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 skills/singleflo/odoo-assistant-mcp/referencesnpx skills add singleflo/odoo-assistant-mcp --skill referencesgit clone --depth 1 https://github.com/singleflo/odoo-assistant-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/skills/singleflo/odoo-assistant-mcp/references)<a href="https://agentmods.dev/skills/singleflo/odoo-assistant-mcp/references"><img src="https://agentmods.dev/badge/skills/singleflo/odoo-assistant-mcp/references.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 | $0.00018 | $0.04932 |
| Opus 5 | $0.00009 | $0.02466 |
| Sonnet 5 | $0.00004 | $0.00986 |
| Haiku 4.5 | $0.00002 | $0.00493 |
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 4d 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 — 417 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 1.1.0 — reads, writes, documents, notifications, collaboration. Coherence-reviewed. Working now:
odoo_client.py,safety_layer.py,view_first.py,census.py,query.py(all tested against a live instance). Readreferences/BUILD-STATE.mdfor what is done and what is not.
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 factor in brackets is how far off the answer was.
1. Never query account.move without move_type.
That model holds customer invoices, vendor bills, credit notes AND raw
journal entries in one table. On the reference instance a filterless count
returns 3.613 records while the user sees 373 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 over-counts — measured 24,3× on "Credit Notes" and 218,7× on
"Vendor Refunds", 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. Measured: 8 foreign-currency invoices out of 376 inflate the
total from €1.200.298 to €14.317.483 — 11,9× on the total, 24,6× on the
top customer — with nothing in the output looking wrong. Any field with a
_signed twin: use the twin.
What ships with it
24 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.
- accounting.md 5.7 KB
- api_crm.md 3.0 KB
- BUILD-STATE.md 9.1 KB
- call3cx.md 1.3 KB
- collaboration.md 8.9 KB
- crm_leads.md 9.2 KB
- crm.md 4.4 KB
- deletion.md 4.6 KB
- documents.md 9.5 KB
- evo_manager.md 4.5 KB
- evolution.md 2.8 KB
- fb_leads.md 2.9 KB
- helpdesk.md 5.0 KB
- multi_mail.md 7.6 KB
- odoomon.md 3.4 KB
- partners.md 4.7 KB
- payments.md 8.4 KB
- preinvoice.md 10 KB
- projects.md 8.4 KB
- recipes.md 13 KB
- recording.md 2.7 KB
- sales.md 6.5 KB
- superchat.md 4.3 KB
- writing.md 13 KB
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.
- 4d ago First seen · 417 lines · 18 tokens per session scan A c7a299c49e93
odoo is a skill published in the GitHub repository singleflo/odoo-assistant-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 18 tokens to every session and 4,932 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…