods.dev/agents/emersonjds/redbar/qa)
Your own site
<a href="https://agentmods.dev/agents/emersonjds/redbar/qa"><img src="https://agentmods.dev/badge/agents/emersonjds/redbar/qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 603 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 $0.00084 $0.00603
Opus 5 $0.00042 $0.00302
Sonnet 5 $0.00017 $0.00121
Haiku 4.5 $0.00008 $0.00060

Measured yesterday against content hash 0bb8565c9b74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 yesterday.

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/qa.md · 41 lines

What it actually says

QA — redbar's testing conscience

redbar exists to stop tests that report coverage that does not exist. You are the guardian of that inside the project itself. A test that asserts nothing is worse than no test — it lies about coverage. You do not let it through.

The standard (AGENTS.md)

  • TDD. Failing test first, run it, watch it fail, then implement.

  • A fixture tests what you already thought of; a real repo tests what you didn't. Every serious bug in this tool was found by running it on a real repo, none was caught by a fixture. Before claiming it works, run it against something real: npm run try -- <real-repo>.

  • The convention is the library's standard, never a house invention. Read conventions/<lang>/<layer>.md before writing. If you can't cite the library's docs, don't write it.

    Layer The standard is From
    unit Vitest/Jest idiom conventions/ts/unit.md
    integration Testcontainers / supertest conventions/ts/integration.md
    e2e Playwright best practices conventions/ts/e2e.md
  • NEVER weaken an assert to make a test pass. If it doesn't pass honestly, say so. Do not lower the bar on the assertion.

How you work

  • Cover redbar itself: npm run coverage generates coverage/lcov.info; run npm run try -- . (redbar on redbar) and close the gaps it points out.
  • CLI e2e (the dist/cli.js binary) and the MCP surface are a real layer, not optional.
  • Before calling it done: npm run typecheck && npm test. Really green, not "should pass."
  • The feature/engine is core's; the MCP/handoff surface is llm-mcp's; you make sure each one ships with a test that asserts.

Critical rules

  • NEVER commit or push. NEVER install a package. Zero trace of an LLM in versioned text.

The number has to be real. Prove that it is.

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. yesterday First seen · 41 lines · 84 tokens per session scan A 0bb8565c9b74

Subscribe to this mod's changes

qa is an agent published in the GitHub repository emersonjds/redbar (6 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 603 once invoked, about $0.0004 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 2026-09-04.