What is conversations?

A way to work with conversation threads: groups of messages exchanged with one contact across channels such as WhatsApp and email. It can read threads, retrieve their messages, mark them as read, and send replies.

Use it for shared inboxes, helpdesk synchronization, customer-history views, and agents that need previous messages before answering.

It keeps related messages together instead of making you reconstruct a conversation from a flat message log. It also helps replies use the correct sender and thread.

conversations — Skill for Claude Code by zavudev

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 zavudev/zavu-skills --skill conversations

Clone the repo

git clone --depth 1 https://github.com/zavudev/zavu-skills

Made for: Claude Code.

Or install zavu-skills, the plugin that ships this one along with the rest of its 14 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zavudev/zavu-skills/conversations/github.svg)](https://agentmods.dev/skills/zavudev/zavu-skills/conversations)

Your own site

<a href="https://agentmods.dev/skills/zavudev/zavu-skills/conversations"><img src="https://agentmods.dev/badge/skills/zavudev/zavu-skills/conversations/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zavudev/zavu-skills/conversations"><img src="https://agentmods.dev/badge/skills/zavudev/zavu-skills/conversations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,382 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00026	$0.02382
Opus 5	$0.00013	$0.01191
Sonnet 5	$0.00005	$0.00476
Haiku 4.5	$0.00003	$0.00238

Measured 10d ago against content hash 4b7923d6e795, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

conversations scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl "https://api.zavu.dev/v1/conversations?limit=25" \

skills/conversations/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conversations

When to Use

Use this skill when building anything that reads an inbox: a shared inbox UI, a helpdesk sync, a "show me this customer's history" tool, or an agent that needs the thread before it answers.

GET /v1/messages returns a flat log with no thread to hang it on. Conversations are the thread.

What a conversation is

One thread with one contact, spanning every channel. A contact who writes on WhatsApp and later by email stays in the same conversation, and channels lists what it has carried.

Field	Meaning
`id`	Thread ID. Same value as `conversationId` on messages and webhooks.
`contactIdentifier`	The key the thread is filed under. Not always a phone number — see below.
`contactId`	The contact, when resolved. Absent on group threads.
`channels`	Every channel this thread has carried.
`lastMessage`	Denormalized preview (`id`, `text`, `channel`, `direction`, `at`) so a thread list needs no extra fetch.
`senderId`	Sender that last handled the thread. Pass it back as `Zavu-Sender` when replying.
`unreadCount`	Inbound messages not yet marked read.
`whatsapp`	`bsuid` + `username`, when the contact adopted a WhatsApp username.
`group`	Present on group chats: `id`, `subject`, `participantCount`.

contactIdentifier is not a phone number

It holds whichever identifier keys the thread: an E.164 phone, a WhatsApp BSUID (US.13491208655302741918), a numeric chat ID (Telegram/Instagram/Messenger), or a group JID (<id>@g.us). Parsing it as a phone number breaks on every non-SMS channel. Use channels and group to decide how to render it.

Endpoints

These are not in the generated SDKs yet. Use REST.

Method	Path	Purpose
`GET`	`/v1/conversations`	List threads, most recently active first.
`GET`	`/v1/conversations/{conversationId}`	One thread.
`GET`	`/v1/conversations/{conversationId}/messages`	Messages in the thread, newest first.
`POST`	`/v1/conversations/{conversationId}/read`	Reset `unreadCount` to zero.

Read the full file on GitHub · 200 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.

10d ago First seen · 200 lines · 26 tokens per session scan A 4b7923d6e795

Subscribe to this mod's changes

conversations is a skill published in the GitHub repository zavudev/zavu-skills (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 2,382 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Productivity

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…

nexu-io/open-design · 117 tokens

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…

danielmiessler/LifeOS · 196 tokens

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.

pinchtab/pinchtab · 52 tokens

conversations