respond

A command that creates replies to common legal inquiries from configured templates, such as privacy requests, subpoenas, and NDA questions.

In plain words
What is it for?
Use it to draft replies for data-subject requests, litigation holds, vendor questions, NDA requests, privacy inquiries, subpoenas, insurance claims, or custom templates.
Why use it?
It saves time on routine legal correspondence and identifies cases that need a lawyer’s review instead of a standard response.

Command

Part of the legal plugin — 2 commands shipped together

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/fergupa/claude_plugins/respond
Clone the repo
git clone --depth 1 https://github.com/fergupa/claude_plugins

Or install legal, the plugin that ships this one along with the rest of its 2 commands.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,449 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00011 $0.01449
Opus 5 $0.00005 $0.00724
Sonnet 5 $0.00002 $0.00290
Haiku 4.5 $0.00001 $0.00145

Measured 2d ago against content hash 319c785cdee1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

respond 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.

Origin

This is a copy

100% identical to respond — 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.

legal/commands/respond.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/respond -- Generate Response from Templates

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Generate a response to a common legal inquiry using configured templates. Customizes the response with specific details and includes escalation triggers for situations that should not use a templated response.

Important: This command assists with legal workflows but does not provide legal advice. Generated responses should be reviewed by qualified legal professionals before being sent.

Invocation

/respond [inquiry-type]

Common inquiry types:

  • dsr or data-subject-request -- Data subject access/deletion/correction requests
  • hold or discovery-hold -- Litigation hold notices
  • vendor or vendor-question -- Vendor legal questions
  • nda or nda-request -- NDA requests from business teams
  • privacy or privacy-inquiry -- Privacy-related questions
  • subpoena -- Subpoena or legal process responses
  • insurance -- Insurance claim notifications
  • custom -- Use a custom template

If no inquiry type is provided, ask the user what type of response they need and show available categories.

Workflow

Step 1: Identify Inquiry Type

Accept the inquiry type from the user. If the type is ambiguous, show available categories and ask for clarification.

Step 2: Load Template

Look for templates in local settings (e.g., legal.local.md or a templates directory).

If templates are configured:

  • Load the appropriate template for the inquiry type
  • Identify required variables (recipient name, dates, specific details)

If no templates are configured:

  • Inform the user that no templates were found for this inquiry type
  • Offer to help create a template (see Step 6)
  • Provide a reasonable default response structure based on the inquiry type

Step 3: Check Escalation Triggers

Before generating the response, evaluate whether this situation has characteristics that should NOT use a templated response:

Read the full file on GitHub · 198 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 · 198 lines · 11 tokens per session scan A 319c785cdee1

Subscribe to this mod's changes

respond is a command published in the GitHub repository fergupa/claude_plugins (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,449 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to respond, differing in 0 lines, and is treated as a copy.