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.
npx agentmods add agents/codeforusers/odoo-dev-superskill/review-behaviorgit clone --depth 1 https://github.com/CodeForUsers/odoo-dev-superskillWhat 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 | $0.00000 | $0.00449 |
| Opus 5 | $0.00000 | $0.00225 |
| Sonnet 5 | $0.00000 | $0.00090 |
| Haiku 4.5 | $0.00000 | $0.00045 |
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.
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
- Review structure first.
- Review security and access model.
- Review models and business logic.
- Review XML/UI consistency.
- Review connectors/integrations if present.
- Review tests, linting, and maintainability.
- Present findings by severity: critical, important, optional.
- 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_exploreto quickly map the models defined in the module and their inheritance hierarchy. Usecodegraph_callersto verify if modified methods are invoked elsewhere in the codebase, preventing broken references. - Engram: Retrieve past review findings or conventions using
mem_searchbefore starting the audit. Record any significant new architectural decisions or custom coding constraints identified during review usingmem_save.
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.
- 2d ago First seen · 51 lines · 0 tokens per session scan A 56476bdff3c7
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.
Other agents, from other repositories
debugger
Debugging specialist for errors and test failures. Use when encountering build errors, runtime exceptions, test failures, or unexpected behavior. Invoke with /debugger to investigate issues.
verifier
Validates completed work. Use after tasks are marked done to confirm implementations are functional. Invoke with /verifier when you need to verify code actually works.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
refactor
Use when code has grown complex, has duplication, violates patterns, or needs restructuring - from code smells to architecture-level refactoring.
marketing
Use when creating marketing copy, landing pages, email campaigns, social media strategy, SEO content, or growth experiments.