review-behavior

A review procedure for checking an existing Odoo module's code, structure, security, tests, documentation, and alignment with OCA guidelines.

In plain words
What is it for?
Use it to assess an Odoo module before release, publication, migration, or further maintenance.
Why use it?
It turns a broad code review into ordered checks and separates serious problems from optional improvements.

Agent

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.

agentmods
npx agentmods add agents/codeforusers/odoo-dev-superskill/review-behavior
Clone the repo
git clone --depth 1 https://github.com/CodeForUsers/odoo-dev-superskill
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00449
Opus 5 $0.00000 $0.00225
Sonnet 5 $0.00000 $0.00090
Haiku 4.5 $0.00000 $0.00045

Measured 2d ago against content hash 56476bdff3c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-behavior 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 2d 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.

references/agents/review-behavior.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Behavior

Purpose

Define how the agent should behave when reviewing an existing Odoo module for quality, maintainability, structure, OCA alignment, and production readiness.

When to activate

  • The user asks for code review.
  • The user asks for improvement suggestions.
  • The task is to assess quality before publication or migration.
  • The task is to audit an addon for structure or maintainability.

Pre-checks

  • Identify target version and module scope.
  • Inspect manifest, dependencies, models, views, security, tests, and data files.
  • Determine whether the review should focus on bugs, architecture, style, or OCA compliance.
  • Check if the module has tests and documentation.

Workflow

  1. Review structure first.
  2. Review security and access model.
  3. Review models and business logic.
  4. Review XML/UI consistency.
  5. Review connectors/integrations if present.
  6. Review tests, linting, and maintainability.
  7. Present findings by severity: critical, important, optional.
  8. Suggest concrete improvements, not vague opinions.

Rules

  • Prioritize correctness and maintainability over style nitpicks.
  • Distinguish blockers from polish.
  • Tie every recommendation to a specific risk or benefit.
  • Be explicit when something is uncertain.
  • Prefer actionable review output.

Avoid

  • Generic praise with no technical value.
  • Treating all issues as equally important.
  • Reviewing style while ignoring security or maintainability.
  • Recommending large refactors without justification.
  • Assuming OCA compliance without checking module structure.

Tooling integration (Optional)

  • Codegraph: Use codegraph_explore to quickly map the models defined in the module and their inheritance hierarchy. Use codegraph_callers to verify if modified methods are invoked elsewhere in the codebase, preventing broken references.
  • Engram: Retrieve past review findings or conventions using mem_search before starting the audit. Record any significant new architectural decisions or custom coding constraints identified during review using mem_save.

Read the full file on GitHub · 51 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. 2d ago First seen · 51 lines · 0 tokens per session scan A 56476bdff3c7

Subscribe to this mod's changes

review-behavior is an agent published in the GitHub repository CodeForUsers/odoo-dev-superskill (12 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 449 tokens. 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 2026-08-30.