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/security-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 | $0.00391 |
| Opus 5 | $0.00000 | $0.00196 |
| Sonnet 5 | $0.00000 | $0.00078 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
security-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.
What it actually says
Security Behavior
Purpose
Define how the agent should behave when a task affects access control, record rules, privilege escalation, controllers, SQL, or other security-sensitive logic.
When to activate
- The task changes
ir.model.access.csv. - The task introduces or modifies
ir.rule. - The task uses
sudo(). - The task creates controllers or public routes.
- The task writes custom SQL.
- The task exposes business data through APIs, portals, exports, or cron jobs.
Pre-checks
- Identify affected models and user groups.
- Check whether the logic should run as user, system, or elevated privileges.
- Identify possible data leaks across companies, users, or portals.
- Inspect whether custom SQL can be replaced with ORM.
- Inspect whether controllers validate auth, csrf, and input.
Workflow
- Identify the security boundary affected by the change.
- Review access rights and record rules before implementing logic.
- Minimize use of
sudo()and justify every use. - Prefer ORM with proper domain filtering over raw SQL.
- Validate portal/public endpoints carefully.
- Check multi-company implications.
- Ensure exports/imports do not bypass intended restrictions.
- Recommend tests for permission-sensitive flows.
Rules
- Least privilege first.
sudo()must be exceptional, not default.- Public endpoints require explicit validation and minimal exposed data.
- ORM is preferred over SQL unless there is a justified reason.
- Multi-company safety must be checked explicitly.
Avoid
- Blanket
sudo()in create/write/search flows. - Overly broad record rules.
- Exposing internal fields in controllers or portal endpoints.
- Building security only after business logic is done.
- Raw SQL without parameter safety and access review.
Related references
references/security.mdreferences/sql-performance.mdreferences/testing.mdreferences/maturity-levels.md
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 · 50 lines · 0 tokens per session scan A 345caa53c6f7
security-behavior is an agent published in the GitHub repository CodeForUsers/odoo-dev-superskill (11 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 391 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-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?
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
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.