Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ahmed-lakosha/odoo-pluginsnpx agentmods add commands/ahmed-lakosha/odoo-plugins/odoo-securityWrote 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/commands/ahmed-lakosha/odoo-plugins/odoo-security)<a href="https://agentmods.dev/commands/ahmed-lakosha/odoo-plugins/odoo-security"><img src="https://agentmods.dev/badge/commands/ahmed-lakosha/odoo-plugins/odoo-security/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ahmed-lakosha/odoo-plugins/odoo-security"><img src="https://agentmods.dev/badge/commands/ahmed-lakosha/odoo-plugins/odoo-security.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.03654 |
| Opus 5 | $0.00009 | $0.01827 |
| Sonnet 5 | $0.00003 | $0.00731 |
| Haiku 4.5 | $0.00002 | $0.00365 |
Grade A, and why
odoo-security scanned grade A 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 9d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
/odoo-security my_module --layer=sudo /odoo-security my_module --layer=access --fix 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 — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/odoo-security
Unified security audit for Odoo modules. Scans model access rules, HTTP route authentication, sudo() privilege escalation, SQL injection risks, and record rule coverage — all in one command.
Argument Parsing
Parse $ARGUMENTS for:
| Token | Type | Default | Description |
|---|---|---|---|
| First positional | path/name | (required) | Module path or name |
--severity= |
enum | low |
Minimum severity to report: critical, high, medium, low |
--layer= |
enum | all |
Which audit layer to run: access, routes, sudo, sql, all |
--fix |
flag | off | Generate and apply safe remediations after review |
--json |
flag | off | Output as machine-readable JSON |
Examples of valid invocations:
/odoo-security my_module
/odoo-security /path/to/module --severity=high
/odoo-security my_module --layer=sudo
/odoo-security my_module --layer=access --fix
/odoo-security my_module --severity=critical --layer=routes
Help (No Module Provided)
If $ARGUMENTS is empty or --help, display:
Odoo Security — Comprehensive Module Security Audit
USAGE
/odoo-security <module> [options]
LAYERS (--layer=)
all Run every audit layer (default)
access Model access rules — ir.model.access.csv completeness
routes HTTP route auth, CSRF, data exposure
sudo .sudo() usage — privilege escalation, loops, unscoped
sql SQL injection — unsafe cr.execute(), string formatting in queries
SEVERITY LEVELS (--severity=)
critical Immediate vulnerability — fix before deployment
high Significant risk, likely exploitable — fix within sprint
medium Security weakness — fix in next release
low Minor improvement — fix when convenient (default threshold)
EXAMPLES
/odoo-security my_module Full audit, all layers
/odoo-security my_module --severity=high Only HIGH+ issues
/odoo-security my_module --layer=access --fix Check access rules, apply fixes
/odoo-security my_module --layer=sudo Find risky sudo() calls
/odoo-security my_module --layer=routes Audit HTTP route security
/odoo-security my_module --layer=sql Scan for SQL injection risks
LAYER EQUIVALENTS (conceptual mappings)
Full audit -> /odoo-security (default, all layers)
Access rules only -> /odoo-security --layer=access
Route security -> /odoo-security --layer=routes
Sudo analysis -> /odoo-security --layer=sudo
SQL injection -> /odoo-security --layer=sql
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.
- 9d ago First seen · 423 lines · 17 tokens per session scan A fb952135cdc1
odoo-security is a command published in the GitHub repository ahmed-lakosha/odoo-plugins (74 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 3,654 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.