rocket-guide

A reference guide for rocket-cli, a command-line and MCP interface for reading rooms, messages, unread items, and mentions. It also explains profiles, cached data, and how command-line tools map to MCP tools.

In plain words
What is it for?
Use it when selecting rocket-cli tools, reading communication rooms, handling profiles, or translating between its command-line and MCP interfaces.
Why use it?
It helps the agent choose the right rocket-cli operation without guessing how its tools, cache, or profiles work.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/jeanfbrito/rocket-cli/rocket-guide
Any agent
npx skills add jeanfbrito/rocket-cli --skill rocket-guide
Clone the repo
git clone --depth 1 https://github.com/jeanfbrito/rocket-cli

Made for: Claude Code, Codex.

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,680 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00098 $0.01680
Opus 5 $0.00049 $0.00840
Sonnet 5 $0.00020 $0.00336
Haiku 4.5 $0.00010 $0.00168

Measured yesterday against content hash 493cc4999d9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

skills/rocket-guide/SKILL.md · 77 lines

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) or ROCKET_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

Read the full file on GitHub · 77 lines

Changes

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.

  1. yesterday First seen · 77 lines · 98 tokens per session scan A 493cc4999d9f

Subscribe to this mod's changes

rocket-guide is a skill published in the GitHub repository jeanfbrito/rocket-cli (2 stars, last pushed 15d ago), licensed MIT. It adds 98 tokens to every session and 1,680 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens