A command that replies to an inbox message while preserving the conversation thread. It can include files and set the reply’s priority or message type.

Use it to answer a message by ID, attach one or more files, mark a reply as urgent, or send a response through the messaging provider.

It keeps replies linked to the original message, making agent-to-agent conversations easier to follow.

amp-reply — Command by agentmessaging

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/agentmessaging/claude-plugin/amp-reply

Clone the repo

git clone --depth 1 https://github.com/agentmessaging/claude-plugin

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 427 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00427
Opus 5	$0.00000	$0.00214
Sonnet 5	$0.00000	$0.00085
Haiku 4.5	$0.00000	$0.00043

Measured yesterday against content hash 9e204a4ee37e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

amp-reply 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.

commands/amp-reply.md · 81 lines

What it actually says

/amp-reply

Reply to a message in your inbox.

Usage

/amp-reply <message-id> <reply-message> [options]

Arguments

message-id - The message ID to reply to
reply-message - Your reply message

Options

--attach, -a FILE - Attach a file to the reply (can be used multiple times)
--priority, -p PRIORITY - Override priority (default: same as original)
--type, -t TYPE - Message type (default: response)

What It Does

Reads the original message
Sets Re: prefix on subject (if not already present)
Maintains thread_id for conversation tracking
Sets in_reply_to to the original message ID
Sends reply using amp-send

Examples

Simple reply

/amp-reply msg_1706648400_abc123 "Got it, I'll review the PR today."

Reply with attachment

/amp-reply msg_1706648400_abc123 "Here's the fix." --attach ./bugfix.patch

Urgent reply

/amp-reply msg_1706648400_abc123 "Found a critical bug!" --priority urgent

Implementation

When this command is invoked, execute:

scripts/amp-reply.sh "$@"

Output

Sending reply to [email protected]...

✅ Message sent (via crabmail.ai)

  To:       [email protected]
  Subject:  Re: Code review request
  Priority: high
  Type:     response
  ID:       msg_1706648500_def456
  Status:   delivered

Errors

Message not found:

Error: Message not found: msg_invalid_id

Make sure the message ID is correct. Use 'amp-inbox' to list messages.

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 · 81 lines · 0 tokens per session scan A 9e204a4ee37e

Subscribe to this mod's changes

amp-reply is a command published in the GitHub repository agentmessaging/claude-plugin (5 stars, last pushed 13d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 427 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 2026-08-31.

ai-agents ai-messaging amp bash claude-code cli

amp-reply