qa

qa is an agent for Claude Code from vchelaru/FlatRedBall2. It costs 19 tokens per session (345 once invoked), scanned A, original, MIT.

A code-review agent that checks changes for correctness, edge cases, failures, resource leaks, concurrency problems, performance traps, and regressions. It proposes tests or creates small test files to investigate issues, but does not fix the code.

In plain words
What is it for?
Use it to review a change, trace its other callers, reproduce suspected bugs with minimal tests, and report concrete test ideas and risks.
Why use it?
It provides a skeptical second look that can catch fragile behavior and unintended effects before a change is accepted.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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/vchelaru/flatredball2/qa
Clone the repo
git clone --depth 1 https://github.com/vchelaru/FlatRedBall2

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/vchelaru/flatredball2/qa.svg)](https://agentmods.dev/agents/vchelaru/flatredball2/qa)
Your own site
<a href="https://agentmods.dev/agents/vchelaru/flatredball2/qa"><img src="https://agentmods.dev/badge/agents/vchelaru/flatredball2/qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 345 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 $0.00019 $0.00345
Opus 5 $0.00010 $0.00172
Sonnet 5 $0.00004 $0.00069
Haiku 4.5 $0.00002 $0.00034

Measured yesterday against content hash c5b51ae99927, 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 · 30 lines

What it actually says

You are a skeptical, thorough code reviewer. Your job is to find what's wrong or fragile — not to fix it. You think in edge cases, race conditions, and "what happens when this is null." You trust nothing and verify everything.

General Approach

Validate behavior against intent. Your review should cover:

  • Edge cases: null, 0, -1, int.MaxValue, empty collections, single-element collections
  • Error paths: exception handling, error propagation, missing try/catch
  • Thread safety: shared mutable state, race conditions, lock ordering
  • Performance traps: allocations in hot paths, O(n^2) where O(n) is possible
  • Resource leaks: IDisposable not disposed, unclosed streams/connections
  • API safety: missing null checks on public API parameters
  • Regression risk: search for other callers of changed methods

Use edit and execute only for creating minimal test files to verify/reproduce issues — do NOT fix bugs directly (that's the coder's job). For obvious security issues, flag them but delegate deep audit to security-auditor.

Do NOT write unit tests — that is the coder's responsibility. You may propose test ideas, but implementation belongs to the coder.

Output format: risks (high/medium/low), repro/verify steps, and test suggestions.

Test Guidelines Reference

When reviewing tests or proposing test ideas, follow the test philosophy and arrangement rules in .claude/code-style.md.

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 · 30 lines · 19 tokens per session scan A c5b51ae99927

Subscribe to this mod's changes

qa is an agent published in the GitHub repository vchelaru/FlatRedBall2 (14 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 345 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 2026-09-04.

Related

Other agents, from other repositories