What is cocoindex-code CLAUDE.md?

Project instructions for cocoindex-code, an AST-based semantic code-search tool. They describe its Python commands, background daemon, command-line client, and MCP server.

Use them when developing or testing cocoindex-code, including its daemon, Unix-socket or Windows-pipe communication, CLI, and MCP server.

They give a coding agent the repository’s build, test, lint, type-checking, architecture, and Docker test instructions.

cocoindex-code CLAUDE.md — Instructions file by cocoindex-io

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/cocoindex-io/cocoindex-code/claude-md

Clone the repo

git clone --depth 1 https://github.com/cocoindex-io/cocoindex-code

Per session 1,766 This file is loaded in full into every session.

When invoked 1,766 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.01766	$0.01766
Opus 5	$0.00883	$0.00883
Sonnet 5	$0.00353	$0.00353
Haiku 4.5	$0.00177	$0.00177

Measured yesterday against content hash f28b9d779483, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cocoindex-code 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 yesterday.

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.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 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.

This is an AST-based semantic code search tool built on top of CocoIndex v1.

Build and Test Commands

This project uses uv for project management.

uv sync                                # Install all dev dependencies
uv run pytest tests/                   # Run all tests
uv run pytest tests/test_settings.py  # Run a single test file
uv run pytest tests/ -k test_name     # Run tests matching a name
uv run mypy .                          # Type check Python code
uv run ruff check .                    # Lint
uv run ruff format .                   # Format
uv run prek run --all-files            # Full CI suite (lint, format, mypy, pytest)

Docker E2E tests are excluded by default (need pytest -m docker_e2e to run them).

Architecture

Process Model

The tool runs as a long-lived background daemon (daemon.py) that accepts connections over a Unix socket (Windows: named pipe). The ccc CLI and MCP server communicate with it via short-lived per-request connections (client.py): connect → handshake → send one request → receive response(s) → close.

The daemon is auto-started by client.py when not running. It is restarted automatically when the global_settings.yml mtime changes (version bump or settings edit), detected via the HandshakeResponse.global_settings_mtime_us field.

The daemon idle-exits after daemon.idle_timeout_minutes (default 180, 0 = never) without client activity. A live MCP session sends heartbeats by default; users can set daemon.keep_alive_with_mcp: false to allow idle exit during a connected session. Clients transparently restart the daemon on the next real request. Graceful exits leave a last_exit marker file so the client can tell an expected exit from a crash (which triggers a loud restart, capped after consecutive crashes).

Read the full file on GitHub · 105 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.

yesterday First seen · 105 lines · 1,766 tokens per session scan A f28b9d779483

Subscribe to this mod's changes

cocoindex-code CLAUDE.md is an instructions file published in the GitHub repository cocoindex-io/cocoindex-code (2,682 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,766 tokens to every session, about $0.0088 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.

Data and AI Research Testing agents code-search coding-agent context-engineering indexing python

cocoindex-code CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Build and Test Commands

Architecture

Process Model

What this file has done since we first saw it

Other instructions, from other repositories

agno CLAUDE.md

remind AGENTS.md

terminal-jarvis AGENTS.md

ken CLAUDE.md

openai-agents-python CLAUDE.md

mini-claude-code-python AGENTS.md