A guide for using Zoho’s connected business applications, including CRM, support, email, calendars, accounting, projects, files, and campaigns.

Use it for customer records, support cases, messages, meetings, invoices, projects, files, campaigns, and related business tasks.

It provides a consistent way to search, summarize, update, schedule, and report on business records across Zoho.

zoho — Skill for Claude Code by HybridAIOne

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 HybridAIOne/hybridclaw --skill zoho

Clone the repo

git clone --depth 1 https://github.com/HybridAIOne/hybridclaw

Made for: Claude Code.

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/hybridaione/hybridclaw/zoho/github.svg)](https://agentmods.dev/skills/hybridaione/hybridclaw/zoho)

Your own site

<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/zoho"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/zoho/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/hybridaione/hybridclaw/zoho"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/zoho.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,017 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00072	$0.01017
Opus 5	$0.00036	$0.00508
Sonnet 5	$0.00014	$0.00203
Haiku 4.5	$0.00007	$0.00102

Measured 9d ago against content hash fe2856dd6a3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

zoho 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 9d 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.

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/zoho/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zoho

Use this skill for Zoho work through the configured Zoho MCP server. The MCP server owns the exact Zoho app connections, OAuth scopes, tool schemas, and allowed actions.

Official reference: https://www.zoho.com/mcp/

Required Surface

Use the HybridClaw MCP server configured as zoho.
Prefer visible MCP tools named zoho__<tool> and follow each tool's schema.
If the server is configured under a different name, use that namespace only after confirming it is the Zoho MCP server.
If no Zoho MCP tools are visible, tell the operator to run /mcp list, /mcp status zoho, or /mcp login zoho.
Do not ask for Zoho OAuth tokens, passwords, cookies, or refresh tokens in chat. Do not use browser login or raw Zoho REST calls for normal skill work.

Setup Guidance

For a new connection, use the Zoho MCP endpoint details from Zoho MCP and store the server in HybridClaw as zoho:

/mcp add zoho {"transport":"http","url":"<zoho-mcp-server-url>","auth":"oauth","enabled":true}
/mcp login zoho
/mcp status zoho

Use sse instead of http only when Zoho's connection details specify SSE.

Default Workflow

Identify the Zoho app, object type, record target, and requested action.
Start with a read or search tool to resolve exact IDs and current state.
For read-only requests, summarize the MCP result with record names, dates, statuses, owners, amounts, links, and IDs needed for follow-up actions.
For writes, show the exact target and change, then wait for explicit confirmation before calling the MCP write tool.
Execute multi-app workflows one confirmed write step at a time. Stop after the first failed step and report which steps did and did not run.
Do not claim a write succeeded until the MCP tool returns a success result.

Task Routing

CRM and Bigin: leads, contacts, accounts, deals, stages, owners, notes, meetings, and follow-up tasks.
Desk: ticket lookup, thread summaries, status changes, assignments, and replies.
Mail, Calendar, and Cliq: searches and summaries are read-only; sending mail, scheduling events, or posting messages requires confirmation.
Books, Billing, and Expense: read invoices, bills, expenses, payments, and reports; creating invoices or expenses requires confirmation.
Projects and WorkDrive: task, project, milestone, file, and folder lookup; file moves or task edits require confirmation.
Creator and other configured apps: follow the MCP tool descriptions and prefer low-risk reads before any record mutation.

Read the full file on GitHub · 115 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.

9d ago First seen · 115 lines · 72 tokens per session scan A fe2856dd6a3d

Subscribe to this mod's changes

zoho is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,017 once invoked, about $0.0004 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 2026-09-03.

Productivity Project management RAG and vectors ai enterprise-ai gdpr local-llm proactive-agent

m3-notify

Poll the inbox for new notifications addressed to you.

skynetcmd/m3-memory · 15 tokens

m3-tasks

List your tasks and their state. Pass an argument to filter by state.

skynetcmd/m3-memory · 20 tokens

things-mac

Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Otto to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

elizaOS/eliza · 67 tokens

zoho