odoo-intake

odoo-intake is a skill for Claude Code from Viindoo/odoo-mcp-client. It costs 248 tokens per session (20,542 once invoked), scanned B, original, MIT.

A starting point for any Odoo or ERP request, including strategy, sales, development, testing, and support work. It clarifies vague requests, sends clear requests to the right specialist, and requires a plan before execution.

In plain words
What is it for?
Use it to route questions, feature requests, investigations, and delivery tasks to the appropriate Odoo specialist.
Why use it?
It prevents broad or unclear Odoo requests from being handled by the wrong workflow or acted on without agreement about the work.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter; mentions subagents; names the ExitPlanMode tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the odoo-ai-agents plugin — 51 skills, 8 commands, 26 agents, 8 hooks, 1 MCP server shipped together

Good fit Use it to route questions, feature requests, investigations, and delivery tasks to the appropriate Odoo specialist.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add Viindoo/odoo-mcp-client
Claude Code
/plugin install odoo-ai-agents

Made for: Claude Code.

Or install odoo-ai-agents, the plugin that ships this one along with the rest of its 51 skills, 8 commands, 26 agents, 8 hooks, 1 MCP server.

Wrote 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.

agentmods badge for odoo-intake

README.md
[![agentmods](https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-intake/github.svg)](https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-intake)
Your own site
<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-intake"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-intake/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.

agentmods 80×15 button for odoo-intake

Your own site · 80×15
<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-intake"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-intake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 248 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 20,542 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00248 $0.20542
Opus 5 $0.00124 $0.10271
Sonnet 5 $0.00050 $0.04108
Haiku 4.5 $0.00025 $0.02054

Measured 6d ago against content hash 9c37859c35e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

odoo-intake scanned grade B with 1 finding 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 6d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| 56 | "audit security", "is this code safe", "SQL injection risk", "XSS in QWeb", "check access control", "sudo bypass", "hardcoded secret", "okay to ship?", VI: "kiểm tra bảo mật code", "có bị SQL injection không", "re
plugins/odoo-ai-agents/skills/odoo-intake/SKILL.md · 461 lines

How it starts

The opening of the file, as written. The whole thing — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Odoo Intake - Universal Front Door (Brainstorm + Route + Soft-Plan-Gate)

Your role - orchestrator, not implementer (THIS IS MANDATARY)

You are the main agent and orchestrator: get work done by invoking the right skill with the Skill tool, not by doing it yourself. Skills launch the specialist subagents that do the actual work; only when no skill fits do you launch an agent directly. Route, sequence, gate, and decide - own the orchestration, delegate the execution.

IMPORTANT: NEVER read Pull Requests, Github Issues, web pages, codebase, or any Internet URL yourself. If no skill can do it for you, launch haiku or sonnet agents until you have the information you need.

Role

Domain-agnostic front door for all 9 README persona buckets: CEO/strategist, consultant, sales AE, pre-sales, marketer, developer, QA, customer-success, and anyone in between.

The user is often NOT a developer and may not know skill names - they just describe the outcome they need. This skill's job is to:

  1. Detect whether the intent is clear (fast-path) or vague (brainstorm).
  2. Route via 4-tier logic to the single best specialist skill or workflow.
  3. Gate every execution with a Proposed Plan before any work runs.
  4. Never do the routed work itself - it MAY produce plan/design artifacts during its turn, but the routed execution (production code, proposals) happens after approval.

Language - mirror the user in every chat output

The user prompts in THEIR language; every chat-facing output of this skill - brainstorm framings, option menus, plan proposals, RUN-DAG summaries, gates, clarifying questions - is written in that language, mirroring their prompts. The templates in this file are instructions to you, not text to paste: keep their STRUCTURE (lines, tables, reply keywords approve / refine: / skip / cancel verbatim) but translate every label and sentence. Keep code, identifiers, module/model names, file paths, skill names, and URLs verbatim; explain unavoidable technical terms in plain words in the user's language on first use. Full contract: ${CLAUDE_PLUGIN_ROOT}/snippets/language-mirroring.md.

Read the full file on GitHub · 461 lines

Files

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.

Changes

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.

  1. 6d ago First seen · 461 lines · 248 tokens per session scan B 9c37859c35e7

Subscribe to this mod's changes

odoo-intake is a skill published in the GitHub repository Viindoo/odoo-mcp-client (7 stars, last pushed 3d ago), licensed MIT. It adds 248 tokens to every session and 20,542 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories