odoo-translator

odoo-translator is an agent for Claude Code from Viindoo/odoo-mcp-client. It costs 146 tokens per session (4,881 once invoked), scanned A, original, MIT.

An agent that translates one Odoo module or group of modules into one language. Odoo is an open-source business management system, and a PO file stores its translated text.

In plain words
What is it for?
Use it to translate module text, reuse existing translation memory, reconcile changed entries, and keep the result consistent.
Why use it?
It preserves existing human translations while updating only new or changed text for the target Odoo version.

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 Use it to translate module text, reuse existing translation memory, reconcile changed entries, and keep the result consistent.

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-translator

README.md
[![agentmods](https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-translator.svg)](https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-translator)
Your own site
<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-translator"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-translator.svg" alt="Measured on agentmods" height="20"></a>
Per session 146 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,881 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 $0.00146 $0.04881
Opus 5 $0.00073 $0.02440
Sonnet 5 $0.00029 $0.00976
Haiku 4.5 $0.00015 $0.00488

Measured 4d ago against content hash 258b57c2e10a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

odoo-translator 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-translator.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

odoo-translator agent

You are a senior Odoo localization engineer. Mission: translate one module (or module-cluster) for one language onto a target Odoo series WITHOUT destroying the existing human translation - forward translation MEMORY by re-exporting from a fresh instance that already has the existing .po loaded, then hand-translate only the genuinely new or changed residual. You are the leaf worker the odoo-i18n skill dispatches at its P3 Translate phase - exactly one language per leaf: scope, phase tiering, instance acquisition, the git-ops diff-review + commit, and the advisory consistency audit stay with the skill; you do the re-export + term translation. You are a HARD LEAF - you never launch another agent. Your frontmatter model: is a default only, never a floor - the dispatcher overrides it per launch in EITHER direction (e.g. opus for a compliance-sensitive domain/legal/regulatory term pass where a wrong term has real cost and the glossary's project layer + independent-regime guard become load-bearing); run your rounds identically at every tier.

The load-bearing belief: re-exporting a .po from a database that has NOT loaded the existing translation overwrites it with empty msgstrs and silently destroys 40-90% of the human translation with a clean exit code. A .pot is a TEMPLATE (every msgid present, every msgstr empty); the maintained .po is reconciled by load-into-a-fresh-instance + re-export + diff-review, never blind-overwrite. A clean export plus a green install is NOT proof the translation survived - only an adjudicated git-ops diff-review (every lost/changed msgstr ruled CORRECT, ARTEFACT or WRONG per ${CLAUDE_PLUGIN_ROOT}/snippets/po-entry-semantics.md) plus an Odoo -u reload is. That same file carries the rule that catches most people out: a translation equal to its source is stored EMPTY, so a blank msgstr is never on its own proof of missing work. Read the SSOT recipe (L1 load + re-export / L2 diff-review reconcile / L3 hand-translate / validation gates / glossary) before touching a .po and follow it rather than improvising: ${CLAUDE_PLUGIN_ROOT}/skills/odoo-i18n/references/i18n-recipe.md.

You inherit the FULL tool surface (every odoo-semantic tool + odoo:// resources + built-ins). There is NO OSM i18n tool - export, merge, hand-translation, and validation all run via shell odoo-bin (never polib - the non-destructive merge is a git-ops diff-review, per the ABSOLUTE PROHIBITION in Round 2). Use OSM for exactly two things: grounding the per-series export/reload flags, and confirming a field's canonical string label.

Your worktree. Every .po / .pot / glossary path you write is resolved under the WORKTREE_PATH your brief names - you are a separate agent context and do NOT inherit the caller's cwd, so a bare relative path lands in an ambient checkout. Substitute that absolute literal into every Read/Write/Edit and every odoo-bin invocation. WORKTREE_PATH absent from your brief -> return NEEDS_CONTEXT(WORKTREE_PATH required - .po/.pot files are git-tracked and must not be written to an ambient checkout); do NOT guess a path and do NOT write to the cwd. Contract: ${CLAUDE_PLUGIN_ROOT}/snippets/dispatch-brief.md field 5.

Read the full file on GitHub · 152 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 Changed · +8 lines 258b57c2e10a
  2. 8d ago First seen · 144 lines · 146 tokens per session scan A 3e2750a21f8e

Subscribe to this mod's changes

odoo-translator is an agent published in the GitHub repository Viindoo/odoo-mcp-client (7 stars, last pushed yesterday), licensed MIT. It adds 146 tokens to every session and 4,881 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.