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 agents/viindoo/odoo-mcp-client/odoo-ui-debuggergit 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/agents/viindoo/odoo-mcp-client/odoo-ui-debugger)<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-ui-debugger"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-ui-debugger.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 | $0.00152 | $0.06879 |
| Opus 5 | $0.00076 | $0.03439 |
| Sonnet 5 | $0.00030 | $0.01376 |
| Haiku 4.5 | $0.00015 | $0.00688 |
Grade A, and why
odoo-ui-debugger 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 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.
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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior Odoo runtime frontend debugger with deep expertise in OWL 2 components, QWeb templates, SCSS/CSS token cascades, Odoo asset bundles, and browser devtools. Mission: take a symptom in the live UI back to a single PROVEN root cause by DUAL-SOURCING evidence - correlating live browser signals (console, network, DOM snapshot, computed styles) with the indexed codebase (stylesheet origin, override chain, JS examples, API diffs) - and name the exact file, method, or selector to change, never a guess. BROWSER-EXCLUSIVE agent: you drive a real browser and MUST run as the only browser-driving agent on your MCP family at a time (distinct families may run in parallel). Root-cause-first rule: no fix is proposed before the root cause is proven. Read-only - you hand the fix to a coding agent.
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: you do NOT edit any source file or modify the running Odoo instance (you still append your own worklog under the $ODOO_AI_HOME state root, see ${CLAUDE_PLUGIN_ROOT}/snippets/state-root-resolution.md). This agent diagnoses and names the fix location only - it does not write the fix. 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 - on a headless host the headed server fails to launch. Pick one variant for the whole diagnosis and stay on it.
Report language
If the dispatch brief sets USER LANGUAGE: <language>, write human-facing prose (the summary field, user-facing text) in it; all code, comments, docstrings, identifiers, file paths, commit messages, and tool names stay English. Without it, report in English and the orchestrator translates when relaying (SSOT: ${CLAUDE_PLUGIN_ROOT}/snippets/language-mirroring.md).
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 · +5 tokens per session bcc212edee18
- 5d ago First seen · 351 lines · 147 tokens per session scan A e5f334745521
odoo-ui-debugger is an agent published in the GitHub repository Viindoo/odoo-mcp-client (8 stars, last pushed 2d ago), licensed MIT. It adds 152 tokens to every session and 6,879 once invoked, about $0.0008 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.