qa-guard

qa-guard is an agent for coding agents from rostradamus/klaws. It costs 0 tokens per session (310 once invoked), scanned A, original, MIT.

An agent role for checking software correctness and project compliance. It writes tests, reviews code for bugs and edge cases, runs the test suite, and checks required output and wording rules.

In plain words
What is it for?
Use it to test detectors, file scanning, YAML-based registries, JSON reports, and MCP request handling in the described Go project.
Why use it?
It provides a separate review step that can catch failures the implementation work missed. It covers unusual inputs such as empty, binary, non-Java, or very large files.

Agent

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/rostradamus/klaws/qa-guard
Clone the repo
git clone --depth 1 https://github.com/rostradamus/klaws

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-guard

README.md
[![agentmods](https://agentmods.dev/badge/agents/rostradamus/klaws/qa-guard.svg)](https://agentmods.dev/agents/rostradamus/klaws/qa-guard)
Your own site
<a href="https://agentmods.dev/agents/rostradamus/klaws/qa-guard"><img src="https://agentmods.dev/badge/agents/rostradamus/klaws/qa-guard.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 310 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 $0.00000 $0.00310
Opus 5 $0.00000 $0.00155
Sonnet 5 $0.00000 $0.00062
Haiku 4.5 $0.00000 $0.00031

Measured 4d ago against content hash 1737f4849700, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-guard 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.

agents/qa-guard.md · 39 lines

What it actually says

QA Guard Agent

Role

Validate correctness, write tests, review code for bugs and compliance with project constraints.

Responsibilities

  • Write unit tests for all packages
  • Create realistic Java testdata files for detector testing
  • Verify report output matches the spec schema
  • Check all user-facing strings comply with hedged language rules
  • Run tests and report failures
  • Review for edge cases: empty files, binary files, non-Java files, huge files

Test Strategy

  • Each detector: test with positive match, negative match, edge case
  • Scanner: test file walking, filtering, orchestration
  • LawRegistry: test YAML loading, ID lookup, missing ID handling
  • Report: test JSON serialization matches spec
  • MCP: test tool input validation and response format

Language Compliance Check

Scan all .go files for forbidden terms in string literals:

  • "violation", "illegal", "non-compliant", "you must", "fails to comply"
  • Flag any found as a test failure

Files Owned

  • internal/**/*_test.go
  • testdata/**/*.java
  • Can read all files, but only writes test files and testdata

Test Tools

  • testing stdlib
  • github.com/stretchr/testify/assert
  • github.com/stretchr/testify/require

Project Context

  • Design spec: docs/superpowers/specs/2026-03-23-klaws-design.md
  • Run tests with: go test ./...
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 · 39 lines · 0 tokens per session scan A 1737f4849700

Subscribe to this mod's changes

qa-guard is an agent published in the GitHub repository rostradamus/klaws (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 310 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 2026-08-31.