agentmods.dev

converse-cli

converse-cli is a skill for Claude Code, Codex from conversejs/converse.js. It costs 62 tokens per session (2,989 once invoked), scanned A, original, MPL-2.0.

A command-line tool for reading and sending XMPP messages. XMPP, also called Jabber, is a messaging protocol used for private chats and group rooms.

In plain words
What is it for?
Use it to catch up on messages, read conversations, reply, react, wait for replies, and join or post in group rooms.
Why use it?
It lets scripts and developers handle conversations without manually keeping a chat application open or managing the persistent connection.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 3.3krepo +1 changed today A scan 62 tokens original MPL-2.0

Good fit Use it to catch up on messages, read conversations, reply, react, wait for replies, and join or post in group rooms.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/conversejs/converse.js/skill
View source ↗ conversejs/converse.js conversejs.org
About the project

Converse is a browser-based XMPP chat client, meaning it lets people communicate through the Jabber messaging protocol from a web page. It runs as a standalone application or inside another website and supports features such as encrypted messaging, file sharing, notifications, and plugins.

conversejs/converse.js · 3,303 stars · on GitHub · conversejs.org

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.

Any agent
npx skills add conversejs/converse.js --skill skill
Clone the repo
git clone --depth 1 https://github.com/conversejs/converse.js

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for converse-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/conversejs/converse.js/skill/github.svg)](https://agentmods.dev/skills/conversejs/converse.js/skill)
Your own site
<a href="https://agentmods.dev/skills/conversejs/converse.js/skill"><img src="https://agentmods.dev/badge/skills/conversejs/converse.js/skill/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.

agentmods 80×15 button for converse-cli

Your own site · 80×15
<a href="https://agentmods.dev/skills/conversejs/converse.js/skill"><img src="https://agentmods.dev/badge/skills/conversejs/converse.js/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,989 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00062 $0.02989
Opus 5.5 $0.00025 $0.01196
Sonnet 5.5 $0.00012 $0.00598
Haiku 4.5 $0.00006 $0.00299

Measured today against content hash 7c688ce73b9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

converse-cli 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 today.

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.

src/cli/skill/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

converse-cli

converse-cli is a command line client of the Converse daemon, which keeps one XMPP session open for the account. Each command is a short process: it prints its result and exits. Any command starts the daemon if it isn't running, so you never manage it yourself.

The built-in help is the full reference. Run converse-cli --help for the overview, and converse-cli help <command> for a command's arguments, options, exit codes and examples. Check it before using a command or option you haven't used yet. This skill covers how to work with it.

The workflow

  1. Catch up. converse-cli inbox prints every incoming message you haven't seen yet, grouped under a == <jid> (<n> new) line per conversation, and marks them seen. The next inbox shows only what arrived after. If it prints "No new messages." on stderr, there is nothing new. The inbox only counts from your first command on: anything older is history, left out of inbox and the unread counts. On a first run, or when the user says a message is there, use converse-cli conversations and read the recent ones.

  2. Get context. converse-cli read <contact|room> prints the recent messages of one conversation, yours included, oldest first. Use --since 2h for a time window and --before <id> to page further back. read marks nothing as seen.

  3. Reply, and wait for the answer. converse-cli send <contact|room> "text" sends. Add --reply-to <id> to answer a specific message. For long or multi-line text, or text that would need careful shell quoting, pipe it in on stdin instead: printf '%s\n' "$text" | converse-cli send <contact>. converse-cli wait --from <contact> --timeout 300 blocks until a matching message arrives, prints it and exits 0, or exits 2 when the time runs out. Only messages that arrive after wait starts count, so to wait for the answer to a send, start wait first, in the background, then send:

    converse-cli wait --from [email protected] --timeout 300 > answer.txt &
converse-cli send [email protected] "Ready when you are"
wait $!   # the shell builtin, which returns the exit code of the background command
cat answer.txt

Read the full file on GitHub · 220 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. today Changed · +34 lines 7c688ce73b9c
  2. 2d ago First seen · 186 lines · 62 tokens per session scan A 8461a28ed33d

Subscribe to this mod's changes

converse-cli is a skill published in the GitHub repository conversejs/converse.js (3,303 stars, last pushed yesterday), licensed MPL-2.0. It adds 62 tokens to every session and 2,989 once invoked, about $0.0002 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 2026-11-04.

Productivitychatjabberlitomemoxmppxmpp-client
Related

converse-cli compared with skills from other repositories

converse-cli next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
converse-cliconversejs/converse.jsSkill3.3kyesterdayMPL-2.0A62Claude Code, Codex
nvim-contextshabaraba/vibing.nvimSkill13yesterdayMITA63Claude Code
xmpp-enumerationblacklanternsecurity/red-runSkill30214d agoAGPL-3.0A92Claude Code, Codex
Chat Response Generatoreddiebelaval/squireSkill212mo agoMITA14Claude Code, Codex
activity-recordqqqqqf-q/ArkloopSkill37424d agononeA55Claude Code, Codex
ultraworkgracefullight/docusaurus-pluginsSkill231mo agoMITA0Claude Code
workgracefullight/docusaurus-pluginsSkill231mo agoMITA0Claude Code