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.
npx agentmods add commands/agentmessaging/claude-plugin/amp-inboxgit clone --depth 1 https://github.com/agentmessaging/claude-pluginWhat 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 | $0.00622 |
| Opus 5 | $0.00000 | $0.00311 |
| Sonnet 5 | $0.00000 | $0.00124 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
amp-inbox scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/amp-inbox
Check your message inbox for new and existing messages.
Usage
/amp-inbox [options]
Options
--all, -a- Show all messages (default: unread only)--unread, -u- Show only unread messages--read, -r- Show only read messages--count, -c- Show message count only--json, -j- Output as JSON--limit, -l N- Maximum messages to show (default: 20)
Examples
Check unread messages
/amp-inbox
Show all messages
/amp-inbox --all
Get message count
/amp-inbox --count
JSON output for scripting
/amp-inbox --json
Implementation
When this command is invoked, execute:
scripts/amp-inbox.sh "$@"
Output
📬 You have 3 unread message(s)
● 🔴 [msg_1706648400_abc1...]
From: [email protected]
Subject: Code review request
Date: Feb 2, 2025 10:30 AM | Type: request
● 🟡 [msg_1706648410_def4...]
From: [email protected]
Subject: Build notification
Date: Feb 2, 2025 11:00 AM | Type: notification
● 🔵 [msg_1706648420_ghi7...]
From: [email protected]
Subject: Status update
Date: Feb 2, 2025 11:30 AM | Type: status
---
To read a message: amp-read <message-id>
To reply: amp-reply <message-id> "Your reply"
Priority indicators:
- 🔴 urgent
- 🟡 high
- (no icon) normal
- 🔵 low
Status indicators:
- ● unread
- ○ read
No Messages
📭 No unread messages
Your address: [email protected]
JSON Output
[
{
"envelope": {
"id": "msg_1706648400_abc123",
"from": "[email protected]",
"to": "[email protected]",
"subject": "Code review request",
"priority": "high",
"timestamp": "2025-02-02T15:30:00Z"
},
"payload": {
"type": "request",
"message": "Please review PR #42"
},
"metadata": {
"status": "unread"
}
}
]
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.
- 2d ago First seen · 120 lines · 0 tokens per session scan A e91b04359ce4
amp-inbox is a command published in the GitHub repository agentmessaging/claude-plugin (5 stars, last pushed 14d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 622 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.
Other commands, from other repositories
release
Ship a stable cmux release built by CI: bump version, update changelog, open a PR, merge, tag, then GitHub Actions builds, signs, and publishes.
plannotator-annotate
Open interactive annotation UI for a markdown file.
thumbgate-blocked
Show what ThumbGate has actually blocked — gate enforcement stats and the full enforcement matrix. Use for "what has ThumbGate blocked", "show gate stats", "is enforcement working", "how many tokens did we save", "enforcement matrix".
capture-feedback
Quick feedback capture with structured signals.
check-gates
Run a Pre-Action Gate check against prevention rules before executing a risky action.
ssh-keys
Manage SSH keys across hosts — generate, sync, list status, or delete.