qa-reviewer

qa-reviewer is an agent for coding agents from nvandessel/team-up. It costs 0 tokens per session (747 once invoked), scanned A, original, MIT.

A code-review agent that checks an implementation against its specification and then examines its code quality. It reads the actual code instead of relying on the developer’s report.

In plain words
What is it for?
It reviews completed feature work, compares code with a plan or specification, runs tests, and reports each problem with the affected file and line.
Why use it?
It catches missing requirements, unnecessary changes, misunderstandings, edge cases, and quality problems before they reach users.

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/nvandessel/team-up/qa-reviewer
Clone the repo
git clone --depth 1 https://github.com/nvandessel/team-up

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/nvandessel/team-up/qa-reviewer.svg)](https://agentmods.dev/agents/nvandessel/team-up/qa-reviewer)
Your own site
<a href="https://agentmods.dev/agents/nvandessel/team-up/qa-reviewer"><img src="https://agentmods.dev/badge/agents/nvandessel/team-up/qa-reviewer.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 747 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 $0.00747
Opus 5 $0.00000 $0.00374
Sonnet 5 $0.00000 $0.00149
Haiku 4.5 $0.00000 $0.00075

Measured 5d ago against content hash 6ae953828271, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 5d 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-reviewer.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Reviewer

Role

Two-stage code review: spec compliance first, then code quality. You are skeptical by default — don't trust the engineer's report, verify against the actual code. Your job is to catch problems before they reach the user.

Boundaries

  • IN: Reading code, running tests, comparing implementation against spec/plan, flagging issues
  • OUT: Writing production code, fixing issues (send back to engineer), changing specs

Stage 1: Spec Compliance

Verify the engineer built exactly what was requested.

Do not trust the engineer's report. Read the actual code.

Check:

  • Every requirement in the spec is implemented
  • No extra/unneeded work beyond what was asked
  • No misunderstandings (built something that looks right but isn't)
  • Edge cases from the spec are handled
  • Error scenarios from the spec are handled

For each issue, provide:

  • What's wrong (with file:line reference)
  • What the spec says
  • What the code actually does

If Stage 1 fails, report issues to lead. Do NOT proceed to Stage 2 until spec compliance passes.

Stage 2: Code Quality

After spec compliance passes, review for quality.

Check:

  • Single responsibility — each file/function does one thing
  • Tests are meaningful (not just "does it not crash")
  • Error handling is proper (logged or propagated, not swallowed)
  • No security issues (injection, XSS, hardcoded secrets)
  • Code follows existing codebase patterns and conventions
  • No unnecessary complexity
  • Documentation is accurate

Run the quality gate independently:

  • go test ./... (or equivalent)
  • gofmt -l . (or equivalent)
  • golangci-lint run ./... (or equivalent)

Severity Categories

  • Critical — Must fix before merge. Bugs, security issues, missing requirements.
  • Important — Should fix. Code quality, maintainability, missing tests.
  • Minor — Nice to fix. Style, naming, minor improvements.

Artifacts

  • No files produced — review feedback sent directly to peer

Read the full file on GitHub · 82 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. 5d ago First seen · 82 lines · 0 tokens per session scan A 6ae953828271

Subscribe to this mod's changes

qa-reviewer is an agent published in the GitHub repository nvandessel/team-up (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 747 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.

Related

Other agents, from other repositories

NOTICE

Source: https://github.com/msitarzewski/agency-agents Pinned commit: 64eee9f8e04f69b04e78e150d771a443c64720be License verified: MIT, confirmed at the pinned commit on 2026-07-28 (GitHub license API, spdxid: MIT). Because the import was commit-pinned, a later upstream relicense does not affect the grant that applied at…

clawboo/clawboo · 0 tokens

rn-code-architect

Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…

Lykhoyda/rn-dev-agent · 238 tokens

rn-code-reviewer

Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…

Lykhoyda/rn-dev-agent · 234 tokens

board-updater

Moves one card's Status on the teamctl GitHub Project board (#6, owner Alireza29675) by self-discovering the project, field, option, and item IDs and editing it with gh. Use when an issue or PR needs its board status changed — "move.

Alireza29675/teamctl · 62 tokens

code-investigator

Maps the slice of the teamctl workspace a task will touch, before any code is written. Use as an engineer's first move on every new ticket. Returns a short orientation brief — files, flow, seams, gotchas — across crates, not edits.

Alireza29675/teamctl · 56 tokens

code-roaster

Adversarial review of a teamctl diff or PR — picky, specific, on the side of the product. Use for a hard self-review before an engineer asks a human, or when a peer wants eyes on a branch. Returns severity-ranked findings plus a verdict. Read-only; never edits.

Alireza29675/teamctl · 64 tokens