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.
/plugin marketplace add Viindoo/odoo-mcp-client/plugin install odoo-ai-agentsWrote 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.
[](https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-code-review)<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-code-review"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-code-review.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00248 | $0.08105 |
| Opus 5 | $0.00124 | $0.04052 |
| Sonnet 5 | $0.00050 | $0.01621 |
| Haiku 4.5 | $0.00025 | $0.00810 |
Grade B, and why
odoo-code-review scanned grade B 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 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`find <ISOLATE_DIR>/reviews/ -mindepth 1 -maxdepth 1 -type d -mmin +43200 -exec rm -rf {} +` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Developer / Tech Lead reviewing Odoo code with semantic MCP enrichment.
Out of Scope
- Writing new code → route to
odoo-coding - Module-level pre-upgrade audit → route to
odoo-deprecation-audit - Override safety analysis → route to
odoo-override-finding - Verifying a render error in a real browser → route to
odoo-debug - Rating a rendered screen's look / UX / accessibility → route to
odoo-ui-review(static source review here never judges rendered appearance)
When to invoke
Invoke the odoo-code-reviewer agent when Odoo code needs review. Review scales with change size: one module -> one reviewer; many modules -> per-module fan-out + Opus integration pass.
Two entry paths - choose before dispatching the scoper:
- Pasted block or single file_path (not a git target): dispatch ONE
odoo-code-reviewerdirectly (skip scoper); the block/file is the scope. - Git target (local tree, worktree, or PR): dispatch
odoo-review-scoperfirst (Phase 0), then fan-out reviewers from its output. Each leg runs as an autonomous agent.
Derive TARGET from user intent:
| User intent | TARGET to pass |
|---|---|
| "review this" on the working tree | TARGET: local |
| "review PR #N" or a GitHub PR URL | TARGET: pr:<N> or TARGET: pr:<url> |
| Work lives in another worktree | TARGET: worktree:<abs-path> - REQUIRED; if omitted, scoper diffs principal cwd (empty diff -> BLOCKED) |
| Pasted block / single file_path, no git context | skip scoper (see above) |
For a sibling git worktree (a node's run-integration tree, or a forward-port integration tree), the orchestrator passes its WORKTREE_PATH as TARGET: worktree:<abs-path> so review runs there, not cwd.
Node-scoped review (files-in-scope). A caller driving a plan node's review MAY supply that
node's files-in-scope globs directly. Once a node can cover PART of a module, a per-module review
dispatch reviews a diff WIDER than the node that actually produced it - so when files-in-scope is
supplied, scope the review (and the diff the scoper/reviewer reads) to those globs rather than the
whole module.
What ships with it
3 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.
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.
- 4d ago Changed · +1 lines dfdf4227631f
- 8d ago First seen · 286 lines · 248 tokens per session scan B b8b4096eee34
odoo-code-review is a skill published in the GitHub repository Viindoo/odoo-mcp-client (7 stars, last pushed yesterday), licensed MIT. It adds 248 tokens to every session and 8,105 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…