overview

A guide to Code Context Engine integrations for AI coding agents and editors that support MCP, a standard way for an agent to call external tools. It covers automatic setup for Claude Code, Copilot, Cursor, Codex CLI, Pi, and Gemini CLI.

In plain words
What is it for?
Use it to configure supported agents, select which agent to set up, understand where each configuration and instruction file belongs, and use shared project context across agents.
Why use it?
It provides one setup path for connecting the same code-search and memory service to different agents. Automatic detection can identify supported tools already present in a project or environment.

Agent

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/elara-labs/code-context-engine/overview
Clone the repo
git clone --depth 1 https://github.com/elara-labs/code-context-engine
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,275 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00012 $0.01275
Opus 5 $0.00006 $0.00638
Sonnet 5 $0.00002 $0.00255
Haiku 4.5 $0.00001 $0.00128

Measured 2d ago against content hash e56088afbb9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

overview scanned grade B 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| [Codex CLI](/code-context-engine/guide/agents/codex/) | `~/.codex/config.toml` | `AGENTS.md` | User (global) | `~/.codex/` or VS Code OpenAI extension |
docs-src/src/content/docs/agents/overview.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Context Engine works with any AI coding agent that supports MCP (Model Context Protocol). The cce init command auto-detects which agents are present in your environment and configures them automatically.

The --agent flag

cce init                   # Default. Detects installed agents.
cce init --agent claude    # Configure only Claude Code
cce init --agent copilot   # Configure only VS Code / Copilot
cce init --agent codex     # Configure only Codex CLI
cce init --agent pi        # Configure only Pi
cce init --agent all       # Configure all supported agents

When no --agent flag is provided, cce init defaults to auto, which scans for known config files and editor directories.

Supported Editors and Agents

Agent MCP Config Instruction File Scope Detection
Claude Code .mcp.json CLAUDE.md Project Always configured
VS Code / Copilot .vscode/mcp.json .github/copilot-instructions.md Project .vscode/ exists
Cursor .cursor/mcp.json .cursorrules Project .cursor/ or .cursorrules exists
Gemini CLI .gemini/settings.json GEMINI.md Project .gemini/ or GEMINI.md exists
Codex CLI ~/.codex/config.toml AGENTS.md User (global) ~/.codex/ or VS Code OpenAI extension
OpenCode opencode.json (none) Project opencode.json exists
Tabnine .tabnine/agent/settings.json TABNINE.md Project .tabnine/ exists
Pi .mcp.json AGENTS.md Project .pi/ exists

How it works

Each agent integration does two things:

Read the full file on GitHub · 104 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. 2d ago First seen · 104 lines · 12 tokens per session scan B e56088afbb9e

Subscribe to this mod's changes

overview is an agent published in the GitHub repository elara-labs/code-context-engine (407 stars, last pushed 9d ago), licensed MIT. It adds 12 tokens to every session and 1,275 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.