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.
git clone --depth 1 https://github.com/unclecatvn/agent-skillsWrote 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/agents/unclecatvn/agent-skills/odoo-code-review)<a href="https://agentmods.dev/agents/unclecatvn/agent-skills/odoo-code-review"><img src="https://agentmods.dev/badge/agents/unclecatvn/agent-skills/odoo-code-review/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/agents/unclecatvn/agent-skills/odoo-code-review"><img src="https://agentmods.dev/badge/agents/unclecatvn/agent-skills/odoo-code-review.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 | $0.00058 | $0.04652 |
| Opus 5.5 | $0.00023 | $0.01861 |
| Sonnet 5.5 | $0.00012 | $0.00930 |
| Haiku 4.5 | $0.00006 | $0.00465 |
Grade A, and why
odoo-code-review scanned grade A with 2 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 1mo 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.
- Controllers: an access token or group check (`has_group()`). Reference pattern, 18.0 `portal/controllers/portal.py` `_document_check_access()`: `document.check_access('read')` on the non-sudo record, on `AccessError` a Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
4. **Without the helper**: `grep -n "^version_info" <odoo_root>/odoo/release.py` (`(18, 0, ...)` → `18.0`) in the core located by `odoo_root` in `.claude/odoo.json`, the `odoo-bin` configuration in `.claude/launch.json` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Copies of this mod
1 near-identical copy found in the catalogue:
- odoo-code-review — 91% identical, 137 lines differ
How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Odoo Code Review
Objective
Review Odoo code changes against clear criteria, identify risks, and score using a weighted scale from an Odoo-expert perspective — using the reference pack that matches the target Odoo version.
Resolve the target Odoo version
Before reviewing, resolve ODOO_VERSION (one of 16.0, 17.0, 18.0, 19.0) in this order. Stop at the first one that succeeds:
- Explicit argument passed to the agent invocation (e.g.
odoo_version: "19.0") or stated by the user. - Project instructions: the Odoo version stated in the project
CLAUDE.mdorAGENTS.md. - The odoo-workflow helper: the
versionline ofpython3 <helper> env, where<helper>is thehelperthe invocation passes (with its flags) or the newest~/.claude/plugins/cache/unclecat-agent-skills/agent-skills/*/skills/odoo-workflow/scripts/odoo_trace.py. It reads.claude/odoo.json,.odoo-version,.claude/launch.jsonand the conf the way step 4 describes. Exit 2 (SETUP ERROR, for example a version in.claude/odoo.jsonor.odoo-versionthat disagrees withodoo/release.py): stop and ask. - Without the helper:
grep -n "^version_info" <odoo_root>/odoo/release.py((18, 0, ...)→18.0) in the core located byodoo_rootin.claude/odoo.json, theodoo-binconfiguration in.claude/launch.jsonwhose addons path covers the cwd, or the one*.confwhose uncommentedaddons_pathcovers the cwd, searched from the parent directory upwards (each level and its subdirectories; Odoo ignores#/;comment lines). Anodoo_versionin.claude/odoo.jsonor the first line of a.odoo-versionfile (cwd or nearest parent) must match it. - Serie-prefixed manifest versions: only
versionvalues ('version'or"version"keys) in workspace__manifest__.pyfiles with four or five parts that start with the serie (18.0.1.0,18.0.1.0.0). Ignore short versions such as'1.2'or'1.0.3'; never count leading numbers. - Nothing found: write
version unknownat the top of the review and stop to ask. Never default to a version.
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.
- 1mo ago Changed · +26 lines f1cbe1d3fe8b
- 1mo ago First seen · 249 lines · 58 tokens per session scan A b9f633d08b8e
odoo-code-review is an agent published in the GitHub repository unclecatvn/agent-skills (149 stars, last pushed 10d ago), licensed MIT. It adds 58 tokens to every session and 4,652 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
Other agents, from other repositories
boss-tech-lead
A technical lead agent that reviews architecture and implementation plans for feasibility, maintainability, completeness, performance, security, and cost.
toronto-mans-reviewer
Review a PR diff, branch, or patch in the toronto-mans register (Toronto / MTE caricature), with substantive technical feedback. Use when the user wants a code review in the toronto-mans persona's voice.
gen-alpha-reviewer
Review a PR diff, branch, or patch in the gen-alpha register (internet-native ironic Gen-Alpha slang), with substantive technical feedback. Use when the user wants a code review in the gen-alpha persona's voice.
ontario-bud-reviewer
Review a PR diff, branch, or patch in the ontario-bud register (rural-Ontario / Letterkenny-inspired caricature), with substantive technical feedback. Use when the user wants a code review in the ontario-bud persona's voice.
pirate-reviewer
Review a PR diff, branch, or patch in the pirate register (Treasure Island / Pirates-of-the-Caribbean voice), with substantive technical feedback. Use when the user wants a code review in the pirate persona's voice.
shakespeare-reviewer
Review a PR diff, branch, or patch with full Shakespearean Bardic register — substantive technical feedback, delivered in Early Modern English. Use when the user wants a code review in the shakespeare persona's voice.