What is codebaxing CLAUDE.md?

Project instructions for Codebaxing, a Node.js and TypeScript service that searches source code by meaning. It indexes functions, classes, and methods from many programming languages and finds related code for a natural-language query.

Use it to understand the project structure, search for semantically related code, and work with its local code index. The instructions also describe its parsers, embeddings, and database.

It helps locate relevant code when you do not know the exact file name or wording to search for. This can be useful in large codebases where ordinary text search misses related implementations.

How duysolo/codebaxing configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to duysolo/codebaxing. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/duysolo/codebaxing/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/duysolo/codebaxing

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/duysolo/codebaxing/claude-md/github.svg)](https://agentmods.dev/instructions/duysolo/codebaxing/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/duysolo/codebaxing/claude-md"><img src="https://agentmods.dev/badge/instructions/duysolo/codebaxing/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/duysolo/codebaxing/claude-md"><img src="https://agentmods.dev/badge/instructions/duysolo/codebaxing/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,822 This file is loaded in full into every session.

When invoked 1,822 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01822	$0.01822
Opus 5.5	$0.00729	$0.00729
Sonnet 5.5	$0.00364	$0.00364
Haiku 4.5	$0.00182	$0.00182

Measured 2mo ago against content hash 0854c3b54ea6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codebaxing CLAUDE.md scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Parallel Embedding**: `child_process` pool (default 2 workers, local) or concurrent API calls (cloud)

CLAUDE.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebaxing (Node.js/TypeScript)

MCP server for semantic code search using vector embeddings.

How It Works

Source Code → Tree-sitter (AST) → Symbols → Embedding Model → Vectors → ChromaDB
                                                                            ↓
Query → Embedding Model → Query Vector → Cosine Similarity → Top-k Results

Tree-sitter parses code into AST, extracts functions/classes/methods
all-MiniLM-L6-v2 converts code chunks to 384-dim vectors (runs locally via ONNX)
ChromaDB stores vectors for fast similarity search
Search embeds query and finds nearest neighbors by cosine similarity

Project Structure

src/
├── core/
│   ├── models.ts           # Symbol, ParsedFile, CodebaseIndex, Memory, MemoryType
│   ├── interfaces.ts       # IParser interface
│   └── exceptions.ts       # Error hierarchy
├── parsers/
│   ├── treesitter-parser.ts  # Multi-language AST parsing
│   └── language-configs.ts   # Tree-sitter node mappings (24+ languages)
├── indexing/
│   ├── embedding-service.ts  # @huggingface/transformers wrapper
│   ├── embedding-pool.ts     # Worker pool for parallel embedding
│   ├── embedding-worker.ts   # Worker thread entry point
│   ├── parallel-indexer.ts   # File parsing
│   ├── source-retriever.ts   # Code indexing + semantic search
│   └── memory-retriever.ts   # Memory storage + semantic recall
└── mcp/
    ├── state.ts              # Global singleton (SourceRetriever + MemoryRetriever)
    └── server.ts             # MCP server (8 tools)

MCP Tools (8 total)

Code Search

Tool	Purpose
`index`	Index codebase. Modes: `auto` (incremental), `full`, `load-only`. Required first.
`search`	Semantic search. Returns ranked code chunks with filters (language, symbol_type)
`stats`	Index statistics (files, symbols, chunks)
`languages`	Supported language extensions

Memory Layer

Tool	Purpose
`remember`	Store memories (conversation, status, decision, preference, doc, note)
`recall`	Semantic search over memories
`forget`	Delete memories by ID, type, tags, or age. Destructive.
`memory-stats`	Memory statistics by type

Read the full file on GitHub · 152 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.

2mo ago First seen · 152 lines · 1,822 tokens per session scan A 0854c3b54ea6

Subscribe to this mod's changes

codebaxing CLAUDE.md is an instructions file published in the GitHub repository duysolo/codebaxing (52 stars, last pushed 7mo ago), licensed MIT. It adds 1,822 tokens to every session, about $0.0073 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

codebaxing CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codebaxing CLAUDE.mdduysolo/codebaxing	Instructions file	52	7mo ago	MIT	A	1,822	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

codebaxing: Instructions file for Claude Code