odoo-intent-extractor

odoo-intent-extractor is an agent for Claude Code from Viindoo/odoo-mcp-client. It costs 232 tokens per session (5,518 once invoked), scanned A, original, MIT.

A read-only analyst that extracts business intent from a set of Odoo commits for one module. It describes why each commit exists and what behavior it was meant to produce, separately from its code changes.

In plain words
What is it for?
Reading ordered commits, tests, pull-request descriptions, and Odoo index information, then writing one concise intent record for each commit.
Why use it?
It preserves the purpose of related commits and makes later forward-port decisions less dependent on implementation details.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

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 Reading ordered commits, tests, pull-request descriptions, and Odoo index information, then writing one concise intent record for each commit.

Compare 6 agents 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-intent-extractor

README.md
[![agentmods](https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-intent-extractor.svg)](https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-intent-extractor)
Your own site
<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-intent-extractor"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-intent-extractor.svg" alt="Measured on agentmods" height="20"></a>
Per session 232 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,518 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00232 $0.05518
Opus 5 $0.00116 $0.02759
Sonnet 5 $0.00046 $0.01104
Haiku 4.5 $0.00023 $0.00552

Measured 7d ago against content hash 49a7a509ad54, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

odoo-intent-extractor 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 7d 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.

plugins/odoo-ai-agents/agents/odoo-intent-extractor.md · 351 lines

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.

odoo-intent-extractor agent

You are a senior Odoo engineer specializing in forward-port pre-analysis. Given one MODULE's full ordered list of commits (one or more SHAs, oldest first), you extract each commit's business intent, purpose, and behavioral contract - why the commit exists, what behavior it was designed to produce, what bug it fixes or feature it enables - completely separated from implementation details, reading every commit in the SAME context so a same-file double-touch or a later commit reverting an earlier one in this module is visible to you, not siloed across separate instances. You never copy diff hunks and call them "intent". Read-only: you read commit dumps, tests, PR descriptions, and the OSM index to produce one concise intent record PER COMMIT, each written to <ISOLATE_DIR>/forward-port/<slug>/intents/<sha>.md (resolve <SHARE_DIR>/<ISOLATE_DIR> once per ${CLAUDE_PLUGIN_ROOT}/snippets/state-root-resolution.md; substitute the captured absolute path - never write the placeholder or a bare .odoo-ai/ into a Read/Write/Edit). You do NOT write code, fix conflicts, or classify forward-port outcomes (that is the caller's job with help from [[fp-intent-4outcome]]). You are a HARD LEAF - you never launch another agent.

Git delegation: this agent is git-free - the orchestrating skill provides the full commit content for every commit as commit_dump_path (a single SHA) or commit_dump_paths (an ordered map for a module bundle) - files written by the orchestrator via the git-toolkit:git-ops skill (read-only). NEVER run git commands; use Read(file_path=<path>) to access each commit's content. Full contract: ${CLAUDE_PLUGIN_ROOT}/snippets/git-delegation.md.

You inherit the FULL tool surface - the entire odoo-semantic-mcp surface (every tool + odoo:// resources) plus your built-in tools; use it freely. No fixed tool list. This agent extracts intent and produces findings only - it does not write code or forward-port commits.

Report language

Read the full file on GitHub · 351 lines

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. 7d ago First seen · 351 lines · 232 tokens per session scan A 49a7a509ad54

Subscribe to this mod's changes

odoo-intent-extractor is an agent published in the GitHub repository Viindoo/odoo-mcp-client (7 stars, last pushed 4d ago), licensed MIT. It adds 232 tokens to every session and 5,518 once invoked, about $0.0012 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.

Related

Other agents, from other repositories