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.
npx agentmods add commands/viindoo/odoo-mcp-client/odoo-setupgit clone --depth 1 https://github.com/Viindoo/odoo-mcp-clientWrote 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.
[](https://agentmods.dev/commands/viindoo/odoo-mcp-client/odoo-setup)<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="Measured on agentmods" height="20"></a>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 | $0.00063 | $0.09645 |
| Opus 5 | $0.00032 | $0.04823 |
| Sonnet 5 | $0.00013 | $0.01929 |
| Haiku 4.5 | $0.00006 | $0.00965 |
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 5d 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.
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 Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| **Gemini CLI** | Bundled `gemini-extension.json` (installed via `gemini extensions install <your-clone>/plugins/odoo-ai-agents` or `gemini extensions link ...` for live dev). **Note:** Gemini cannot install an extensio How it starts
The opening of the file, as written. The whole thing — 573 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/odoo-ai-agents:odoo-setup
Unified, idempotent, extensible setup command for the Odoo visual / browser
workflow. It drives a registry of numbered step scripts under
scripts/setup-steps/, each exposing a describe | check | apply contract.
Adding a new capability later is a drop-in: add one more numbered script - you
do NOT edit this command.
What it sets up:
- Browser MCP - only ONE family is EAGER: the plugin's bundled
.mcp.jsonships the headlesschrome-devtools(Claude auto-loads it; the Codex/Gemini bundle manifests mirror it). The other five families (chrome-devtools-headed,playwright[-headed],pagecast[-headed]) are OPT-IN so a plain session does not launch browser processes it does not need. This command wires them on demand:10-browser-mcp(Codex/Gemini config) and12-browser-mcp-optin(Claude, user scope) register the opt-in families from the pinned SSOT. - Browser deps - Node >= 20 check; pre-installs the 3 pinned browser MCP packages ON DISK (npm cache warm, never launched - disk cost, zero RAM cost); Playwright Chromium install; ffmpeg check. This is INSTALL-only and strictly separate from step 12's REGISTER: pre-installing here means a later real spawn (once step 12 wires it) has no download latency, without ever starting a process or paying idle RAM for it.
- Permissions - auto-allows the browser MCP tools in Claude permissions, plus the narrow set of state-root Bash/Read/Edit rules the planning pipeline needs.
- Instance profile - discovers local Odoo repos via OSM-grounded propose-then-confirm,
writes the machine-global
$ODOO_AI_HOME/instances.toml(resolvable from any cwd by any agent on this host; see${CLAUDE_PLUGIN_ROOT}/snippets/state-root-resolution.mdfor the full Tier-1/SHARE/ISOLATE convention). - DB local auth - makes a LOCAL cluster accept the declared PostgreSQL role without a stored
password, so every build can open Odoo's own connection; reverted with
48-db-local-auth.sh revert. - Instance spin-up - launches a declared Odoo instance and waits for HTTP 200.
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.
- 5d ago First seen · 573 lines · 63 tokens per session scan C 8ebd58d5400b
odoo-setup is a command published in the GitHub repository Viindoo/odoo-mcp-client (8 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 9,645 once invoked, about $0.0003 per session on Opus 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.
Other commands, from other repositories
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
ccboard-web
Launch ccboard web interface.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
gh-issue-use-cypress
Like /gh-issue-use-browser, but pinned to the Cypress MCP — use when your project runs the Cypress MCP for browser automation. Example — /gh-issue-use-cypress "Composer > Save" saving toasts failure but the record persists.
can-i-use
Check browser support for web platform features against the project's browser targets.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.