agentmods.dev

rocket-link

A skill for opening Rocket.Chat links, including links to messages, threads, or channels. Rocket.Chat is a team chat application.

In plain words
What is it for?
Use it to inspect a Rocket.Chat message, read a thread, view recent channel messages, or continue with related chat actions.
Why use it?
It turns a pasted chat link into the relevant message or conversation and shows what actions are available.

Skill for Claude CodeCodex

2 15d ago A scan 119 tokens original MIT
View the source file jeanfbrito/rocket-cli
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-link
Any agent
npx skills add jeanfbrito/rocket-cli --skill rocket-link
Clone the repo
git clone --depth 1 https://github.com/jeanfbrito/rocket-cli

Made for: Claude Code, Codex.

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 628 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 $0.00119 $0.00628
Opus 5 $0.00060 $0.00314
Sonnet 5 $0.00024 $0.00126
Haiku 4.5 $0.00012 $0.00063

Measured yesterday against content hash 508c0abec39f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rocket-link 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-link/SKILL.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resolve any pasted Rocket.Chat link into content + action affordances. Keep it short — open, show, offer.

Transport

  • Prefer MCP when connected: open_url.
  • Otherwise shell out: rocket-cli open <url> --json.
  • Multi-server: --profile <name> (CLI) or ROCKET_CLI_PROFILE (MCP env). The link's host should match the active profile's server; if it points at a different server than the connected one, say so.

Workflow

  1. Pass the URL straight through. open_url params: url (any Rocket.Chat link — message, thread, or channel), count (1-100, default 20, how many messages of context). It accepts message permalinks, thread links, and channel links alike — you do not need to classify the link yourself first.
  2. Branch on the returned entity type:
    • Message → present the message and its surrounding context; offer get_message_context for a wider window.
    • Thread → present the thread (parent + replies); offer get_thread_messages for the full thread if truncated.
    • Channel / room → present recent messages; offer the rocket-catchup workflow for a summary.
  3. Always surface the affordances the tool returns — the ids needed to reply, react, or send. Offer concrete next steps: "reply in this thread?", "react?", "summarize the channel?". Route any send/react/reply through the rocket-send workflow.
  4. Include the permalink of the resolved entity in your reply.

Notes

  • If open_url rejects the input as not-a-link, the user likely pasted plain text or a partial id — fall back: a bare message id can go to get_message_context / get_thread_messages; a room name to the rocket-catchup workflow.
  • Honor refreshing: true if present (cache served while a background sync runs; data may be seconds stale).

Anti-patterns

  • Do NOT try to parse the URL yourself or guess the entity type before calling — open_url does the resolution.
  • Do NOT take any write action (reply/react) from this skill without explicit user confirmation — hand off to rocket-send.
  • Do NOT dump the raw payload; present the content and the next-step affordances.

Read the full file on GitHub · 36 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 · 36 lines · 119 tokens per session scan A 508c0abec39f

Subscribe to this mod's changes

rocket-link is a skill published in the GitHub repository jeanfbrito/rocket-cli (2 stars, last pushed 15d ago), licensed MIT. It adds 119 tokens to every session and 628 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.

Writing and docs
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