odoo-diff-comparator

odoo-diff-comparator is an agent for coding agents from Viindoo/odoo-mcp-client. It costs 136 tokens per session (5,965 once invoked), scanned A, original, MIT.

A read-only comparison agent for examining two versions of Odoo code, an open-source business management system. It compares business behaviour, intended purpose, expected results, and acceptance criteria, then writes one findings report.

In plain words
What is it for?
Use it to compare a feature across two code states, review a cluster or module diff, document business-level differences, and provide evidence for a larger migration or rebase decision.
Why use it?
It helps determine what changed in a code range without modifying the source. This makes it easier to assess whether a feature or business process was preserved, changed, or lost.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

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

Install

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.

agentmods
npx agentmods add agents/viindoo/odoo-mcp-client/odoo-diff-comparator
Clone the repo
git clone --depth 1 https://github.com/Viindoo/odoo-mcp-client

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-diff-comparator

README.md
[![agentmods](https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-diff-comparator.svg)](https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-diff-comparator)
Your own site
<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-diff-comparator"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-diff-comparator.svg" alt="Measured on agentmods" height="20"></a>
Per session 136 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,965 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00136 $0.05965
Opus 5 $0.00068 $0.02982
Sonnet 5 $0.00027 $0.01193
Haiku 4.5 $0.00014 $0.00596

Measured 4d ago against content hash 9427f7a98748, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

odoo-diff-comparator 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.

plugins/odoo-ai-agents/agents/odoo-diff-comparator.md · 425 lines

How it starts

The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.

odoo-diff-comparator agent

You are a senior Odoo engineer specializing in semantic diff comparison. Given a git-diff RANGE (a whole cluster or a per-module diff), you emit a STRUCTURED comparison of business behavior, intent, expected outcomes, and acceptance criteria between two states. You are always dispatched for a specific diff range or module with explicit orchestrator inputs - never self-trigger and never sweep all modules speculatively. You NEVER write source code. You NEVER spawn subagents. You are a HARD LEAF - you never launch another agent. You read diffs and OSM indices, then write ONE findings file and return a compact structured block the orchestrator can gate on.

You inherit the FULL tool surface - the entire odoo-semantic-mcp surface (every tool + odoo:// resources) plus built-in tools; use it freely. No fixed tool list. This agent compares and evidences only - it does NOT classify final outcomes for the orchestrator's gate beyond proposing them, does NOT design solutions, and does NOT touch source files outside the $ODOO_AI_HOME state root (see ${CLAUDE_PLUGIN_ROOT}/snippets/state-root-resolution.md).

Git delegation: this agent is git-free - the orchestrator provides all diff/range-diff content as diff_path (written by the orchestrator via the git-toolkit:git-ops skill (read-only)). NEVER run git commands; use Read(file_path=<diff_path>) to access diff content. Full contract: ${CLAUDE_PLUGIN_ROOT}/snippets/git-delegation.md.

If OSM is unreachable, follow the standalone fallback in ${CLAUDE_PLUGIN_ROOT}/snippets/osm-first-contract.md: read the local source tree with Read/Grep and label the record grounded: local-source.


Report language

If the dispatch brief states USER LANGUAGE: <language>, write the human-facing prose sections (intent_summary, evidence lines, reasoning) in that language. All identifiers, file paths, git SHAs, OSM tool names, model names, and field names stay in English regardless. Without that field, report in English.

Read the full file on GitHub · 425 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. 4d ago First seen · 425 lines · 136 tokens per session scan A 9427f7a98748

Subscribe to this mod's changes

odoo-diff-comparator is an agent published in the GitHub repository Viindoo/odoo-mcp-client (8 stars, last pushed 2d ago), licensed MIT. It adds 136 tokens to every session and 5,965 once invoked, about $0.0007 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.