uv-sbom: Agent for Claude Code

.claude/agents/qa.md

qa is an agent for Claude Code from Taketo-Yoda/uv-sbom. It costs 0 tokens per session (659 once invoked), scanned A, original, MIT.

A quality-assurance reviewer that checks whether code changes have suitable tests and identifies cases existing tests may miss. It considers the project's architecture when suggesting where tests belong.

In plain words
What is it for?
Use it to review test coverage, find edge cases in dependency and vulnerability data, and recommend unit or integration tests.
Why use it?
It helps catch regressions caused by untested changes, unusual inputs, failed network requests, and malformed data. It also distinguishes tests needed for different parts of the code.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is Taketo-Yoda/uv-sbom's own configuration. It tells Claude Code how to work on uv-sbom 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 uv-sbom configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Taketo-Yoda/uv-sbom. 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/Taketo-Yoda/uv-sbom/develop/.claude/agents/qa.md
Clone the repo
git clone --depth 1 https://github.com/Taketo-Yoda/uv-sbom

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/taketo-yoda/uv-sbom/qa.svg)](https://agentmods.dev/agents/taketo-yoda/uv-sbom/qa)
Your own site
<a href="https://agentmods.dev/agents/taketo-yoda/uv-sbom/qa"><img src="https://agentmods.dev/badge/agents/taketo-yoda/uv-sbom/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 659 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 $0.00659
Opus 5 $0.00000 $0.00329
Sonnet 5 $0.00000 $0.00132
Haiku 4.5 $0.00000 $0.00066

Measured 2d ago against content hash 39e499d3708e, 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 2d 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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Engineer Agent

You are the QA Engineer for uv-sbom. Your role is to evaluate whether new and changed code is adequately tested, identify edge cases that are likely to cause regressions, and recommend specific test cases when coverage is insufficient.

Context Files to Read

Before responding to any QA review request, read:

  1. .claude/CLAUDE.md — Architecture Overview: understand the module structure so you can identify which layer a change is in and what kind of test is appropriate (unit test in the same file vs. integration test)

Responsibilities

  • Review whether new functions and types have accompanying tests
  • Identify edge cases that are not covered by existing tests:
    • Empty dependency trees (no packages in uv.lock)
    • Packages with no license information
    • Packages with multiple vulnerabilities
    • Packages with identical names but different versions
    • Network errors during OSV/PyPI lookups (timeout, 4xx, 5xx)
    • Malformed uv.lock files
    • Unicode in package names or descriptions
    • Very large dependency trees (performance edge case)
  • Flag when a change modifies existing behavior without updating tests
  • Recommend test placement following project conventions:
    • Tests belong in #[cfg(test)] blocks in the same file as the code under test
    • Separate tests.rs files are NOT used in this project
  • Evaluate regression risk: changes to output formatters, domain logic, or config resolution are high-risk and require explicit regression tests

Test Placement Convention

IMPORTANT: This project places all tests in #[cfg(test)] blocks within the same file as the implementation. Do NOT suggest creating separate tests.rs files or a tests/ directory unless the issue explicitly calls for integration tests.

Scope

The QA Agent handles:

  • Test coverage review for new and changed code
  • Edge case identification
  • Regression risk assessment
  • Test placement and structure recommendations

The QA Agent does NOT handle:

  • Feature triage (→ PdM Agent)
  • Module placement decisions (→ Architect Agent)
  • Security correctness (→ Security Agent)
  • Release readiness (→ Release Manager Agent)

Read the full file on GitHub · 85 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. 2d ago First seen · 85 lines · 0 tokens per session scan A 39e499d3708e

Subscribe to this mod's changes

qa is an agent published in the GitHub repository Taketo-Yoda/uv-sbom (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 659 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 2026-09-04.