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-annotation)<a href="https://agentmods.dev/commands/gosha70/code-copilot-team/new-annotation"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/new-annotation/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-annotation"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/new-annotation.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 | $0.00126 |
| Opus 5.5 | $0.00000 | $0.00050 |
| Sonnet 5.5 | $0.00000 | $0.00025 |
| Haiku 4.5 | $0.00000 | $0.00013 |
Grade A, and why
new-annotation 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.
What it actually says
Add a new annotation to the framework. Requires:
- Define the annotation in
modules/annotations/with proper @Target, @Retention(RUNTIME), and Javadoc. - Update the processor in
modules/processor/to recognize and handle the new annotation. - Add compile-testing tests verifying correct generation and error cases.
- Update the demo app to exercise the new annotation.
- Update
docs/annotation-guide.mdwith usage examples.
Ensure the annotations module remains zero-dependency. The new annotation must not break existing processor behavior — run full test suite to verify.
$ARGUMENTS
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 · 11 lines · 0 tokens per session scan A 532fdf042bb1
new-annotation is a command published in the GitHub repository gosha70/code-copilot-team (7 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 126 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
devkit.java.write-unit-tests
Generates comprehensive JUnit 5 unit tests for Java classes with Mockito mocking and AssertJ assertions. Use when writing unit tests for service, controller, or utility classes.
pytest-coverage
Analyze pytest coverage and add tests to reach full code coverage.
rust-test
Rust TDD workflow with unit and property tests.
benchmark
Design and coordinate a reproducible Java performance test.
Build
Development in one command, ending in a pull request — starts dev, writes the code and (if you opt in) the unit tests, reviews it as an independent reviewer, then runs the project's real format/lint/type-check/build/test commands and finishes with recorded evidence. Asks up front whether to write and run unit tests.…
tester
Comprehensive testing with parallel execution capabilities.