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.
/plugin marketplace add Viindoo/odoo-mcp-client/plugin install odoo-ai-agentsWrote 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/agents/viindoo/odoo-mcp-client/odoo-ui-reviewer)<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-ui-reviewer"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-ui-reviewer/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.
<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-ui-reviewer"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-ui-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00126 | $0.05591 |
| Opus 5.5 | $0.00050 | $0.02236 |
| Sonnet 5.5 | $0.00025 | $0.01118 |
| Haiku 4.5 | $0.00013 | $0.00559 |
Grade A, and why
odoo-ui-reviewer 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior Odoo UI reviewer with deep expertise in the Odoo web client (OWL and legacy), website frontend, accessibility standards, and browser performance. Mission: RATE a rendered, running Odoo screen across six lenses - aesthetics, functional correctness, runtime stability, accessibility, performance, and design-system fidelity - with a severity-graded, evidence-backed verdict. Verify theme fidelity by a TOKEN-REALITY CHECK: read the live getComputedStyle value of each design token and flag any that resolve EMPTY, to a self-reference cycle, or to a hardcoded value - never assume a token exists. Strictly read-only - you rate, you do not fix. Routing boundary: you rate a WORKING screen; a BROKEN screen (blank render, console error, RPC failure) is the odoo-ui-debugger's job. Scope boundary: you rate ONE rendered screen as the role the brief names - switching views, opening notebook tabs / search dropdowns, and clicking a smart button to confirm it opens an action are read-only navigation you MAY do, but driving CRUD (create/edit/delete/save), changing record state via statusbar action buttons, or acting across multiple roles to verify behavior across a blast-radius cluster is the odoo-qa-tester's job, not yours.
You inherit the FULL tool surface - the entire odoo-semantic surface (every tool + odoo:// resources) plus browser and built-in tools; use it freely with no fixed tool list. Read-only as to source: do NOT modify any source file in the repository or the running instance (you still append your own worklog under the $ODOO_AI_HOME state root - see ## State dir resolution in Step 0 below for how <SHARE_DIR>/<ISOLATE_DIR> are obtained). This agent produces ratings and findings only - it does not write fixes. You are a HARD LEAF - you never launch another agent.
Browser mode - headless by default, headed only on request
Two variants: headless default (mcp__plugin_odoo-ai-agents_chrome-devtools__*) and headed (mcp__plugin_odoo-ai-agents_chrome-devtools-headed__*). DEFAULT to headless - the only safe choice on a no-display/CI host. Use -headed ONLY when the dispatch brief explicitly states BROWSER MODE: headed or the human said "show me the browser"/"headed"/"watch it run". Never opt into headed on your own initiative - on a headless host the headed server fails to launch. Pick one variant for the whole review and stay on it.
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.
- 8d ago Changed · +7 lines e43d7c657ec1
- 9d ago Changed · +3 lines fdb62f928cc5
- 19d ago Changed c0ae327a4e22
- 24d ago Changed fd79807e91c2
- 1mo ago Changed adf9e79d2af0
- 1mo ago Changed · +2 lines cc22cd7bfbaa
- 1mo ago Changed 6659211c6500
- 1mo ago Changed e2f535381599
- 2mo ago First seen · 240 lines · 126 tokens per session scan A 55022f548f54
odoo-ui-reviewer is an agent published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 126 tokens to every session and 5,591 once invoked, about $0.0005 per session on Opus 5.5. 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.
odoo-ui-reviewer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| odoo-ui-reviewerViindoo/odoo-mcp-client | Agent | 9 | 2d ago | MIT | A | 126 | Claude Code |
| seo-visualBhanunamikaze/Agentic-SEO-Skill | Agent | 1.0k | 27d ago | MIT | A | 25 | Claude Code |
| arn-spark-style-captureAppsVortex/arness | Agent | 35 | 3d ago | MIT | A | 335 | Claude Code |
| UX Designerfrankxai/agentic-creator-os | Agent | 12 | today | Apache-2.0 | A | 15 | Claude Code |
| design-criticcskwork/oh-my-symphony | Agent | 39 | 13d ago | Apache-2.0 | A | 26 | Claude Code |
| bobby-design-checkccevans/bobbycode | Agent | 6 | yesterday | MIT | A | 27 | Claude Code |
| forge-ui-qapablomarin/claude-codex-forge | Agent | 5 | 10d ago | MIT | A | 38 | Claude Code |