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.
git clone --depth 1 https://github.com/agentmessaging/claude-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/agentmessaging/claude-plugin/amp-prune)<a href="https://agentmods.dev/commands/agentmessaging/claude-plugin/amp-prune"><img src="https://agentmods.dev/badge/commands/agentmessaging/claude-plugin/amp-prune/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/agentmessaging/claude-plugin/amp-prune"><img src="https://agentmods.dev/badge/commands/agentmessaging/claude-plugin/amp-prune.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00000 | $0.00234 |
| Opus 5.5 | $0.00000 | $0.00094 |
| Sonnet 5.5 | $0.00000 | $0.00047 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
amp-prune 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 7d 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-prune
Remove old messages and attachments from your agent's mailbox.
Usage
/amp-prune [options]
Options
--dry-run- Show what would be removed (default)--apply- Remove it--days N- Age threshold in days (default: 90)--include-unread- Also remove unread inbox messages (default: keep them)--id UUID- Operate as this agent
What it removes
- Read inbox messages older than N days
- Sent messages older than N days
- Attachment folders older than N days that no remaining message refers to
Symlinks are never followed. A summary with the bytes freed is printed.
Automatic pruning
Off by default. Set AMP_RETENTION_DAYS=N and saving a message to the inbox runs this in the background, at most once every 24 hours. Unset, 0 or a non-number leaves it off.
Examples
/amp-prune
/amp-prune --days 30 --apply
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.
- 7d ago First seen · 37 lines · 0 tokens per session scan A 50ddf4078cf5
amp-prune is a command published in the GitHub repository agentmessaging/claude-plugin (5 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 234 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 2026-10-10.
Other commands, from other repositories
delete-session
A command for safely listing, inspecting, moving, and restoring Claude Code history sessions.
atomic-help
Route a lost user to the right atomic verb, skill, agent, or binary subcommand. Bare invocation reads git state and recommends one next step. Topic keyword or freeform intent → focused pointer. tour → guided walkthrough of the system. Help router, not duplicated docs.
follow-up
Review and act on pending reminders. Bare invocation shows all reminders as an indexed list; cron-fired invocation (/follow-up due ) surfaces the specific reminder and waits for a response; /follow-up review lists stale project follow-up entries for per-item disposition (extend/close/promote/skip). Transport-aware…
stop
Gracefully close the Vibe Squad tmux session from inside Chrono.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
maestro-companion
Quick execution for small tasks — minimal run lifecycle (start + done) with evidence recording. Full LLM capability, scoped to mechanically clear tasks.