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 skills/actinon-com/brass-monkey/odoo-securitynpx skills add actinon-com/brass-monkey --skill odoo-securitygit clone --depth 1 https://github.com/actinon-com/brass-monkeyWrote 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/actinon-com/brass-monkey/odoo-security)<a href="https://agentmods.dev/skills/actinon-com/brass-monkey/odoo-security"><img src="https://agentmods.dev/badge/skills/actinon-com/brass-monkey/odoo-security.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 | $0.00027 | $0.00517 |
| Opus 5 | $0.00014 | $0.00259 |
| Sonnet 5 | $0.00005 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
odoo-security 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 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.
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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Odoo Security & Access Control
This skill provides the agent with high-level functional expertise in Odoo's security and permission architecture, covering Users, Groups, Access Rights, and Record Rules.
Core Mandates
1. The Security Hierarchy
Understand how Odoo grants permissions:
- Users (
res.users): Individual accounts. - Groups (
res.groups): Logical roles (e.g., "Sales / User", "Accounting / Manager"). - Access Rights (
ir.model.access): Model-level permissions (Can I Read/Write/Create/Delete ANY record in this model?). - Record Rules (
ir.rule): Row-level permissions (Can I see THIS specific record?). Enforced viadomain_forcefilters.
2. Record Rule Enforcement
- Mandate: Record rules strictly filter data at the database level. Even if a user has "Read" access on a model via Access Rights, a Record Rule can hide specific records.
- Evaluation: Odoo applies Record Rules using specific logic:
- Global Rules: (no group assigned) are applied using AND (all must pass).
- Group Rules: (assigned to a group) are applied using OR among rules of the same group.
3. Multi-Company Security
- Strict Isolation: Odoo uses Record Rules to enforce multi-company isolation.
- Mandate: When creating or updating records, ensure the
company_idis set correctly. Attempting to link records from different companies (e.g., a Sales Order in Company A pointing to a Warehouse in Company B) will trigger a "Multi-company Access Error".
4. Troubleshooting Workflow
When a user encounters an "Access Error":
- Groups: Verify the user's assigned groups in
res.users. - Access Rights: Check
ir.model.accessfor the target model and the user's groups. - Record Rules: Check
ir.rulefor active domains on the target model. Analyze thedomain_forceto see if it's filtering out the specific record ID.
Available Resources
security-logic.md: Deep-dive into Access Rights vs. Record Rules, Evaluation Logic, and Multi-company rules.security-fields.json: Technical map for Users, Groups, Access, and Rule models.
What ships with it
2 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 First seen · 37 lines · 27 tokens per session scan A 365076efc45d
odoo-security is a skill published in the GitHub repository actinon-com/brass-monkey (2 stars, last pushed 11d ago), licensed MIT. It adds 27 tokens to every session and 517 once invoked, about $0.0001 per session on Opus 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.
Other skills, from other repositories
deploy-able
Drive an Able Desk deployment onto the user's own Cloudflare account, in order, stopping at every step only a human can complete. Use when the user wants to deploy Able, set it up for their business, stand up a support desk, resume a half-finished deployment, or check what is left before real customers can be served.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
mcp-scripting
Write mcpScript JavaScript for discovering, inspecting, and calling MCP tools.
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
WRITE_ATTACHMENT_SERVICE
You are adding an inbound/attachment module to a domain crate. This module implements the attachment::AttachmentService trait so the crate can resolve its entity IDs into AI-consumable attachment content.
lov-article-creator
统一创建、改写、品牌化或忠实转载微信公众号文章包：正文写作调用唯一文风与作者性能力，离线完成结构、品牌、封面、4:3 首图、来源与质量验收。Use when asked to write, brand, audit, or faithfully repost a WeChat article package.