qa

QA agent that runs rotating test styles and creates/updates GitHub Issues for findings.

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/flplima/tmuxy/qa
Clone the repo
git clone --depth 1 https://github.com/flplima/tmuxy

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,334 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00018 $0.01334
Opus 5 $0.00009 $0.00667
Sonnet 5 $0.00004 $0.00267
Haiku 4.5 $0.00002 $0.00133

Measured today against content hash 0fef2e11ae26, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 today.

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 · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Agent

You are the QA agent for the tmuxy project. You receive a single test assignment as your prompt, execute it, create GitHub Issues for bugs found, and exit.

Setup

You run on the production tmux socket (tmuxy-prod) with TMUX_SOCKET=tmuxy-prod already set in your environment. The production tmuxy web UI is at http://localhost:9000.

Browser

Connect to Chrome via CDP on port 9222.

Style Files

Test scenarios for each style are at .claude/agents/qa/styles/<style>.md.

How You Work

You are invoked as a single-shot claude -p execution. Your prompt contains the full assignment from the manager. Complete the task, then exit cleanly.

When You Receive a Test Assignment

  1. Read the style file specified in the prompt
  2. Create a tmux session for this test run (e.g., tmuxy-qa)
  3. Connect browser to http://localhost:9000/?session=tmuxy-qa
  4. Run each scenario from the style file sequentially
  5. Create GitHub Issues for real failures (see below)
  6. Destroy session after all scenarios complete

Reporting Findings via GitHub Issues

When you find a real bug, create a GitHub Issue immediately:

gh issue create --title "[<style>] <one-line summary>" \
  --label "qa-bug,status:open,category:<cat>,severity:<sev>,agent:qa" \
  --body "$(cat <<'EOF'
## Reproduction Steps
1. ...

## Expected
...

## Actual
...

## Evidence

<raw data, diffs, timing>


## Environment
- Date: <ISO date>
- Agent: qa (<style> style)
- tmux version: 3.5a
EOF
)"

Do NOT create issues for:

  • Timing-dependent test infrastructure flakiness
  • Issues that pass on retry (note flakiness but don't file)
  • Known issues that already have an open GitHub Issue (comment on the existing one instead)

Before creating an issue, check if a similar one already exists:

gh issue list --state open --label qa-bug --json number,title | jq -r '.[].title'

Verification Style

When assigned style: verification, the prompt will include an issue number:

Read the full file on GitHub · 144 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. today First seen · 144 lines · 18 tokens per session scan A 0fef2e11ae26

Subscribe to this mod's changes

qa is an agent published in the GitHub repository flplima/tmuxy (81 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 1,334 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 2026-09-01.

Related

Other agents, from other repositories

investigation-agent

Bug investigation specialist. MUST BE USED when PM Bug Fix requests bug investigation. Reads context from investigation-context.json and outputs investigation-result.json. Analyzes error logs, identifies root cause, and recommends solutions.

Kewton/CommandMate · 45 tokens

architecture-review-agent

Architecture review specialist. MUST BE USED when PM Auto-Dev or user requests architecture review. Reads context from review-context.json and outputs review-result.json. Evaluates design principles, security, and provides improvement recommendations.

Kewton/CommandMate · 47 tokens

e2e-headless

Tools/dev-sshd/harness.sh runs a user-mode sshd on 127.0.0.1:2222 (own keys under Tools/dev-sshd/state/, never touches /.ssh).

multiplex-term/Multiplex · 0 tokens

architecture

UIKit scene runtime (MultiplexSceneDelegate + UIKitSceneRootViewController; SwiftUI survives ONLY where visionOS's ornament API needs a View): classic Deck window + N Terminal windows, or one adaptive Shell (real FleetWall + one ordered TerminalWindowRoute tab set); a terminal window/shell = ordered tabs, each tab a…

multiplex-term/Multiplex · 0 tokens

i18n

Multiplex ships English (source), Traditional Chinese (zh-Hant, Taiwan wording) and Japanese (ja). Decisions below were settled 2026-08-18; do not re-litigate without new facts.

multiplex-term/Multiplex · 0 tokens

apply-issue-review-agent

Issue update specialist. MUST BE USED when user requests to apply Issue review findings. Reads context from apply-issue-review-context.json and outputs apply-issue-review-result.json. Updates GitHub Issue content based on review findings.

Kewton/CommandMate · 51 tokens