A setup command for Odoo's browser-based development and testing workflow. It installs browser dependencies, configures browser connections for several coding assistants, and can declare and start local Odoo instances.

Use it when preparing browser automation, installing Chromium and related packages, configuring browser tools, or setting up local Odoo instances.

It gathers the setup work needed for visual testing in one repeatable operation. It is designed to be safe to run again without repeating completed setup unnecessarily.

odoo-setup — Command for Claude Code by Viindoo/odoo-mcp-client

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 50 skills, 8 commands, 23 agents, 8 hooks, 3 MCP servers.

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/commands/viindoo/odoo-mcp-client/odoo-setup/github.svg)](https://agentmods.dev/commands/viindoo/odoo-mcp-client/odoo-setup)

Your own site

<a href="https://agentmods.dev/commands/viindoo/odoo-mcp-client/odoo-setup"><img src="https://agentmods.dev/badge/commands/viindoo/odoo-mcp-client/odoo-setup/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/commands/viindoo/odoo-mcp-client/odoo-setup"><img src="https://agentmods.dev/badge/commands/viindoo/odoo-mcp-client/odoo-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,988 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.00016	$0.03988
Opus 5.5	$0.00006	$0.01595
Sonnet 5.5	$0.00003	$0.00798
Haiku 4.5	$0.00002	$0.00399

Measured yesterday against content hash d21772fb7f11, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

odoo-setup scanned grade C with 2 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **Never sudo silently.** ffmpeg, system packages and a native SERVER's `pg_hba.conf` are only *advised*; the

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

writes there). `$CLAUDE_SETTINGS` (`~/.claude/settings.json`) holds *permissions* - steps 30 and 32 write

plugins/odoo-ai-agents/commands/odoo-setup.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/odoo-ai-agents:odoo-setup

Unified, idempotent setup command for the Odoo visual / browser workflow. It drives the numbered step scripts under scripts/setup-steps/, each exposing describe | check | apply. Detail lives in ${CLAUDE_PLUGIN_ROOT}/commands/references/odoo-setup/: preflight.md, instance-cluster.md, steps-core.md, steps-publishing.md (read the one for the goal in hand, once, before its first step). STEPS_DIR = ${CLAUDE_PLUGIN_ROOT}/scripts/setup-steps.

Hard rules

Two different Claude files, never crossed. ~/.claude.json is the MCP server registry (step 10 never writes there). $CLAUDE_SETTINGS (~/.claude/settings.json) holds permissions - steps 30 and 32 write there. Do not edit either file by hand with Edit/Write.
Never sudo silently. ffmpeg, system packages and a native SERVER's pg_hba.conf are only advised; the user runs any privileged change themselves.
Idempotent. Always run a step's check before its apply. Re-running the whole command is a no-op when everything is configured, and re-running a goal with a changed answer updates what that answer owns (an instance's addons path, a venv's packages, a channel's privacy) - never a second copy, never a silent skip.
Spawn a HAIKU subagent ONLY for read-only local filesystem scans (repo -> local path mapping in AI-3, venv -> series mapping in AI-4). Every file mutation goes through the deterministic *.sh step scripts (40/45/46/47/48/50/60), NEVER through a subagent. The HAIKU subagent reads; the shell scripts write.
If a step script reports the shared lib missing (scripts/lib/config_merge.py, discover_odoo.sh, or instances_io.py), the plugin is partially installed: tell the user to reinstall odoo-ai-agents@viindoo-plugins fully, restart the session and re-run; never hand-write the browser MCP or permission config in its place. If the plugin is installed, do not add the browser servers by hand to ~/.claude.json. The preflight scripts (00-osm-gate.sh, 05-prereq-check.sh) are detect-only; the Gate #1 tool call stays authoritative without 00-osm-gate.sh.

Read the full file on GitHub · 174 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.

yesterday Changed d21772fb7f11
7d ago Changed · -599 lines c73a6de5cf46
9d ago Changed · +8 lines 331b82907974
16d ago Changed · +109 lines 09e07c2d4358
17d ago Changed · +54 lines 549dc832a1ae
19d ago Changed · -8 lines 82f5c2e84233
20d ago Changed · -92 lines 6d15e71c4f97
21d ago Changed · +17 lines 664e2d0bac8d
1mo ago Changed · +29 lines · -49 tokens per session 467caf59fdd5
1mo ago First seen · 656 lines · 65 tokens per session scan C ce90d0848a16

Subscribe to this mod's changes

odoo-setup is a command published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 3,988 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automation

odoo-setup next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
odoo-setupViindoo/odoo-mcp-client	Command	9	2d ago	MIT	C	16	Claude Code
auto-browsemarcusquinn/aidevops	Command	444	today	MIT	A	18	Claude Code
webapp-testinghamr0/agentic-toolkit	Command	23	10d ago	Apache-2.0	A	35	Claude Code
verify-prdesplega-ai/qa-use	Command	29	1mo ago	MIT	A	0	Claude Code
gh-issue-use-cypressskyfox675/agents-skills	Command	11	today	MIT	A	49	Claude Code
readinesscygaco/master-console	Command	128	20d ago	AGPL-3.0	A	51	Claude Code
can-i-useivklgn/ai-kit	Command	12	1mo ago	MIT	A	13	Claude Code

odoo-setup