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-fetchgit 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 | $0.00488 |
| Opus 5 | $0.00000 | $0.00244 |
| Sonnet 5 | $0.00000 | $0.00098 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
amp-fetch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/amp-fetch
Fetch new messages from external AMP providers.
Usage
/amp-fetch [options]
Options
--provider, -p PROVIDER- Fetch from specific provider only--verbose, -v- Show detailed output--no-mark- Don't acknowledge messages on provider
What It Does
- Connects to each registered external provider
- Downloads new messages not already in local inbox
- Acknowledges receipt (optional, for message tracking)
- Stores messages locally in
~/.agent-messaging/messages/inbox/
Examples
Fetch from all providers
/amp-fetch
Fetch from specific provider
/amp-fetch --provider crabmail.ai
Verbose output
/amp-fetch --verbose
Implementation
When this command is invoked, execute:
scripts/amp-fetch.sh "$@"
Output
Normal:
✅ Fetched 3 new message(s)
View messages: amp-inbox
Verbose:
Fetching from crabmail.ai...
API: https://api.crabmail.ai
Address: [email protected]
Found 3 new message(s)
Saved: msg_1706648400_abc123
From: [email protected]
Subject: Code review request
Saved: msg_1706648410_def456
From: [email protected]
Subject: Question about API
Saved: msg_1706648420_ghi789
From: [email protected]
Subject: Welcome to Crabmail
✅ Fetched 3 new message(s)
View messages: amp-inbox
No new messages:
No new messages from external providers.
Errors
Not registered:
Error: Not registered with crabmail.ai
Register first: amp-register --provider crabmail.ai
Authentication failed:
Error: Authentication failed for crabmail.ai
Your API key may have expired. Re-register with:
amp-register --provider crabmail.ai --force
Connection failed:
Error: Could not connect to crabmail.ai
Check your internet connection.
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 · 108 lines · 0 tokens per session scan A 6d216ea525cb
amp-fetch 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 488 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.
impact-statusline
Show or configure the compact Fallow Impact statusline in Claude Code.
thumbgate-protect
Show this repo's branch/release governance and grant a scoped, time-limited approval for an action that touches protected files. Use for "protect this branch", "is main protected", "approve this protected change", "branch governance", "let me edit a protected file".
capture-feedback
Quick feedback capture with structured signals.
check-gates
Run a Pre-Action Gate check against prevention rules before executing a risky action.
show-lessons
Display promoted lessons and their corrective actions.