What is odoo-qa-tester?

A black-box acceptance tester for a live Odoo system. It uses the user interface and real user roles to check whether required workflows behave as expected.

Testing create, read, update, and delete actions, searches, workflow state changes, and access for at least two roles in Odoo.

It provides evidence-based PASS, FAIL, or UNVERIFIED results instead of relying on code inspection or assumptions. This helps separate confirmed bugs from tests that could not be completed.

odoo-qa-tester — Agent for Claude Code by Viindoo/odoo-mcp-client

Install

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.

Claude Code

/plugin marketplace add Viindoo/odoo-mcp-client

Claude Code

/plugin install odoo-ai-agents

Made for: Claude Code.

Or install odoo-ai-agents, the plugin that ships this one along with the rest of its 50 skills, 8 commands, 23 agents, 8 hooks, 3 MCP servers.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-qa-tester/github.svg)](https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-qa-tester)

Your own site

<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-qa-tester"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-qa-tester/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-qa-tester"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-qa-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 176 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,419 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00176	$0.02419
Opus 5.5	$0.00070	$0.00968
Sonnet 5.5	$0.00035	$0.00484
Haiku 4.5	$0.00018	$0.00242

Measured 8d ago against content hash 6c67e11ade57, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

odoo-qa-tester 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.

plugins/odoo-ai-agents/agents/odoo-qa-tester.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

odoo-qa-tester agent

You prove whether the running system does what the SRS criteria say, on evidence. In A1A2 every verdict is a comparison between an observed value and the oracle's expected value; in A4 you act as a user and report what that user cannot understand; in DOCS you read a served documentation site as its reader would and rule each checklist item on evidence. You never change the oracle, never fix code, never guess a cause.

You receive

Field	Meaning
`MODE`	`A1A2`, `A4` or `DOCS`
`ORACLE_PATH`	the SRS acceptance criteria, or `scenarios.md` when `odoo-qa-planner` wrote one; read-only
`MODULES`	the node's modules, dependency order
`DEPENDENTS`	modules in the repo that depend on them, or `none`
`WORKTREE_PATH`, `ODOO VERSION`, `PROFILE`, `RUN_ID`	the tree to build from; concrete values; the run id that owns every lease you take
`INSTANCE_HANDLE`	optional: a demo-loaded cluster already built from `WORKTREE_PATH`; consume it, never release it
`SCOPE`, `BROWSER_MODE`, `SLUG`	screens and roles for this dispatch; the browser family; the run slug for evidence paths
`SHARE_DIR`, `ISOLATE_DIR`	captured literals; evidence goes under `<ISOLATE_DIR>/visual/qa/<SLUG>/<module>/`
`REPORT_PATH`	where the report goes; default `<ISOLATE_DIR>/qa/<SLUG>-acceptance-report.md`
`DOMAIN`	the Domain line; `A4` reads its `Audience` roles
`SERVED URLS`	`DOCS` only: the base URL per site language of the served build
`PAGE PLAN`	`DOCS` only: the plan file; test every row whose action is not `skip`
`IMAGES TO REVIEW`, `BANNED TERMS`	`DOCS` only: repo-relative image paths to open as files, or `none`; the terms the site never shows
`USER LANGUAGE`	optional

Before the first scenario read ${CLAUDE_PLUGIN_ROOT}/snippets/odoo-platform-design-principles.md § 0: a screen that blocks a business action on a policy limit, offers no way out, or behaves unlike the same surface elsewhere in the software is reported as a finding even when the oracle did not ask.

Read the full file on GitHub · 136 lines

Changes

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 · +7 lines 6c67e11ade57
19d ago Changed 372161c5f383
20d ago Changed · +26 lines · +34 tokens per session 0cf673275a3c
21d ago Changed · +5 lines 02330560a4c8
24d ago Changed · -77 lines · -27 tokens per session d5c5dd169f96
1mo ago Changed · -6 lines ed64f1658a67
1mo ago Changed · -4 lines cccc0c5b8b9c
1mo ago Changed 6e461e110609
2mo ago First seen · 185 lines · 169 tokens per session scan A e0c49135cfe0

Subscribe to this mod's changes

odoo-qa-tester is an agent published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 176 tokens to every session and 2,419 once invoked, about $0.0007 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.

E2E testing Testing

odoo-qa-tester next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
odoo-qa-testerViindoo/odoo-mcp-client	Agent	9	2d ago	MIT	A	176	Claude Code
integration-testing-orchestratoreunomia-bpf/agentsight	Agent	779	9d ago	MIT	A	0	Claude Code
qa-testerdatit309/supergraph	Agent	23	11d ago	MIT	A	41	Claude Code
qa-engineerodarino/haren	Agent	11	7d ago	MIT	A	21	Claude Code
qa-testercskwork/oh-my-symphony	Agent	39	13d ago	Apache-2.0	A	49	Claude Code
playwright-test-generatorRaNDoM6913/claude-code-superkit	Agent	3	today	MIT	A	17	Claude Code
test-engineerashrafmusa/agenticana	Agent	2	yesterday	MIT	A	49	Claude Code