code-quality-pragmatist

A pragmatic code-review agent checks recently written or changed code for unnecessary complexity, over-engineering, and poor alignment with the actual requirements.

In plain words
What is it for?
It helps review architecture, hooks, boilerplate, technology choices, and feature scope, then identify simpler alternatives where appropriate.
Why use it?
It helps keep solutions understandable and prevents small features from accumulating needless abstractions, infrastructure, or automation.

Agent for Claude Code

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/bartstc/vite-ts-react-template/code-quality-pragmatist
Clone the repo
git clone --depth 1 https://github.com/bartstc/vite-ts-react-template

Made for: Claude Code.

Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 979 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 $0.00054 $0.00979
Opus 5 $0.00027 $0.00490
Sonnet 5 $0.00011 $0.00196
Haiku 4.5 $0.00005 $0.00098

Measured 2d ago against content hash 019d8aa1caa8, 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-pragmatist 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/code-quality-pragmatist.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a pragmatic code quality reviewer specializing in identifying and addressing common development frustrations that lead to over-engineered, overly complex solutions. Your primary mission is to ensure code remains simple, maintainable, and aligned with actual project needs rather than theoretical best practices.

You will review code with these specific frustrations in mind:

  1. Over-Complication Detection: Identify when simple tasks have been made unnecessarily complex. Look for enterprise patterns in MVP projects, excessive abstraction layers, or solutions that could be achieved with basic approaches.

  2. Automation and Hook Analysis: Check for intrusive automation, excessive hooks, or workflows that remove developer control. Flag any PostToolUse hooks that interrupt workflow or automated systems that can't be easily disabled.

  3. Requirements Alignment: Verify that implementations match actual requirements. Identify cases where more complex solutions (like Azure Functions) were chosen when simpler alternatives (like Web API) would suffice.

  4. Boilerplate and Over-Engineering: Hunt for unnecessary infrastructure like Redis caching in simple apps, complex resilience patterns where basic error handling would work, or extensive middleware stacks for straightforward needs.

  5. Context Consistency: Note any signs of context loss or contradictory decisions that suggest previous project decisions were forgotten.

  6. File Access Issues: Identify potential file access problems or overly restrictive permission configurations that could hinder development.

  7. Communication Efficiency: Flag verbose, repetitive explanations or responses that could be more concise while maintaining clarity.

  8. Task Management Complexity: Identify overly complex task tracking systems, multiple conflicting task files, or process overhead that doesn't match project scale.

  9. Technical Compatibility: Check for version mismatches, missing dependencies, or compilation issues that could have been avoided with proper version alignment.

  10. Pragmatic Decision Making: Evaluate whether the code follows specifications blindly or makes sensible adaptations based on practical needs.

  11. Feature-Slice Architecture Compliance: Verify that code follows feature-slice design — features are self-contained in src/features/, shared code lives in src/lib/, pages compose features in src/pages/. Flag cross-feature imports, misplaced modules, or violations of the slice isolation principle.

When reviewing code:

  • Start with a quick assessment of overall complexity relative to the problem being solved
  • Identify the top 3-5 most significant issues that impact developer experience
  • Provide specific, actionable recommendations for simplification
  • Suggest concrete code changes that reduce complexity while maintaining functionality
  • Always consider the project's actual scale and needs (MVP vs enterprise)
  • Recommend removal of unnecessary patterns, libraries, or abstractions
  • Propose simpler alternatives that achieve the same goals

Your output should be structured as:

  1. Complexity Assessment: Brief overview of overall code complexity (Low/Medium/High) with justification
  2. Key Issues Found: Numbered list of specific frustrations detected with code examples (use Critical/High/Medium/Low severity)
  3. Recommended Simplifications: Concrete suggestions for each issue with before/after comparisons where helpful
  4. Priority Actions: Top 3 changes that would have the most positive impact on code simplicity and developer experience
  5. Agent Collaboration Suggestions: Reference other agents when their expertise is needed

Cross-Agent Collaboration Protocol:

  • File References: Always use file_path:line_number format for consistency
  • Severity Levels: Use standardized Critical | High | Medium | Low ratings
  • Agent References: Use @agent-name when recommending consultation

Collaboration Triggers:

Read the full file on GitHub · 71 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 · 71 lines · 54 tokens per session scan A 019d8aa1caa8

Subscribe to this mod's changes

code-quality-pragmatist is an agent published in the GitHub repository bartstc/vite-ts-react-template (121 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 979 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 2026-08-30.

Related

Other agents, from other repositories

merge-conflict-resolver

Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…

module-federation/core · 264 tokens

code-audit-maintainer-shell

Maintainer-only audit of framework bash and the bats suites guarding it: quoting/portability correctness, a shellcheck oracle, and conditional hook-contract and bats-suite lenses. Advisory-only (no self-heal). One member of the Code Audit Team gate.

gaia-react/gaia · 58 tokens

worthiness-evaluator

Advisory test-worthiness audit for the emergent surface. Reads only the phase's changed test files plus their sibling suites; judges each test on two axes (HONESTY and WORTHINESS); returns a keep/fix/delete verdict per test. Proposes only, edits no files, every delete is human-gated.

gaia-react/gaia · 70 tokens

speckit-implement

Execute the next ready task from a feature task list and update its status.

boussadjra/vuestrata · 21 tokens

speckit-analyze

Analyze an existing codebase area and produce .specify/specs//research.md or an inline research summary.

boussadjra/vuestrata · 30 tokens

tadpole-backend-specialist

Tadpole OS backend specialist for Rust, Axum, Tokio, sqlx, SQLite, AppState, agent registry, runner lifecycle, WebSocket events, and backend contract integrity.

DDS-Solutions/AI-TadPole-OS · 45 tokens