Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gosha70/code-copilot-teamnpx agentmods add commands/gosha70/code-copilot-team/functional-testWrote 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/commands/gosha70/code-copilot-team/functional-test)<a href="https://agentmods.dev/commands/gosha70/code-copilot-team/functional-test"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/functional-test/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/commands/gosha70/code-copilot-team/functional-test"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/functional-test.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 | $0.00000 | $0.00447 |
| Opus 5.5 | $0.00000 | $0.00179 |
| Sonnet 5.5 | $0.00000 | $0.00089 |
| Haiku 4.5 | $0.00000 | $0.00045 |
Grade A, and why
functional-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 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.
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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/functional-test
Run TestKit-based functional tests locally against the same matrix CI uses.
Procedure
# Default: runs against the wrapper's Gradle version
./gradlew :plugin:functionalTest
# Specific Gradle version (matches what CI's matrix uses)
./gradlew :plugin:functionalTest -PgradleTestVersion=8.5
./gradlew :plugin:functionalTest -PgradleTestVersion=8.10
./gradlew :plugin:functionalTest -PgradleTestVersion=current
# End-to-end via the sample consumer (real composite build, real plugin apply)
(cd sample-consumer && ../gradlew exampleHello --stacktrace)
What to assert in functional tests
Every functional test must assert on task outcome, not just exit code:
val result = runner().withArguments("myTask").build()
assertEquals(TaskOutcome.SUCCESS, result.task(":myTask")?.outcome)
// Re-run to verify incremental wiring
val second = runner().withArguments("myTask").build()
assertEquals(TaskOutcome.UP_TO_DATE, second.task(":myTask")?.outcome)
For tasks meant to be cached, also test TaskOutcome.FROM_CACHE after a clean.
Common failures and what they mean
| Failure | Likely cause |
|---|---|
NoSuchMethodError from a Gradle API class |
API drift — failing version is outside the supported window |
Task outcome is SUCCESS on the second run, not UP_TO_DATE |
Missing input/output annotation, or a non-deterministic input |
Cannot mutate the build state in execution phase |
Reading config-time state at execution time — wire via Provider<T> |
| TestKit hangs | Daemon issue — set org.gradle.testkit.dir to a clean dir per test |
Refuse to merge if
- Any new public API lacks a functional test.
- Any functional test only asserts exit code without checking
TaskOutcome. - The matrix doesn't cover both the minimum supported Gradle version and the latest.
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 First seen · 48 lines · 0 tokens per session scan A ed0adee5c4c5
functional-test is a command published in the GitHub repository gosha70/code-copilot-team (7 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 447 tokens. 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 commands, from other repositories
e2e
A command for creating and running end-to-end (E2E) tests, which check a complete user flow through a web, mobile, or desktop app.
toh-test
Auto test with Playwright and fix until all tests pass.
run-workflow
Validate and establish the proven rn-dev-agent operating sequence before a real React Native journey — declared package manager and dependencies, read-only inventory, typed session recovery, one exclusive device, managed integration and Metro, only the requested proof, reverse-order cleanup.
lock-e2e
Promote a verified action into a frozen, locked e2e regression test. Runs the action once strict (no repair) via cdplocke2etest and freezes it to .rn-agent/e2e/ .yaml only if it passes. v1 supports param-free actions only.
check-ux
Walk the key flows in a real browser at mobile and desktop viewports, then a task per friction point.
rob
Invoke Rob - Senior QA Engineer for black-box feature testing.