rocket-send

A Rocket.Chat helper for sending messages, replies, reactions, and file uploads. Rocket.Chat is a team chat service, and the helper asks for confirmation before making anything visible to other people.

In plain words
What is it for?
Use it to post in a channel, send a direct message, reply, react to a message, upload a file, or resolve a pasted chat target.
Why use it?
It reduces the risk of posting to the wrong room or sending an unintended message. If the account cannot write, it can instead prepare a message for you to send yourself.

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

Made for: Claude Code, Codex.

Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 875 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 $0.00113 $0.00875
Opus 5 $0.00056 $0.00438
Sonnet 5 $0.00023 $0.00175
Haiku 4.5 $0.00011 $0.00088

Measured yesterday against content hash 0f381b0099a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rocket-send 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-send/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rocket-send

Write actions: send, reply, react, upload. Confirm before anything hits the server. Always return the resulting permalink.

Transport

  • Prefer MCP when connected: send_message, add_reaction, upload_file, plus list_custom_emojis / get_custom_emoji for emoji resolution and open_url to resolve a pasted target.
  • Otherwise shell out: rocket-cli send <target> [text…] --json, rocket-cli upload <room> <file> --json. (Reactions are MCP-first; if no react CLI subcommand is available, fall back to drafting.)
  • Multi-server: --profile <name> (CLI) or ROCKET_CLI_PROFILE (MCP env). Confirm which server when ambiguous.

Read-only degradation (check first)

The write tools (send_message, add_reaction, upload_file) are only registered when the profile permits them. On a read-only profile they are absent. If a write tool is unavailable (not in the tool list, or the call fails with a permission/capability error), do NOT keep retrying — switch to drafting: compose the exact message and tell the user to send it themselves (or switch profiles). Never silently fail.

Workflow

  1. Resolve the target.
    • #channel, @username (opens/uses a DM), a room name, or a room id all work directly as the target / room arg.
    • If the user pasted a message or thread link, run open_url to extract the room and the message/thread id.
  2. Decide thread vs. room. When replying to a thread message, reply IN the thread: pass that thread parent's id as threadId (also tmid in raw API terms). Prefer in-thread replies when responding to anything thread-shaped, rather than posting to the room root.
  3. Confirm before sending. Show the user the exact target and exact text and get a go-ahead BEFORE calling any write tool — UNLESS the user already supplied both exact text and an unambiguous target, in which case proceed.
  4. Send the right action:
    • Message / reply → send_message (params: target, text non-empty, threadId?). Custom emoji in text use :name: — confirm the name via list_custom_emojis if unsure.
    • Reaction → add_reaction (params: messageId — an id or a pasted message link; emojithumbsup or :thumbsup:; remove default false to withdraw). For a custom emoji, resolve the name first via list_custom_emojis / get_custom_emoji.
    • File → upload_file (params: room, filePath absolute, text? caption, threadId?, fileName?).
  5. Return the permalink. The sent/uploaded message is written into the local cache and the response carries its id/permalink — surface that link so the user can jump to it. This closes the URL loop.

Read the full file on GitHub · 39 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 · 39 lines · 113 tokens per session scan A 0f381b0099a9

Subscribe to this mod's changes

rocket-send is a skill published in the GitHub repository jeanfbrito/rocket-cli (2 stars, last pushed 15d ago), licensed MIT. It adds 113 tokens to every session and 875 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.

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