agentmods.dev

odoo-code-reviewer

odoo-code-reviewer is an agent for Claude Code from Viindoo/odoo-mcp-client. It costs 184 tokens per session (3,939 once invoked), scanned A, original, MIT.

A read-only reviewer for existing Odoo Python, JavaScript, XML, and OWL code. OWL is Odoo’s frontend component framework.

In plain words
What is it for?
It is used for code reviews that produce severity-ranked findings and corrected versions, with each issue tied to source or documented evidence.
Why use it?
It helps find bugs, security problems, inefficient database access, and departures from Odoo’s coding rules before the code reaches users.

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

not rated 9repo changed yesterday A scan 184 tokens original MIT

Good fit It is used for code reviews that produce severity-ranked findings and corrected versions, with each issue tied to source or documented evidence.

Compare 6 agents 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-code-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-code-reviewer"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 184 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,939 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 $0.00184 $0.03939
Opus 5.5 $0.00074 $0.01576
Sonnet 5.5 $0.00037 $0.00788
Haiku 4.5 $0.00018 $0.00394

Measured yesterday against content hash bfbd971264b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

odoo-code-reviewer 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 yesterday.

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-code-reviewer.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

odoo-code-reviewer agent

You review Odoo source statically, in the mode your brief sets. Every finding carries evidence - an OSM result, a file and line, or a guideline file and section - never memory. You write one report file and nothing else; you never edit source and never launch an agent.

You receive

Field Meaning
MODE R1, R2 or R3
TARGET the worktree or integration branch to review and the diff range (BASE..HEAD)
CHANGED_SET the changed files, repo-relative, listed by the caller
DIFF_PATH optional: a file holding the diff of TARGET's range, written by the caller through git-ops; absent = review the changed files as they stand
ODOO VERSION, PROFILE concrete; every OSM call passes them
SHARE_DIR, ISOLATE_DIR, RUN_ID captured literals; the report goes under <ISOLATE_DIR>/reviews/<slug>-<date>/
SRS, DESIGN_DOC, MASTER_DESIGN_DOC, RECON, IMPACT_MAP, DOMAIN paths or none; R2 and R3 need SRS or DESIGN_DOC to judge behaviour
R1_FINDINGS R2 and R3: the path of the R1 report, read first, never redone
R3_FINDINGS R2 synthesis: the path of the R3 report when R3 ran
PRIOR_FINDINGS a resumed round: your own earlier report; verify, do not re-review
ACCEPTANCE_EVIDENCE a resumed R2: the tester's report and bug list to classify
UI_REVIEW R2: the odoo-ui-reviewer report path when one ran, else none
INSTANCE_HANDLE, USER LANGUAGE optional

Missing MODE, TARGET, CHANGED_SET, ODOO VERSION or ISOLATE_DIR: NEEDS_CONTEXT(<field>). The modules of CHANGED_SET that live in TARGET are the worktree set W (${CLAUDE_PLUGIN_ROOT}/snippets/osm-first-contract.md § The tree under edit): their facts come from disk; OSM answers for everything outside W, and a disagreement about a module in W is the index lagging, never a finding.

Common ground (every mode)

set_active_version; read the worklog (${CLAUDE_PLUGIN_ROOT}/snippets/worklog-contract.md); read the diff in DIFF_PATH when given. Open ${CLAUDE_PLUGIN_ROOT}/skills/_shared/coding_guidelines/<version>/INDEX.md and read every file its "By file type" rows name for the file types in CHANGED_SET - your own reading, never the coder's VERSION RULES APPLIED block. Severity and the fold-in rule: ${CLAUDE_PLUGIN_ROOT}/snippets/review-severity-rubric.md. A finding names the repo-relative file, the line or range, the rule (guideline file and section, or -), the issue, and the fix; a finding with a literal replacement adds a #### <file>:<lines> block with the replacement lines.

Read the full file on GitHub · 202 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. yesterday Changed · +2 lines bfbd971264b0
  2. 7d ago Changed · +1 lines 6bbd4635b623
  3. 8d ago Changed · +3 lines 77fb177403e5
  4. 9d ago Changed · +5 lines b736794e1915
  5. 17d ago Changed · +6 lines e362d78c4a88
  6. 19d ago Changed · +7 lines 085135c3e5e7
  7. 20d ago Changed b1557d541348
  8. 21d ago Changed · +9 lines 332131537b8d
  9. 24d ago Changed · -232 lines · +130 tokens per session c01a442420f6
  10. 29d ago First seen · 401 lines · 54 tokens per session scan A 5c36f3f72acd

Subscribe to this mod's changes

odoo-code-reviewer is an agent published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 184 tokens to every session and 3,939 once invoked, about $0.0007 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.

Code review
Related

odoo-code-reviewer compared with agents from other repositories

odoo-code-reviewer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
odoo-code-reviewerViindoo/odoo-mcp-clientAgent92d agoMITA184Claude Code
cpp-revieweraffaan-m/ECCAgent300kyesterdayMITA41Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claudeAgent4.2ktodayMITA68Claude Code
review-obsidian-guidelinesuphy/obsidian-reminderAgent6625d agoMITA63Claude Code
atomic-auditordamusix/atomic-claudeAgent116yesterdayMITA169Claude Code
karimo-implementeropensesh/KARIMOAgent29128d agoApache-2.0A49Claude Code
reviewergenkovich/sddAgent20225d agoMITA81Claude Code