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.
npx agentmods add skills/thermiteau/maverick/do-testnpx skills add thermiteau/maverick --skill do-testgit clone --depth 1 https://github.com/thermiteau/maverickWrote 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/thermiteau/maverick/do-test)<a href="https://agentmods.dev/skills/thermiteau/maverick/do-test"><img src="https://agentmods.dev/badge/skills/thermiteau/maverick/do-test.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.01483 |
| Opus 5 | $0.00036 | $0.00741 |
| Sonnet 5 | $0.00014 | $0.00297 |
| Haiku 4.5 | $0.00007 | $0.00148 |
Grade A, and why
do-test 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 4d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write or Update Tests
Wraps test-writing work in a Maverick skill so the workflow report
records what was tested and the agent applies the project's testing
standards before writing tests. Invoke this skill once per testable
change from inside do-issue-solo /
do-issue-guided / do-epic Phase 5 —
typically as a sibling call to do-code, before the
commit for that task.
This skill is a thin wrapper. The actual test files are written by the orchestrating Claude Code session using its built-in tools (Read, Edit, Write, Bash). The skill's job is to pin the right standards for the mode and keep scope tight.
Preflight (mandatory)
Run this first. If it exits non-zero, halt and report the stderr output to the user verbatim. Do not proceed.
uv run maverick preflight do-test
Skip the preflight when invoked from inside a do-issue-* or
do-epic phase — the orchestrator already ran a stricter one this
session. Run it only when this skill is invoked standalone.
The check verifies the project is initialised and uv is on PATH.
Mode Selection
$ARGUMENTS must specify a mode:
unit— module-scoped, fast, deterministic. No network, no real database, no real filesystem outside the test's owntmp_path. Use this for any change that can be exercised through its public surface in-process.integration— crosses module / service / database / external API boundaries. Real I/O is allowed (and usually required). Slower; reserved for changes whose behaviour only emerges across that boundary.
If no mode is specified, halt and ask the caller to pick one. Do not guess — getting the mode wrong invites flaky tests or fast-but-untrue coverage.
Unit Mode
Apply mav-bp-testing for the project's unit-testing
conventions (test framework, naming, fixture style, assertion
patterns).
- Locate the test file. Look for an existing test file that
corresponds to the production code you just changed. If none
exists, follow the project's convention for placement
(
tests/unit/test_<module>.py,<module>.test.ts, etc.) — check how nearby modules are tested. - Identify what changed in observable behaviour. Write tests against the public surface, not the internals. If the change is purely refactoring with no behaviour change, the existing tests should already cover it — re-running them is the validation.
- Write one test per branch / case. Cover the happy path, relevant edge cases, and any error paths the change introduced. Don't write a single mega-test that exercises everything.
- Verify by running the project's unit suite per
mav-local-verification. The whole suite — not just the new tests — must stay green.
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.
- 4d ago First seen · 145 lines · 71 tokens per session scan A 5f67cf9d2c6e
do-test is a skill published in the GitHub repository thermiteau/maverick (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,483 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
run-helix-tests
Submit and monitor .NET MAUI unit tests on Helix infrastructure. Supports running XAML, Resizetizer, Core, Essentials, and other unit test projects on distributed Helix queues.
nunit-testing
Use when writing or modifying tests in NUnit's own test projects, or when making a behavioral change to production code that needs test coverage. Covers test structure, attribute choice, helper visibility, platform guards, and which test projects are real.
dart-test
DART Test: unit tests, integration tests, CI validation, and debugging.
browserless-test
Creates Vaadin Browserless server-side unit tests for Vaadin views covering navigation, component interactions, form validation, grid operations, and notifications. Use when the user asks to "write Browserless tests", "write Vaadin UI unit tests", "unit test a Vaadin view without a browser", "create view tests with…
junit-5-skill
Generates production-grade JUnit 5 unit and integration tests in Java. Covers assertions, parameterized tests, lifecycle hooks, mocking with Mockito, and nested tests. Use when user mentions "JUnit", "JUnit 5", "@Test", "assertEquals", "Assertions", "Java unit test". Triggers on: "JUnit", "@Test", "assertEquals"…
smoke-test-ml-pipeline
Owns the smoke test contract for an ML experiment: a small, diagnostic-by-construction pytest that fits the experiment's learner on a portion of the real data/ source and predicts on a disjoint portion that deliberately carries no pre-history buffer. The assertion is structural — the number of predictions must equal…