serena CLAUDE.md

serena CLAUDE.md is an instructions file for coding agents from chrisgreenx-ctrl/serena. It costs 1,111 tokens per session, scanned A, a copy of serena CLAUDE.md, MIT.

A set of Claude Code instructions for developing Serena, including its commands, architecture, language support, and MCP server usage. Serena is a coding tool that supports work across multiple programming languages.

In plain words
What is it for?
Use it while changing Serena to follow its required development commands, select language-specific tests, understand its structure, and run the project’s MCP server.
Why use it?
It gives contributors project-specific rules for formatting, type checking, testing, linting, and starting its services.

Instructions file

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 instructions/chrisgreenx-ctrl/serena/claude-md
Clone the repo
git clone --depth 1 https://github.com/chrisgreenx-ctrl/serena

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chrisgreenx-ctrl/serena/claude-md.svg)](https://agentmods.dev/instructions/chrisgreenx-ctrl/serena/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chrisgreenx-ctrl/serena/claude-md"><img src="https://agentmods.dev/badge/instructions/chrisgreenx-ctrl/serena/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,111 This file is loaded in full into every session.
When invoked 1,111 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.01111 $0.01111
Opus 5 $0.00556 $0.00556
Sonnet 5 $0.00222 $0.00222
Haiku 4.5 $0.00111 $0.00111

Measured 3d ago against content hash 334c449c8138, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

serena CLAUDE.md 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.

Origin

This is a copy

100% identical to serena CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Development Commands

Essential Commands (use these exact commands):

  • uv run poe format - Format code (BLACK + RUFF) - ONLY allowed formatting command
  • uv run poe type-check - Run mypy type checking - ONLY allowed type checking command
  • uv run poe test - Run tests with default markers (excludes java/rust by default)
  • uv run poe test -m "python or go" - Run specific language tests
  • uv run poe test -m vue - Run Vue tests
  • uv run poe lint - Check code style without fixing

Test Markers: Available pytest markers for selective testing:

  • python, go, java, rust, typescript, vue, php, perl, powershell, csharp, elixir, terraform, clojure, swift, bash, ruby, ruby_solargraph
  • snapshot - for symbolic editing operation tests

Project Management:

  • uv run serena-mcp-server - Start MCP server from project root
  • uv run index-project - Index project for faster tool performance

Always run format, type-check, and test before completing any task.

Architecture Overview

Serena is a dual-layer coding agent toolkit:

Core Components

1. SerenaAgent (src/serena/agent.py)

  • Central orchestrator managing projects, tools, and user interactions
  • Coordinates language servers, memory persistence, and MCP server interface
  • Manages tool registry and context/mode configurations

2. SolidLanguageServer (src/solidlsp/ls.py)

  • Unified wrapper around Language Server Protocol (LSP) implementations
  • Provides language-agnostic interface for symbol operations
  • Handles caching, error recovery, and multiple language server lifecycle

3. Tool System (src/serena/tools/)

  • file_tools.py - File system operations, search, regex replacements
  • symbol_tools.py - Language-aware symbol finding, navigation, editing
  • memory_tools.py - Project knowledge persistence and retrieval
  • config_tools.py - Project activation, mode switching
  • workflow_tools.py - Onboarding and meta-operations

Read the full file on GitHub · 114 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 · 114 lines · 1,111 tokens per session scan A 334c449c8138

Subscribe to this mod's changes

serena CLAUDE.md is an instructions file published in the GitHub repository chrisgreenx-ctrl/serena (0 stars, last pushed 8mo ago), licensed MIT. It adds 1,111 tokens to every session, about $0.0056 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to serena CLAUDE.md, differing in 0 lines, and is treated as a copy.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens