Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/singleflo/odoo-assistant-mcpnpx agentmods add skills/singleflo/odoo-assistant-mcp/references_publicWrote 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/skills/singleflo/odoo-assistant-mcp/references_public)<a href="https://agentmods.dev/skills/singleflo/odoo-assistant-mcp/references_public"><img src="https://agentmods.dev/badge/skills/singleflo/odoo-assistant-mcp/references_public.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 5.1 | $0.00018 | $0.04739 |
| Opus 5 | $0.00009 | $0.02370 |
| Sonnet 5 | $0.00004 | $0.00948 |
| Haiku 4.5 | $0.00002 | $0.00474 |
Grade A, and why
odoo 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 — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Odoo — operate an instance like an experienced user
Query, create, and run cross-module workflows on any Odoo 18 instance (Community or Enterprise) via API. Built on one non-negotiable principle: answer what the user would see in the interface, not what a naive query returns.
STATUS — reads, writes, documents, notifications, collaboration. Working now:
odoo_client.py,safety_layer.py,view_first.py,census.py,query.py(all tested against a live instance). Read the current profile generated bycensus.pyfor instance-specific state.
When to Use
Load this skill for anything touching an Odoo instance: counting or listing records (invoices, orders, leads, tasks, tickets, partners), creating or modifying records, running workflows (quotation → order → invoice → payment), inspecting instance structure, or reporting. Also load it when the user asks "how many X" about a business system and Odoo is the system of record.
Do NOT use for Odoo module development (Python/XML source in an addon) — that is ordinary coding work.
The eight rules that are never negotiable
Each one was learned by getting it wrong against a live instance. The examples below use illustrative figures, not customer data.
1. Never query account.move without move_type.
That model holds customer invoices, vendor bills, credit notes AND raw
journal entries in one table. A filterless count can include every document,
while the user sees only the menu's customer invoices. Same for
account.move.line. The safety layer enforces this structurally.
2. Reproduce the menu's filter, not just the action's domain.
An Odoo menu applies domain AND search_default_* together. Reading only
the domain can substantially over-count entries, and the same defect appears
on vanilla Community. Always resolve through the view-first resolver.
3. Never sum amount_total — sum amount_total_signed.
amount_total is in the invoice's own currency, so summing it adds euros to
crowns. Even a small number of foreign-currency invoices can inflate a total
by an order of magnitude — <example amount> versus <example amount> —
with nothing in the output looking wrong. Any field with a
_signed twin: use the twin.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 414 lines · 18 tokens per session scan A fe1941ad29dc
odoo is a skill published in the GitHub repository singleflo/odoo-assistant-mcp (0 stars, last pushed 14d ago), licensed MIT. It adds 18 tokens to every session and 4,739 once invoked, about $0.0001 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 skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.