serena-initializer

serena-initializer is an agent for coding agents from christian289/dotnet-with-claudecode. It costs 46 tokens per session (595 once invoked), scanned A, original, MIT.

An agent that prepares the Serena MCP project-analysis tools for a new codebase. It checks the active project, activates the current one when needed, and creates an initial project overview if none exists.

In plain words
What is it for?
Initializing Serena at the start of a project, checking whether setup is complete, and onboarding the codebase for later tool use.
Why use it?
It avoids working with the wrong project or missing project context when Serena tools are used.

Agent

Part of the wpf-dev-pack plugin — 28 skills, 10 agents, 4 hooks, 2 MCP servers shipped together

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/christian289/dotnet-with-claudecode/serena-initializer
Clone the repo
git clone --depth 1 https://github.com/christian289/dotnet-with-claudecode

Or install wpf-dev-pack, the plugin that ships this one along with the rest of its 28 skills, 10 agents, 4 hooks, 2 MCP servers.

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-initializer

README.md
[![agentmods](https://agentmods.dev/badge/agents/christian289/dotnet-with-claudecode/serena-initializer.svg)](https://agentmods.dev/agents/christian289/dotnet-with-claudecode/serena-initializer)
Your own site
<a href="https://agentmods.dev/agents/christian289/dotnet-with-claudecode/serena-initializer"><img src="https://agentmods.dev/badge/agents/christian289/dotnet-with-claudecode/serena-initializer.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 595 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 5.1 $0.00046 $0.00595
Opus 5 $0.00023 $0.00298
Sonnet 5 $0.00009 $0.00119
Haiku 4.5 $0.00005 $0.00060

Measured 5d ago against content hash e0e45ac8acb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

serena-initializer 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.

wpf-dev-pack/agents/serena-initializer.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Serena Initializer - Project Setup Agent

Role

Initialize Serena MCP for the current project by checking activation and onboarding status, then performing necessary setup steps.

Workflow

Step 1: Check Current Configuration

First, check the current Serena configuration:

Use mcp__serena__get_current_config to see:
- Active project (if any)
- Available projects
- Current modes

Step 2: Activate Project

If no project is active or wrong project is active:

Use mcp__serena__activate_project with the current project path
- Project path should be the working directory
- Or select from available registered projects

Step 3: Check Onboarding Status

After activation, check if onboarding was performed:

Use mcp__serena__check_onboarding_performed
- Returns whether onboarding is complete
- If not complete, proceed to Step 4

Step 4: Perform Onboarding (if needed)

If onboarding was not performed:

Use mcp__serena__onboarding
- This will analyze the project structure
- Creates project memory for future sessions
- Only needs to be done once per project

Output Format

## Serena Initialization Report

### Project Status
- **Project Path**: [path]
- **Activation**: ✅ Active / ❌ Not Active → Activated
- **Onboarding**: ✅ Complete / ❌ Not Complete → Completed

### Actions Taken
1. [Action 1]
2. [Action 2]

### Ready to Use
Serena is now ready. Available tools:
- find_symbol, find_referencing_symbols
- get_symbols_overview, search_for_pattern
- replace_symbol_body, insert_after_symbol
- rename_symbol, replace_content

Error Handling

Project Not Found

If the project path is not registered:

  1. Try activating with the full path
  2. If fails, inform user to check Serena configuration

Onboarding Fails

If onboarding fails:

  1. Check if project has valid source files (.cs, .xaml)
  2. Ensure project structure is accessible
  3. Report specific error to user

When to Use This Agent

  • First time using Serena on a project
  • After cloning a new repository
  • When Serena tools return "No active project" error
  • When switching between multiple projects

Read the full file on GitHub · 99 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 · 99 lines · 46 tokens per session scan A e0e45ac8acb6

Subscribe to this mod's changes

serena-initializer is an agent published in the GitHub repository christian289/dotnet-with-claudecode (41 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 595 once invoked, about $0.0002 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

documentation-updater

Technical writing specialist for creating and maintaining documentation. Use proactively after code changes to detect and fix documentation drift - new or changed APIs, parameters, configuration, dependencies, or removed features. Also use when asked to write or update READMEs, getting-started guides, API references…

sintaxasn/Fluence.Wpf · 91 tokens

theme-slot-auditor

Read-only auditor for Fluence.Wpf theming structure. Use after any theme, brush, color, accent, or ApplicationThemeManager change to verify the three-slot MergedDictionaries invariant, that slot [0] is rebuilt and replaced every Apply, DynamicResource usage, BrushFactory auto-twinning, canonical WinUI key names, and…

sintaxasn/Fluence.Wpf · 90 tokens

net472-feasibility-checker

Read-only checker that verifies new or changed code in Fluence.Wpf stays runnable on net472. Use after adding APIs, language features, or dependencies, since LangVersion=latest lets modern C# compile but a runtime API that ships only in .NET 10 fails on the separate net472 test lane. Enforces AGENTS.md section 4.3.

sintaxasn/Fluence.Wpf · 81 tokens

winui-parity-reviewer

Read-only reviewer for Fluence.Wpf control and theme changes. Use to compare WPF templates, resources, and behavior against WinUI 3 CommonStyles and official Microsoft guidance.

sintaxasn/Fluence.Wpf · 43 tokens

looping

Re-invoke agents safely with bounded loops, completion evaluators, AI judges, progress feedback, and approval escape behavior.

managedcode/dotnet-skills · 24 tokens

planning-and-todos

Structure long-running agent work with todo and agent-mode providers, custom persistence, and plan-execute patterns.

managedcode/dotnet-skills · 21 tokens