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.
git clone --depth 1 https://github.com/arkatom/ai-instructionsWrote 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.
[](https://agentmods.dev/agents/arkatom/ai-instructions/serena-expert)<a href="https://agentmods.dev/agents/arkatom/ai-instructions/serena-expert"><img src="https://agentmods.dev/badge/agents/arkatom/ai-instructions/serena-expert/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00184 | $0.01100 |
| Opus 5.5 | $0.00074 | $0.00440 |
| Sonnet 5.5 | $0.00037 | $0.00220 |
| Haiku 4.5 | $0.00018 | $0.00110 |
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 2mo 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.
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
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.
- 2mo ago First seen · 120 lines · 0 tokens per session scan A 95ea34dded1e
serena-expert is an agent published in the GitHub repository arkatom/ai-instructions (1 stars, last pushed 11mo ago), licensed MIT. It adds 184 tokens to every session and 1,100 once invoked, about $0.0007 per session on Opus 5.5. 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.
serena-expert compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| serena-expertarkatom/ai-instructions | Agent | 1 | 11mo ago | MIT | A | 184 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | yesterday | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 3d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 26 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |