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 skills/jeanfbrito/rocket-cli/rocket-attentionnpx skills add jeanfbrito/rocket-cli --skill rocket-attentiongit clone --depth 1 https://github.com/jeanfbrito/rocket-cliWhat 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 | $0.00122 | $0.00808 |
| Opus 5 | $0.00061 | $0.00404 |
| Sonnet 5 | $0.00024 | $0.00162 |
| Haiku 4.5 | $0.00012 | $0.00081 |
Grade A, and why
rocket-attention 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rocket-attention
Answer "what needs MY attention right now" — the product's core job. Fast, prioritized, honest about freshness.
Transport
- If the rocket-cli MCP server is connected, prefer its tools (
get_attention,get_unread,get_mentions,get_message_context). - Otherwise shell out:
rocket-cli attention --json,rocket-cli unread --json,rocket-cli mentions --json. - Multi-server: pass
--profile <name>to the CLI, or rely onROCKET_CLI_PROFILEin the MCP env block. Never guess a profile — if the user has several, ask which server.
Workflow
- Pick the right tool for the ask.
- Broad ("what did I miss?", "catch me up", "anything important?") →
get_attention. One call returns all four sections, prioritized and deduplicated. - Narrow → use the focused tool: "any mentions?" →
get_mentions; "unread DMs / what's unread?" →get_unread.
- Broad ("what did I miss?", "catch me up", "anything important?") →
- Call it once.
get_attentionparams:sinceDays(1-90, default 7, how far the mention search looks back),limitPerSection(1-100, default 30),includeChannelWide(default false — set true only if the user cares about @all/@here). Do not widensinceDaysunless the user implies a longer window. - Honor
refreshing. If the envelope carriesrefreshing: true, the data was served from cache while a background sync runs and may be seconds stale. Say so briefly if exactness matters ("counts may be a beat behind"); for a casual triage glance just present it. - Present priority-ordered, in this sequence:
- Mentions of the user (most urgent)
- Unread DMs
- Unread thread replies
- Unread channel messages
Within each section, group by room. Each item: who, a one-line gist, and its permalink (always included — this is the URL-loop contract). Rooms flagged
hiddenMentioned=true(hide-unread-counter on but user is mentioned) still belong in the mentions section.
- Offer per-item follow-ups, do not auto-execute:
- "want the surrounding context?" →
get_message_contexton that message id. - "want to reply?" → hand off to the rocket-send workflow.
- "want the surrounding context?" →
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 · 40 lines · 122 tokens per session scan A 2770acde6d79
rocket-attention is a skill published in the GitHub repository jeanfbrito/rocket-cli (2 stars, last pushed 16d ago), licensed MIT. It adds 122 tokens to every session and 808 once invoked, about $0.0006 per session on Opus 5. 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 skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
lark-im
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
organize-threads
猫猫辅助整理未分类 thread，分析标题和元数据，建议合适的标签。 Use when: 用户说"帮我整理"、"分类 thread"、点击整理按钮。 Not for: 删除/编辑标签本身。 Output: 按 thread 的标签建议列表。.