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.
git clone --depth 1 https://github.com/mart337i/odoo-dev-mcpWrote 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/rules/mart337i/odoo-dev-mcp/odoo-development)<a href="https://agentmods.dev/rules/mart337i/odoo-dev-mcp/odoo-development"><img src="https://agentmods.dev/badge/rules/mart337i/odoo-dev-mcp/odoo-development/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/rules/mart337i/odoo-dev-mcp/odoo-development"><img src="https://agentmods.dev/badge/rules/mart337i/odoo-dev-mcp/odoo-development.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 | $0.04159 | $0.04159 |
| Opus 5.5 | $0.01664 | $0.01664 |
| Sonnet 5.5 | $0.00832 | $0.00832 |
| Haiku 4.5 | $0.00416 | $0.00416 |
Grade A, and why
odoo-development 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 28d 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 — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Odoo Development Guidelines
Module Structure
Naming Conventions
- Module names: Use lowercase with underscores (e.g.,
sale_extended,inventory_custom) - Technical name: Same as module directory name
- Display name: Human-readable with spaces (e.g., "Sales Extended")
- Never use hyphens in module names
Directory Structure
module_name/
├── __init__.py # Import submodules
├── __manifest__.py # Module metadata
├── models/ # Python models
│ ├── __init__.py
│ └── model_name.py
├── views/ # XML views
│ └── model_views.xml
├── security/ # Access rights and rules
│ ├── ir.model.access.csv # Odoo 17-19
│ ├── ir.access.csv # Odoo 20
│ └── module_security.xml
├── data/ # Data files
├── wizard/ # Transient models
├── report/ # Report definitions
├── static/ # Static assets
│ ├── description/
│ │ └── icon.png # 128x128 PNG
│ └── src/
└── i18n/ # Translations
Python Coding Standards
Model Naming
- Model name: Use dot notation (e.g.,
sale.order.line) - Class name: CamelCase matching model (e.g.,
SaleOrderLine) - Inherit: Use
_inheritfor extension,_inheritsfor delegation - Never use underscore in model names (use dots)
Field Naming
- Field names: lowercase_with_underscores
- Boolean fields: Start with
is_,has_, orcan_(e.g.,is_active) - Many2one fields: End with
_id(e.g.,partner_id) - One2many/Many2many fields: End with
_ids(e.g.,line_ids) - Computed fields: Descriptive names, add
computeparameter
Field Types and Parameters
# Char fields
name = fields.Char(string='Name', required=True, index=True)
# Many2one with domain and context
partner_id = fields.Many2one(
'res.partner',
string='Customer',
required=True,
domain="[('customer_rank', '>', 0)]",
context="{'default_customer_rank': 1}"
)
# Selection field
state = fields.Selection([
('draft', 'Draft'),
('confirmed', 'Confirmed'),
('done', 'Done'),
], string='Status', default='draft', required=True)
# Computed field
total_amount = fields.Float(
string='Total',
compute='_compute_total_amount',
store=True
)
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.
- 28d ago Changed · +52 lines · +1,133 tokens per session 369817668b7b
- 2mo ago First seen · 451 lines · 3,026 tokens per session scan A eaea145af701
odoo-development is a cursor rule published in the GitHub repository mart337i/odoo-dev-mcp (24 stars, last pushed 28d ago), licensed MIT. It adds 4,159 tokens to every session, about $0.0166 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 2026-08-30.
Other cursor rules, from other repositories
vibes-plug-backend
Vibes-Plug Backend & Systems Engineering — Node 24, Bun 1.2, Hono, Fastify, Prisma 6, Drizzle, PostgreSQL DDL with RLS, and RFC 9457 errors.
ehs-ims-conventions
EHS IMS app — RBAC, data layer, tRPC, migrations, AI boundaries.
rulesforconvex
description: Convex guidelines globs: alwaysApply: true.
startup-migration-bounded-work
Production djangostartup migrate must be bounded; never run makemigrations in production.
redis_rate_limiting
Complete guide for implementing Redis-based rate limiting with authentication troubleshooting and FastAPI integration.
schema
Scalable and secure schema design patterns for relational databases, NoSQL, and APIs. / TR: İlişkisel veri tabanları, NoSQL ve API'ler için ölçeklenebilir ve güvenli şema tasarım kalıpları.