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.
git clone --depth 1 https://github.com/gosha70/code-copilot-teamWrote 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/new-task)<a href="https://agentmods.dev/commands/gosha70/code-copilot-team/new-task"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/new-task/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/new-task"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/new-task.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 | $0.00552 |
| Opus 5.5 | $0.00000 | $0.00221 |
| Sonnet 5.5 | $0.00000 | $0.00110 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
new-task 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/new-task
Add a new Gradle task type to the plugin.
Procedure
-
Decide the task's inputs and outputs. Every input is
@get:Input,@get:InputFile, or@get:InputDirectory. Every output is@get:OutputFileor@get:OutputDirectory. Anything that is neither is@get:Internal. No exceptions — Gradle uses these annotations to drive incremental builds and the build cache. -
Create the task class under
plugin/src/main/kotlin/com/example/gradleplugin/:abstract class MyNewTask : DefaultTask() { @get:Input abstract val someValue: Property<String> @get:OutputFile abstract val outputFile: RegularFileProperty @TaskAction fun run() { outputFile.get().asFile.writeText(someValue.get()) } }The class must be
abstractand every propertyabstract val ...: Property<T>so Gradle synthesises the implementation and injects theObjectFactory. Do not write a constructor. -
Register the task in
ExamplePlugin.apply()usingtasks.register(nevertasks.create):project.tasks.register("myNewTask", MyNewTask::class.java) { task -> task.someValue.set(extension.someValue) task.outputFile.set(project.layout.buildDirectory.file("...")) } -
Add a unit test under
plugin/src/test/kotlin/...usingProjectBuilder(verifies registration + default values). -
Add a functional test under
plugin/src/functionalTest/kotlin/...that:- Seeds a synthetic build that applies the plugin and configures the extension.
- Runs the task via
GradleRunner.create(). - Asserts on
TaskOutcome.SUCCESSfor the first run. - Re-runs the task and asserts on
TaskOutcome.UP_TO_DATE(proves incremental wiring).
-
Run locally:
./gradlew :plugin:check # unit + functional via the check aggregate ./gradlew :plugin:functionalTest # functional tests only
Refuse to merge if
- Any input/output property is missing its annotation.
- The task is registered with
tasks.createinstead oftasks.register. - There is no functional test asserting on
TaskOutcomefor the new task. - The task action captures
project.<anything>instead of using aProvider.
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 · 53 lines · 0 tokens per session scan A fcac87ba2d08
new-task 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 552 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
story-continue
Resume an interrupted story from where you left off.
views
Create Django views with proper structure and best practices.
go-review
Go code review for idiomatic patterns.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.