odoo-guard

odoo-guard is an agent for Claude Code from giggsoinc/raven. It costs 62 tokens per session (1,442 once invoked), scanned A, original, MIT.

An Odoo code checker for Python and XML files in Odoo modules, which are extensions for the Odoo business software platform.

In plain words
What is it for?
It checks record references, database queries, security files, module structure, and loops over Odoo record sets after edits or during a pre-flight review.
Why use it?
It catches patterns that can break when a module moves between databases or violate common Odoo practices. It can block hardcoded database IDs and raw SQL in ORM code.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Part of the raven plugin — 63 skills, 13 commands, 10 agents, 5 hooks, 1 MCP server shipped together

Good fit It checks record references, database queries, security files, module structure, and loops over Odoo record sets after edits or during a pre-flight review.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/giggsoinc/raven/odoo-guard
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.

Clone the repo
git clone --depth 1 https://github.com/giggsoinc/raven

Made for: Claude Code.

Or install raven, the plugin that ships this one along with the rest of its 63 skills, 13 commands, 10 agents, 5 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-guard

README.md
[![agentmods](https://agentmods.dev/badge/agents/giggsoinc/raven/odoo-guard/github.svg)](https://agentmods.dev/agents/giggsoinc/raven/odoo-guard)
Your own site
<a href="https://agentmods.dev/agents/giggsoinc/raven/odoo-guard"><img src="https://agentmods.dev/badge/agents/giggsoinc/raven/odoo-guard/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-guard

Your own site · 80×15
<a href="https://agentmods.dev/agents/giggsoinc/raven/odoo-guard"><img src="https://agentmods.dev/badge/agents/giggsoinc/raven/odoo-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,442 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 $0.00062 $0.01442
Opus 5.5 $0.00025 $0.00577
Sonnet 5.5 $0.00012 $0.00288
Haiku 4.5 $0.00006 $0.00144

Measured 2mo ago against content hash 7dd02c46d60c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

odoo-guard 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 2mo 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.

agents/odoo-guard.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Odoo Guard Agent

Enforces Odoo module structure and ORM best practices. Runs as sub-agent (pre-flight) and on PostEdit.


Rule 1 — No Hardcoded Database IDs (HARD BLOCK)

Scan .py and .xml files for bare integer IDs used as record references:

Patterns in Python:

  • = 1 or = 2 etc. assigned to _id fields or passed to browse()
  • self.env['model'].browse(3)
  • partner_id = 7

Patterns in XML:

  • <field name="group_id" eval="ref()" /> without proper module prefix
  • id="1" or res_id="42" as raw integers

On violation:

❌ ODOO GUARD — Hardcoded database ID
   File:   [filename]:[line]
   Found:  [expression]
   Risk:   ID 3 in dev = different record in production. Always breaks.

   Fix:
   Python: self.env.ref('base.group_user')
           self.env['res.country'].search([('code', '=', 'US')], limit=1)
   XML:    ref="base.group_user"
           <field name="country_id" ref="base.us"/>

Rule 2 — No Raw SQL in ORM Code (HARD BLOCK)

Detect self.env.cr.execute( or self._cr.execute( with inline SQL strings:

❌ self.env.cr.execute(f"SELECT id FROM res_partner WHERE name = '{name}'")
❌ self._cr.execute("DELETE FROM account_move WHERE state = 'draft'")

Exceptions: Reporting queries with complex aggregations — must be in .sql file, loaded as string, using %s parameterisation only.

On violation:

❌ ODOO GUARD — Raw SQL in ORM context
   File:   [filename]:[line]

   Fix:    Use ORM: self.env['res.partner'].search([('name', '=', name)])
           For reporting only: extract to queries/report_name.sql
           Use: self.env.cr.execute(sql, (param1, param2))  — %s only, no f-strings

Rule 3 — Module Structure Validation

When a new Odoo module is created or __manifest__.py is detected, check:

Required files:
  __init__.py                        ← must exist
  __manifest__.py                    ← must have: name, version, depends, license
  security/ir.model.access.csv       ← must exist for any model with _name
  models/__init__.py                 ← if models/ directory exists

Warn if missing:
  security/ directory                → any model is accessible to all users
  tests/ directory                   → no automated tests
  static/description/icon.png        → Odoo app store requirement

Read the full file on GitHub · 182 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. 2mo ago First seen · 182 lines · 62 tokens per session scan A 7dd02c46d60c

Subscribe to this mod's changes

odoo-guard is an agent published in the GitHub repository giggsoinc/raven (5 stars, last pushed 13d ago), licensed MIT. It adds 62 tokens to every session and 1,442 once invoked, about $0.0002 per session on Opus 5.5. 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

review-obsidian-guidelines

Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.

uphy/obsidian-reminder · 63 tokens

debugger

Diagnoses and fixes failed modules using root-cause analysis, not guessing.

TT-Wang/forge · 17 tokens

debugger

Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.

bostonaholic/rpikit · 28 tokens

loom-advisor

Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.

cosmix/loom · 53 tokens

evolve-retrospective

Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.

mickeyyaya/evolve-loop · 51 tokens

type-reconstructor

Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…

marcosd4h/DeepExtractRuntime · 63 tokens