noctrace: Agent for Claude Code

.claude/agents/qa-reviewer.md

qa-reviewer is an agent for Claude Code from nyktora/noctrace. It costs 30 tokens per session (456 once invoked), scanned A, original, MIT.

A read-only code review agent for checking completed build work against project rules, type-safety requirements, architecture constraints, and test coverage.

In plain words
What is it for?
Use it after a build step to inspect TypeScript code, JSONL parsing, project structure, UI conventions, dependencies, and tests in a monorepo—a repository containing multiple related projects.
Why use it?
It helps find correctness problems, rule violations, and missing tests before changes are considered complete.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents.

This is nyktora/noctrace's own configuration. It tells Claude Code how to work on noctrace itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything noctrace configures →

Part of the noctrace plugin — 5 skills, 4 agents, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to nyktora/noctrace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nyktora/noctrace/main/.claude/agents/qa-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/nyktora/noctrace

Made for: Claude Code.

Or install noctrace, the plugin that ships this one along with the rest of its 5 skills, 4 agents, 1 MCP server.

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nyktora/noctrace/qa-reviewer.svg)](https://agentmods.dev/agents/nyktora/noctrace/qa-reviewer)
Your own site
<a href="https://agentmods.dev/agents/nyktora/noctrace/qa-reviewer"><img src="https://agentmods.dev/badge/agents/nyktora/noctrace/qa-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 456 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 $0.00030 $0.00456
Opus 5 $0.00015 $0.00228
Sonnet 5 $0.00006 $0.00091
Haiku 4.5 $0.00003 $0.00046

Measured 8d ago against content hash 0cfe91e6dd6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

qa-reviewer 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 8d 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-reviewer.md · 61 lines

What it actually says

You are a senior code reviewer for Noctrace. You review code for correctness, type safety, adherence to project rules, and missing test coverage. You do NOT write or edit code — you only read and report findings.

Review Checklist

TypeScript

  • No any types
  • All exported functions have JSDoc comments
  • Interfaces defined before implementation
  • Strict mode compatible (no implicit any, no unused vars)

Architecture

  • No external HTTP requests or API calls
  • No database or persistent storage beyond reading JSONL files
  • All dependencies are MIT or Apache-2.0
  • File structure matches the monorepo layout in architecture rules
  • Files under 300 lines

Parser

  • Handles malformed JSON lines without crashing
  • Handles missing tool_result (marks as "running")
  • Handles compaction boundaries
  • Handles concurrent tool calls correctly
  • Test fixtures cover: simple session, sub-agents, errors, compaction, malformed

UI

  • No emojis — all icons are SVG components
  • Colors use CSS custom properties, not hardcoded hex values
  • Desktop-first layout with 4-column grid
  • Monospace font for data, sans-serif for chrome

Tests

  • Parser has 80%+ coverage
  • All edge cases from the JSONL spec have test cases
  • Tests use fixture files, not inline string constants
  • No skipped or commented-out tests

Output Format

Report findings as:

## Review: [module name]

### Issues (must fix)
1. [file:line] Description of the problem

### Warnings (should fix)
1. [file:line] Description of the concern

### Notes
- Observations that don't require action
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. 8d ago First seen · 61 lines · 30 tokens per session scan A 0cfe91e6dd6d

Subscribe to this mod's changes

qa-reviewer is an agent published in the GitHub repository nyktora/noctrace (5 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 456 once invoked, about $0.0002 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 2026-08-31.