Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Viindoo/odoo-mcp-client/plugin install odoo-ai-agentsWrote 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/viindoo/odoo-mcp-client/odoo-code-review)<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-code-review"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/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/skills/viindoo/odoo-mcp-client/odoo-code-review"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/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 | $0.00023 | $0.01498 |
| Opus 5.5 | $0.00009 | $0.00599 |
| Sonnet 5.5 | $0.00005 | $0.00300 |
| Haiku 4.5 | $0.00002 | $0.00150 |
Grade A, and why
odoo-code-review 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 8d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Front door for reviewing Odoo code. It resolves the target, computes the changed set, launches
odoo-code-reviewer in its three modes at three tiers, and returns the verdict. It launches and
returns; it does not wait on a fix, and the findings go back to the coder that built the node
through the caller's fix round. Every review mode judges the change against
${CLAUDE_PLUGIN_ROOT}/snippets/odoo-platform-design-principles.md § 0: a block on a policy
limit, a guard without a way out, or a surface that behaves unlike core's is a finding.
Out of Scope
- Writing new code or fixing a finding ->
odoo-coding(the caller resumes the node's coder) - Module-level pre-upgrade audit ->
odoo-deprecation-audit - Override safety analysis of one hook ->
odoo-override-finding - Verifying a render error in a real browser ->
odoo-debug - Rating a rendered screen's look, UX or accessibility ->
odoo-ui-review - Executing acceptance scenarios on a live instance ->
odoo-acceptance
Target
| User intent | TARGET |
|---|---|
| "review this" on the working tree | local |
| "review PR #N" or a GitHub PR URL | pr:<N> |
| work in another worktree, a node's worktree, an integration branch | worktree:<abs-path> (required; without it a review of the principal cwd finds an empty diff) |
| a pasted block or one file with no git context | file:<path> - R1 and R2 over that file only |
Steps
- Resolve the tree.
local-> therepo_rootof arepo_factscall on this cwd;worktree:-> the path given;pr:-> invokegit-toolkit:git-opsto fetch the PR metadata and changed files and to check the PR branch out in a worktree at the pathproject_dir(axisworktree,name=pr-<N>) returns - under the state root, never a temp dir and never the principal checkout (git-safety-contract S9). CaptureSHARE_DIRandISOLATE_DIRonce withproject_diragainst that tree. - Changed set. Ask
git-toolkit:git-opsfor the files that differ betweenBASE(default the series main branch, or the PR base) and the tree's HEAD, and for the diff of that range written to<ISOLATE_DIR>/reviews/<slug>-<date>/diff.patch(DIFF_PATH); the files giveCHANGED_SET; the modules it touches and their manifests give the Domain line when the brief carries none (${CLAUDE_PLUGIN_ROOT}/snippets/business-taxonomy.md). Delete<ISOLATE_DIR>/reviews/<slug>-<date>/directories untouched for 30 days (${CLAUDE_PLUGIN_ROOT}/snippets/visual-evidence-lifecycle-contract.mdClause 3). - Launch R1 (
odoo-code-reviewer,MODE: R1,model: haiku) with the brief in${CLAUDE_PLUGIN_ROOT}/skills/odoo-code-review/references/agent-prompts.md. A diff whose changed files exceed one agent's budget is split by module into several R1 launches in one message. - Launch R2, and R3 when due, in ONE message after R1 returns: R2 (
MODE: R2,model: sonnet) withR1_FINDINGS; R3 (MODE: R3,model: opus) only when the unit'sbusiness_functionis on the specialist list of the taxonomy orRECONrecords an override chain or dependent count at the thresholds of${CLAUDE_PLUGIN_ROOT}/skills/_shared/concurrency-guard.md§ 5.2. When R3 runs, R2 is launched after R3 returns, withR3_FINDINGS, so one report carries the verdict. When anINSTANCE_HANDLEis available andCHANGED_SETholds views, launchodoo-ui-reviewer(model: sonnet) in the same message as R2 for the rendered screens; R2 reads its report path when both are given. - Return. The R2 report path, verdict and score, the severity counts, and the Continuation
Contract (
next: odoo-ui-reviewwhen R2 asked for it). Present the summary in the user's language. Post to the PR only on the explicit keywordpost: convert every finding row to{path, startLine, line, severity, body, suggestion}and invokegit-toolkit:git-opsto open one pending review, one inline comment per finding, submitted asREQUEST_CHANGESwhen any CRITICAL or HIGH remains, elseCOMMENT, plus one top-level verdict comment.
What ships with it
1 file 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.
- 8d ago Changed · +2 lines 74e830916a0e
- 17d ago Changed · -8 tokens per session 8cc3ecd1f531
- 19d ago Changed · +1 lines bc9bded58e50
- 24d ago Changed · -178 lines scan B → A d16bdc9766c7
- 29d ago Changed · -13 lines 80c41ef1e483
- 1mo ago Changed · -9 lines · -217 tokens per session 39a9586174d2
- 1mo ago Changed · +17 lines ef3d334f44b5
- 1mo ago Changed · -3 lines 0c28cc905551
- 1mo ago Changed · -7 lines 951088752672
- 2mo ago First seen · 287 lines · 248 tokens per session scan B dfdf4227631f
odoo-code-review is a skill published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 1,498 once invoked, about $0.0001 per session on Opus 5.5. 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.
odoo-code-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| odoo-code-reviewViindoo/odoo-mcp-client | Skill | 9 | 2d ago | MIT | A | 23 | Claude Code |
| autoreviewopenclaw/clawhub | Skill | 9.5k | today | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 4d ago | MIT | A | 115 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.3k | today | MIT | A | 49 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 949 | yesterday | MIT | A | 84 | Claude Code |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | yesterday | MIT | A | 51 | Claude Code, Codex |
| explore-unknownsdzhng/skills | Skill | 1.5k | 2d ago | MIT | A | 162 | Claude Code, Codex |