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 skills add jeanfbrito/rocket-cli --skill rocket-guidegit clone --depth 1 https://github.com/jeanfbrito/rocket-cliWrote 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/skills/jeanfbrito/rocket-cli/rocket-guide)<a href="https://agentmods.dev/skills/jeanfbrito/rocket-cli/rocket-guide"><img src="https://agentmods.dev/badge/skills/jeanfbrito/rocket-cli/rocket-guide/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/skills/jeanfbrito/rocket-cli/rocket-guide"><img src="https://agentmods.dev/badge/skills/jeanfbrito/rocket-cli/rocket-guide.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 | $0.00098 | $0.01680 |
| Opus 5.5 | $0.00039 | $0.00672 |
| Sonnet 5.5 | $0.00020 | $0.00336 |
| Haiku 4.5 | $0.00010 | $0.00168 |
Grade A, and why
rocket-guide 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 1mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rocket-guide
Map of the rocket-cli surface: 18 MCP tools, the cache model, profiles, and the CLI↔MCP correspondence.
Transport
- When the rocket-cli MCP server is connected, prefer its tools (registered under the server you configured — referenced here by their bare snake_case names).
- Otherwise every read tool has a CLI equivalent:
rocket-cli <cmd> --json. - Multi-server:
--profile <name>(CLI) orROCKET_CLI_PROFILE(MCP env). Each profile is an isolated server identity with its own cache db.
All MCP tools
| Tool | Purpose | Key params |
|---|---|---|
list_rooms |
List rooms you belong to (channels, groups, DMs); discover ids/names | filter?, type? (channel/group/dm), limit (≤200, def 50) |
get_messages |
Read recent messages in a room, newest-first; thread parents carry replyCount |
room, count (≤100, def 30), before?/after? ISO, includeSystem (def false) |
get_unread |
Unread messages since each room's last-read watermark (UI-parity) | limitPerRoom (≤100, def 50), includeThreads (def true), includeHidden (def false) |
get_mentions |
Messages that @-mention the user across cached rooms | sinceDays (1-90, def 7), limit (≤100, def 50), includeChannelWide (def false) |
get_attention |
One-call triage: mentions + unread DMs + unread threads + unread channels, prioritized | sinceDays (1-90, def 7), limitPerSection (≤100, def 30), includeChannelWide (def false) |
get_message_context |
Conversation around a message id/link; thread replies pivot to the whole thread | messageId, before (0-50, def 10), after (0-50, def 5) |
open_url |
Resolve any pasted Rocket.Chat link → content + action ids | url, count (≤100, def 20) |
get_thread_messages |
Full thread: parent + replies, chronological | threadId (id or link), count (≤200, def 50) |
list_threads |
Active threads in a room, most-recent first | room, count (≤100, def 25), text? |
sync_history |
Load older history for ONE room into the cache (explicit depth only) | room? (omit = most stale unread room), depth? (≤5000) |
search_messages |
Full-text search; cross-room = local cache only; room enables server fallback |
query, room?, author?, limit (≤100, def 20) |
send_message |
Send to a room or reply in a thread (write) | target, text, threadId? |
add_reaction |
React to a message / remove a reaction (write) | messageId (id or link), emoji, remove (def false) |
upload_file |
Attach a local file to a room/thread (write) | room, filePath, text?, threadId?, fileName? |
get_user_profile |
Look up a user by username/id (status, existence) | user |
download_attachment |
Download a message attachment to local disk | fileUrl (the part after ->), savePath? |
list_custom_emojis |
List server custom emojis (names for :name: / add_reaction) |
filter? |
get_custom_emoji |
Show a custom emoji's image | name |
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.
- 1mo ago First seen · 77 lines · 98 tokens per session scan A 493cc4999d9f
rocket-guide is a skill published in the GitHub repository jeanfbrito/rocket-cli (3 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 1,680 once invoked, about $0.0004 per session on Opus 5.5. 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…