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-test-writing)<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-test-writing"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-test-writing/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-test-writing"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-test-writing.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 | $0.00241 | $0.07791 |
| Opus 5 | $0.00120 | $0.03896 |
| Sonnet 5 | $0.00048 | $0.01558 |
| Haiku 4.5 | $0.00024 | $0.00779 |
Grade A, and why
odoo-test-writing 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
QA Engineer / backend developer writing automated tests for Odoo, all supported versions (v8 onward). Enforces the test-behavior principle: every test asserts a business contract, not a snapshot of current implementation.
Out of Scope
- Static review / quality audit of existing tests - use
odoo-code-review - Writing the production code under test - use
odoo-coding - Debugging a test that fails at runtime on a live instance - use
odoo-debug - Upgrade-safety audit - use
odoo-deprecation-audit - Running the test suite (including tour/HttpCase) - execution is delegated via NEEDS_NEXT to
odoo-instance; authoring (Rounds 0-4) is always in scope regardless of instance availability
Performance / load tests are IN scope (lightweight mode) - author a query-count guard (
@tagged('post_install','-at_install')+self.assertQueryCount(...)/with self.assertQueries([...])) or a bounded-time assertion over a seeded volume, grounded via OSM (orm-performance.mdidioms). It guards a BEHAVIOR contract ("stays O(1) queries under N records"), never a benchmark. A full external load/stress harness (locust-style concurrency, sustained throughput) is out of scope -> a dedicated perf harness /odoo-perf-auditfor diagnosis; state that owner explicitly rather than leaving it unowned.
Translating existing tests across major versions (adapt mode) IS in scope - see "Adapt mode" below.
When to use
Five modes, all governed by the red-before-green contract (${CLAUDE_PLUGIN_ROOT}/snippets/test-first-contract.md):
- Test-first (before the code). Author a module's failing test BEFORE the implementation, independent from the coder, so the test specifies intended behavior and code is written to green. Used standalone, or when a caller hands off red-first authoring. In the
odoo-codingloop theodoo-codercoordinator launches the dedicatedodoo-test-writeragent, which invokes THIS skill INLINE to author the RED test - so this capability is the coding loop's test author, reached through that context-isolated agent (coders never author tests). - Coverage (after the code). Backfill behavior-protecting tests for existing code; the
odoo-code-reviewtest-coverage gate routes here when a CRITICAL/HIGH change ships with no protecting test. - Adapt (forward-port test translation). Translate a test file from a source to a target Odoo version (see Adapt mode below). Invoked by the forward-port pipeline (P4a of
odoo-forward-port) or directly with a source file + version pair. - Performance/load (lightweight). Author a query-count / bounded-time behavior guard for a stated performance contract (boundary in Out of Scope).
- Tour/HttpCase (full-stack UI acceptance). Write a JS tour registered in
web_tour.tours(or the version-appropriate registry) driven by a PythonHttpCase.start_tour(...), decorated@tagged('post_install', '-at_install'). Use when acceptance flows span multiple real browser steps needing an HTTP server, orodoo-qa-planneroracle scenarios need browser-level state verification. Do NOT use for non-browser logic (useTransactionCase/Form) or a JS unit with mocked models (use Hoot - no server, no real browser). Authoring (Rounds 0-4) needs no live instance; execution requires--http-portand MUST be delegated per${CLAUDE_PLUGIN_ROOT}/snippets/test-execution-handoff.md.
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.
- 8d ago First seen · 264 lines · 241 tokens per session scan A f620104fccb0
odoo-test-writing is a skill published in the GitHub repository Viindoo/odoo-mcp-client (7 stars, last pushed 5d ago), licensed MIT. It adds 241 tokens to every session and 7,791 once invoked, about $0.0012 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 2026-09-03.
Other skills, from other repositories
migrate-xunit-to-xunit-v3
Migrate .NET test projects from xUnit.net v2 to xunit.v3 and fix v3 breaks. Use for package/CPM conversion, OutputType=Exe, preserving the VSTest or MTP runner (including projects currently using YTest.MTP.XUnit2), incompatible TFMs, async void tests, string-to-Type attributes, custom Fact/Theory/BeforeAfterTest…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
mobiai-ios-testing
Use when writing or running tests in an iOS project — unit tests, UI tests, snapshot tests, choosing the right framework.
restore-internals-seams-in-finally-blocks-after-each-test
When delegating a task affected by this skill, include.
unit-test-parameterized
Provides parameterized testing patterns with JUnit 5, generates data-driven unit tests using @ParameterizedTest, @ValueSource, @CsvSource, @MethodSource. Creates tests that run the same logic with multiple input values. Use when writing data-driven Java tests, multiple test cases from single method, or boundary value…