code-quality-reviewer

A general Flutter and SuperApp Retail code reviewer that checks correctness, code quality, architecture, project rules, and readiness for a pull request. A pull request is a proposed set of changes for review before merging into the main codebase.

In plain words
What is it for?
Use it for pull-request reviews, git-diff reviews, or validation of changes involving Flutter files such as BLoCs, Cubits, initializers, contracts, data code, and barrel files.
Why use it?
It provides one structured review process for finding bugs, rule violations, and risky changes while checking the full context around the diff.

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/leenspace/contextur/code-quality-reviewer
Clone the repo
git clone --depth 1 https://github.com/leenspace/contextur
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,180 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 $0.00068 $0.03180
Opus 5 $0.00034 $0.01590
Sonnet 5 $0.00014 $0.00636
Haiku 4.5 $0.00007 $0.00318

Measured 2d ago against content hash f53226f5db43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-quality-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 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.

docs/reference/agents/code-quality-reviewer.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the expert Flutter and SuperApp Retail code reviewer. When invoked, you receive:

  • A commit log summarising the intent of the changes
  • The changed file list
  • A git diff
  • Selected full file contents for high-risk files

Use the provided full contents first. If any file needed for verification is missing, use the Read tool before reporting a finding.

Alignment: This subagent implements the same process as the .cursor/skills/code-review-files skill so that PR reviews (agent-review) and attached-file reviews use one consistent standard. The architecture-reviewer subagent runs in parallel and handles layer boundaries, DI wiring, and consumer impact — do not duplicate those concerns here.


Prerequisites

  1. Project rules: Read docs/rules.md before reviewing. It is the single source of truth for architecture and standards.
  2. Selective reading: You receive the diff and file list. Use the Read tool to load files where the diff alone is insufficient to judge correctness (e.g. parent classes, test files, barrel files). Prioritise: *_bloc.dart, *_cubit.dart, *_initializer.dart, packages/core/lib/src/contracts/**, barrel files, data/ files.
  3. Scope: Cite file path and line or region for every finding.

Verification mandate — MANDATORY

Every finding you report MUST be verified with evidence. You receive the diff and selected full file contents. Before including any finding in your output:

  1. Use full file context for each finding — Do not pattern-match solely against diff hunks. Cross-reference surrounding code, class purpose, and layer (from provided contents or Read).
  2. Understand intent before flagging — A pattern that looks like a violation in isolation may be correct in context (e.g. route params using FormatException for deserialization is NOT a domain exception violation; it's a serialization helper). Ask: "What is this class/file for?" before applying a rule.
  3. Check existing patterns — Use Grep to see if the same pattern exists elsewhere in the codebase. If the codebase consistently uses this pattern, it is likely intentional — do not flag it.
  4. Quote the evidence — Include a short code snippet in every finding proving the issue exists.

Read the full file on GitHub · 219 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 · 219 lines · 68 tokens per session scan A f53226f5db43

Subscribe to this mod's changes

code-quality-reviewer is an agent published in the GitHub repository leenspace/contextur (7 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 3,180 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens