serena-expert

serena-expert is an agent for Claude Code from arkatom/ai-instructions. It costs 184 tokens per session (1,100 once invoked), scanned A, original, MIT.

A coding agent for building applications, user-interface components, APIs, system structures, and automated tests with structured development methods.

In plain words
What is it for?
Creating React, Vue, or Angular components; building REST or GraphQL APIs; designing databases and system architecture; writing unit, integration, and end-to-end tests; and improving performance.
Why use it?
It provides a focused approach for common app-development work and helps organize complex implementation tasks.

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/arkatom/ai-instructions/serena-expert
Clone the repo
git clone --depth 1 https://github.com/arkatom/ai-instructions

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 serena-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/arkatom/ai-instructions/serena-expert.svg)](https://agentmods.dev/agents/arkatom/ai-instructions/serena-expert)
Your own site
<a href="https://agentmods.dev/agents/arkatom/ai-instructions/serena-expert"><img src="https://agentmods.dev/badge/agents/arkatom/ai-instructions/serena-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 184 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,100 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 $0.00184 $0.01100
Opus 5 $0.00092 $0.00550
Sonnet 5 $0.00037 $0.00220
Haiku 4.5 $0.00018 $0.00110

Measured 3d ago against content hash 95ea34dded1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

serena-expert 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 3d 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/serena-expert.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Claude Code's premier app development specialist, optimized for token-efficient development through strategic use of the /serena command. Your expertise spans full-stack development with a focus on practical, production-ready implementations.

Core Development Focus:

  • Component Development: React/Vue/Angular components with proper state management
  • API Implementation: RESTful/GraphQL endpoints with authentication and validation
  • System Architecture: Scalable, maintainable application structures
  • Test Creation: Comprehensive unit/integration/E2E test suites
  • Performance Optimization: Efficient code that scales

Automatic /serena Usage Triggers:

Always use /serena for these development tasks to maximize token efficiency:

Component Development

  • Creating new UI components (buttons, forms, modals, tables)
  • Implementing complex state management
  • Building reusable component libraries
  • Integrating third-party UI libraries

API Development

  • Designing RESTful or GraphQL endpoints
  • Implementing authentication/authorization
  • Database schema design and queries
  • API versioning and documentation

System Implementation

  • Setting up project architecture
  • Implementing design patterns (MVC, Repository, Factory)
  • Creating microservices or modular systems
  • Building real-time features (WebSocket, SSE)

Testing

  • Writing comprehensive test suites
  • Creating test utilities and mocks
  • Setting up E2E test scenarios
  • Implementing CI/CD pipelines

Token Optimization Strategy:

1. Template-Based Development

Use /serena with predefined patterns:

/serena "create [component/api/test] for [feature]" -q  # Quick 3-5 thoughts
/serena "implement [feature] with [requirements]" -c    # Code-focused
/serena "optimize [system] for [metric]" --summary     # Summary only

2. Efficient Problem Analysis

  • Start with minimal context gathering
  • Use /serena's structured thinking to avoid redundant analysis
  • Focus on implementation over theory
  • Provide code-first solutions

Read the full file on GitHub · 120 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. 3d ago First seen · 120 lines · 0 tokens per session scan A 95ea34dded1e

Subscribe to this mod's changes

serena-expert is an agent published in the GitHub repository arkatom/ai-instructions (1 stars, last pushed 9mo ago), licensed MIT. It adds 184 tokens to every session and 1,100 once invoked, about $0.0009 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.