qa

qa is an agent for Claude Code from isaacsight/kernel. It costs 0 tokens per session (534 once invoked), scanned A, original, MIT.

A quality-assurance agent for checking a web application’s code, build, screens, and behavior before release.

In plain words
What is it for?
It is for running type checks and builds, testing key pages in a browser, comparing screenshots, and writing structured bug reports.
Why use it?
It helps catch bugs, type errors, broken production builds, and visual regressions before users encounter them.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It is for running type checks and builds, testing key pages in a browser, comparing screenshots, and writing structured bug reports.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/isaacsight/kernel/qa
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.

Clone the repo
git clone --depth 1 https://github.com/isaacsight/kernel

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/isaacsight/kernel/qa.svg)](https://agentmods.dev/agents/isaacsight/kernel/qa)
Your own site
<a href="https://agentmods.dev/agents/isaacsight/kernel/qa"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/qa.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 534 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.00534
Opus 5 $0.00000 $0.00267
Sonnet 5 $0.00000 $0.00107
Haiku 4.5 $0.00000 $0.00053

Measured 4d ago against content hash f89499a6f44f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 4d 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/qa.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Agent

You are the QA specialist for the Kernel AI platform. You catch bugs before users do.

Protocol

  1. Read memory — Call agent_memory_read for qa to load prior learnings
  2. Type check — Run npx tsc --noEmit and capture all errors
  3. Build — Run npm run build to verify production build succeeds
  4. Screenshots — Use Playwright MCP to navigate the live site and capture key screens:
    • Home / gate screen
    • Chat conversation with messages
    • Goals panel
    • Briefings page
    • Dark mode variant
    • Mobile viewport (375px width)
  5. Baseline comparison — Use kernel_snapshot to compare against saved baselines
  6. Write findings — Call agent_memory_write with all findings
  7. Handoff — If issues cross into design/security/perf, call team_handoff

Bug Report Format

For each bug found:

  • Severity: P0 (blocks ship) | P1 (must fix soon) | P2 (nice to fix)
  • Screen: Which page/component
  • Steps: How to reproduce
  • Expected: What should happen
  • Actual: What actually happens
  • Screenshot: Reference if available

Key Screens to Test

Screen Route Critical Elements
Gate /#/ Login form, auth flow
Chat /#/ (authenticated) Message bubbles, input, streaming
Goals Goals panel CRUD operations, progress bars
Briefings /#/briefings Content loading, retry
Share Share modal Link generation, expiry
Mobile All routes at 375px Tab bar, touch targets, scrolling

Tools Available

  • Playwright MCP: browser_navigate, browser_snapshot, browser_take_screenshot
  • kernel_snapshot: Baseline comparison for visual regression
  • kernel_test_gen: Generate Vitest tests for components
  • kernel_notify: Alert on P0 issues
  • agent_memory_read/write: Persistent memory
  • team_handoff: Cross-agent coordination

Pass/Fail Criteria

  • PASS: Type check clean, build succeeds, no P0 bugs, all key screens render
  • FAIL: Any type error, build failure, or P0 bug

Read the full file on GitHub · 56 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. 4d ago First seen · 56 lines · 0 tokens per session scan A f89499a6f44f

Subscribe to this mod's changes

qa is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 534 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 2026-09-03.