add-integration

A command recipe for adding support for another coding assistant to mgrep, a command-line tool. It describes researching the assistant's configuration and adding install and uninstall commands.

In plain words
What is it for?
Use it when adding an integration such as Cursor or Windsurf. It covers finding configuration files, creating installer code, registering commands, and adding any needed plugin settings.
Why use it?
It gives developers a repeatable way to connect mgrep to another assistant. This reduces missed registration steps and inconsistent integration behaviour.

Command for Claude Code

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 commands/mixedbread-ai/mgrep/add-integration
Clone the repo
git clone --depth 1 https://github.com/mixedbread-ai/mgrep

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 421 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 $0.00000 $0.00421
Opus 5 $0.00000 $0.00211
Sonnet 5 $0.00000 $0.00084
Haiku 4.5 $0.00000 $0.00042

Measured 2d ago against content hash 6309305829e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-integration 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 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.

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/commands/add-integration.md · 61 lines

What it actually says

Add Integration

Add support for a new coding agent integration.

Arguments

  • $ARGUMENTS - Name of the agent to integrate (e.g., "cursor", "windsurf")

Steps

  1. Research the agent's configuration

    • Find where the agent stores its configuration
    • Understand what format/files it expects
    • Look for existing plugin/extension patterns
  2. Create the installer at src/install/$ARGUMENTS.ts:

    import { Command } from "commander";
    
    export const install$ARGUMENTS = new Command("install-$ARGUMENTS")
      .description("Install mgrep integration for $ARGUMENTS")
      .action(async () => {
        // 1. Check if agent is installed
        // 2. Authenticate user if needed
        // 3. Write configuration files
        // 4. Display success message
      });
    
    export const uninstall$ARGUMENTS = new Command("uninstall-$ARGUMENTS")
      .description("Remove mgrep integration from $ARGUMENTS")
      .action(async () => {
        // 1. Find configuration files
        // 2. Remove mgrep-specific config
        // 3. Display success message
      });
    
  3. Register commands in src/index.ts:

    • Add imports for both install and uninstall
    • Add program.addCommand() for both
  4. Add plugin configuration if needed:

    • Create plugins/$ARGUMENTS/ directory
    • Add any required manifest or config files
  5. Add tests:

    • Test installation creates correct files
    • Test uninstallation removes files cleanly
  6. Update documentation:

    • Add to README.md under "Using it with Coding Agents"
    • Add to AGENTS.md if agent-specific guidelines needed
  7. Verify:

    pnpm typecheck
    pnpm test
    pnpm build
    
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 · 61 lines · 0 tokens per session scan A 6309305829e6

Subscribe to this mod's changes

add-integration is a command published in the GitHub repository mixedbread-ai/mgrep (4,389 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 421 tokens. 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.