amp-delete

A command for permanently removing a message from an inbox or sent folder. It can ask for confirmation or delete the message immediately with an option.

In plain words
What is it for?
Use it to delete an inbox or sent message by its message ID, with an optional force mode when confirmation is not needed.
Why use it?
It removes unwanted messages without requiring manual navigation through the messaging system. The confirmation step helps prevent deleting the wrong message.

Command

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-delete
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 369 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 $0.00369
Opus 5 $0.00000 $0.00185
Sonnet 5 $0.00000 $0.00074
Haiku 4.5 $0.00000 $0.00037

Measured yesterday against content hash b03aec9115a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

amp-delete 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-delete.md · 83 lines

What it actually says

/amp-delete

Delete a message from your inbox or sent folder.

Usage

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

Arguments

  • message-id - The message ID to delete

Options

  • --sent, -s - Delete from sent folder (default: inbox)
  • --force, -f - Delete without confirmation

Examples

Delete an inbox message

/amp-delete msg_1706648400_abc123

Delete without confirmation

/amp-delete msg_1706648400_abc123 --force

Delete a sent message

/amp-delete msg_1706648400_abc123 --sent

Implementation

When this command is invoked, execute:

scripts/amp-delete.sh "$@"

Output

With confirmation:

Message to delete:

  ID:      msg_1706648400_abc123
  From:    [email protected]
  Subject: Code review request
  Date:    2025-02-02T10:30:00Z

Are you sure you want to delete this message? [y/N] y
✅ Message deleted

With --force:

Message to delete:

  ID:      msg_1706648400_abc123
  From:    [email protected]
  Subject: Code review request
  Date:    2025-02-02T10:30:00Z

✅ Message deleted

Errors

Message not found:

Error: Message not found: msg_invalid_id

Check the message ID and folder (inbox/sent).
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. yesterday First seen · 83 lines · 0 tokens per session scan A b03aec9115a0

Subscribe to this mod's changes

amp-delete 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 369 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.