agentmods.dev

odoo-modules-upgrade

odoo-modules-upgrade is a skill for Claude Code from Viindoo/odoo-mcp-client. It costs 22 tokens per session (3,531 once invoked), scanned C, original, MIT.

A coordinator for upgrading a group of custom Odoo modules from one major Odoo version to another. It organizes code changes and can remove modules whose functionality has been absorbed into the newer Odoo core, without handling data migration.

In plain words
What is it for?
Use it to plan and coordinate module rewrites, merges, splits, removals, testing, and pull-request preparation for a major Odoo upgrade.
Why use it?
It turns a large version upgrade into an ordered, reviewable code change and makes dependencies between modules easier to manage.

Skill for Claude Code

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

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 — 50 skills, 8 commands, 23 agents, 8 hooks, 3 MCP servers shipped together

not rated 9repo changed 7d ago C scan 22 tokens original MIT

Good fit Use it to plan and coordinate module rewrites, merges, splits, removals, testing, and pull-request preparation for a major Odoo upgrade.

Compare 6 skills from other repositories ↓
View source ↗ Viindoo/odoo-mcp-client odoo-semantic.viindoo.com
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 50 skills, 8 commands, 23 agents, 8 hooks, 3 MCP servers.

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-modules-upgrade

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-modules-upgrade"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-modules-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,531 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 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 $0.00022 $0.03531
Opus 5.5 $0.00009 $0.01412
Sonnet 5.5 $0.00004 $0.00706
Haiku 4.5 $0.00002 $0.00353

Measured 7d ago against content hash 5492b80e4019, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

odoo-modules-upgrade scanned grade C 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 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

**Orphan sweep (every run, BEFORE P0).** `find <ISOLATE_DIR>/modules-upgrade/ -mindepth 1 -maxdepth 1 -type d -mmin +43200 -exec rm -rf {} +` (${CLAUDE_PLUGIN_ROOT}/snippets/visual-evidence-lifecycle-contract.md § Clause
plugins/odoo-ai-agents/skills/odoo-modules-upgrade/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Module-upgrade conductor. Move a whole cluster across MAJOR series in ONE PR, reviewed in dependency order (leaves first). Delegate every diff read and custom-vs-core comparison to subagents; read their structured output, enforce gates, run Plan Mode, open the PR, stop for human confirm. Per module decide what target core now ABSORBS: wholly absorbed -> DELETE + reason in the commit message; else KEEP / REWRITE / MERGE / SPLIT.

The upgrade is a CODE upgrade: Hard rule 4 and ${CLAUDE_PLUGIN_ROOT}/snippets/upg-conventions.md § Convention 0. A database upgrade between series needs a dedicated upgrade tool and repository; not this plugin - never raise, plan or offer it. Human sign-off before the PR merges.

Hard rules

  1. Principal-checkout-lock. NEVER check out or switch the principal checkout off its branch; materialize any branch through git-toolkit:git-ops (add a worktree).
  2. Plan Mode before any delete or code write (${CLAUDE_PLUGIN_ROOT}/snippets/planning-gate-contract.md).
  3. ONE PR per cluster, reviewed in dep order. No cluster-squash; per-module consolidation to one commit IS allowed (references/upg-phase-detail-p4-p7.md § Commit consolidation).
  4. Code upgrade only (Convention 0), two module classes. This skill NEVER writes a migration script, never bumps a version, never touches an existing database and never raises existing data. Every module the PR touches is classified at P0 and shown at P3:
    • upgraded - installable False at <work-base>, True after the PR: its migrations/ directory is deleted;
    • already installable - installable True at <work-base> (an absent key counts as True) and changed in the same PR: its existing migrations/ directories are never edited. Convention 0 settles every question about existing data, so none is asked (${CLAUDE_PLUGIN_ROOT}/snippets/read-before-act.md § 2).
  5. DELETE-absorbed = directory removal + dep cleanup, never installable: False; the commit message names the replacing core feature. Gates: (a) the signal #5 behavioral-equivalence proof in absorption/<module>.md; (b) a per-DELETE human acknowledgment at P3, SEPARATE from the plan approval. OBSOLETE: state that the module is obsolete at <tgt>; never invent an absorbing_core_feature.
  6. Acceptance (P5.8) and i18n reconcile (P5.7, every surviving module) are mandatory, narrow escape only; not DONE without the ACCEPTED verdict / per-module i18n result or a recorded escape.

Read the full file on GitHub · 106 lines

Files

What ships with it

5 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. 7d ago Changed · -150 lines 5492b80e4019
  2. 17d ago Changed · -208 lines · -7 tokens per session 46cf9804f921
  3. 19d ago Changed c4c1a88a8680
  4. 20d ago Changed · -87 lines · -4 tokens per session 8e794477659f
  5. 21d ago Changed · -1 lines 0cfac70d76b0
  6. 24d ago Changed · -2 lines c27c89e1c6e2
  7. 29d ago Changed 3779b7a5267c
  8. 1mo ago Changed 97c893ef0318
  9. 1mo ago Changed · -11 lines · -217 tokens per session 7ecf6e4cb815
  10. 1mo ago First seen · 565 lines · 250 tokens per session scan C a2ce0d6e0a34

Subscribe to this mod's changes

odoo-modules-upgrade is a skill published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 3,531 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

PlanningProject management
Related

odoo-modules-upgrade compared with skills from other repositories

odoo-modules-upgrade next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
odoo-modules-upgradeViindoo/odoo-mcp-clientSkill92d agoMITC22Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100ktodayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k3d agoMITA200Claude Code, Codex
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill315k6d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code