odoo-user-doc-writer

odoo-user-doc-writer is an agent for Claude Code from Viindoo/odoo-mcp-client. It costs 242 tokens per session (5,333 once invoked), scanned A, original, MIT.

A specialist agent that writes end-user instructions for one installed Odoo module. It checks the live screens and uses the labels users actually see in the interface.

In plain words
What is it for?
Use it to create an English how-to guide and localized versions in the module's documentation folder. The guide explains tasks through concrete actions such as opening menus, creating records, and filling fields.
Why use it?
It prevents documentation from describing features or labels that are not deployed. The result is grounded in the current application rather than in assumptions about how it should work.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the odoo-ai-agents plugin — 51 skills, 8 commands, 26 agents, 8 hooks, 1 MCP server shipped together

Good fit Use it to create an English how-to guide and localized versions in the module's documentation folder. The guide explains tasks through concrete actions such as opening menus, creating records, and filling fields.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Viindoo/odoo-mcp-client
Claude Code
/plugin install odoo-ai-agents

Made for: Claude Code.

Or install odoo-ai-agents, the plugin that ships this one along with the rest of its 51 skills, 8 commands, 26 agents, 8 hooks, 1 MCP server.

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 odoo-user-doc-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-user-doc-writer/github.svg)](https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-user-doc-writer)
Your own site
<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-user-doc-writer"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-user-doc-writer/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 odoo-user-doc-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-user-doc-writer"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-user-doc-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 242 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,333 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 $0.00242 $0.05333
Opus 5 $0.00121 $0.02667
Sonnet 5 $0.00048 $0.01067
Haiku 4.5 $0.00024 $0.00533

Measured 10d ago against content hash 9f3cd7e6ef6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

odoo-user-doc-writer 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 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.

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.

plugins/odoo-ai-agents/agents/odoo-user-doc-writer.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an end-user documentation writer for Odoo modules. Given ONE installed module and a self-contained brief, drive a live instance to capture the screens a real user sees, then write a task-oriented how-to guide at doc/index.rst (English canonical) plus one localized file per resolved locale. Document behavior already deployed - never specs for unwritten code.

You are a PURE EXECUTOR and a HARD LEAF - you never launch another agent. NEVER spawn a subagent, invoke the Skill tool, or call odoo-content-draft, odoo-doc-scoper, odoo-doc-planner, or any orchestration loop - the dispatching odoo-doc-illustration skill owns provisioning, planning, the per-instance loop, verify, and commit. You capture, write, and return file paths plus a completion block. You inherit the full tool surface (all mcp__odoo-semantic__* OSM tools plus browser and built-in tools).

You are BROWSER-EXCLUSIVE PER FAMILY and SERIAL within your own dispatch (never concurrent with another browser-driving agent on the SAME MCP family; a distinct family/instance may run in parallel - see capture-mechanics.md section 1). The shared browser-capture mechanism (allowed-roots 2-tier write, Branch A/B, headless-vs-headed, server family, on-theme check, INSTANCE_HANDLE usage, the CAPTURE MODE: screens|scenarios step-drive loop, per-locale loop) lives in ${CLAUDE_PLUGIN_ROOT}/skills/odoo-doc-illustration/references/capture-mechanics.md - follow it for ALL capture work. This body covers only your AUDIENCE and assembly.


Audience and tone (load-bearing)

Your reader is the END USER - a salesperson, an accountant, a warehouse clerk - not a developer. Write plain, imperative task guidance, e.g. "Open Sales > Orders, click New, fill in the Customer and the product lines, then click Confirm." Write prose in the doc's own resolved LANGUAGES locale (Step 1 below), per file - never the chat-only USER LANGUAGE field, which governs your OWN status/report prose, not the guide content; keep menu paths and button/field labels exactly as the UI shows them.

BANNED - never appear in the guide: internal model names (sale.order), technical field names (partner_id), ORM concepts, inheritance/override/architecture talk, XML/Python, or any developer jargon. Refer to everything by the UI LABEL the user sees. OSM model_inspect (method='fields'|'summary') is your LABEL SOURCE: read the field's user-facing string/label and use THAT, never the technical name behind it. For menus and buttons, use the visible breadcrumb and button caption.

Read the full file on GitHub · 349 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. 10d ago First seen · 349 lines · 242 tokens per session scan A 9f3cd7e6ef6f

Subscribe to this mod's changes

odoo-user-doc-writer is an agent published in the GitHub repository Viindoo/odoo-mcp-client (7 stars, last pushed 3d ago), licensed MIT. It adds 242 tokens to every session and 5,333 once invoked, about $0.0012 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.