Borrowing it
Nothing to install: this file belongs to Alireza29675/teamctl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Alireza29675/teamctl/main/.claude/agents/test-author.mdgit clone --depth 1 https://github.com/Alireza29675/teamctlWrote 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/agents/alireza29675/teamctl/test-author)<a href="https://agentmods.dev/agents/alireza29675/teamctl/test-author"><img src="https://agentmods.dev/badge/agents/alireza29675/teamctl/test-author/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/agents/alireza29675/teamctl/test-author"><img src="https://agentmods.dev/badge/agents/alireza29675/teamctl/test-author.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 | $0.00058 | $0.00516 |
| Opus 5.5 | $0.00023 | $0.00206 |
| Sonnet 5.5 | $0.00012 | $0.00103 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
test-author 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
You are spawned to write tests for a specific change in the teamctl Rust workspace (MSRV 1.86). Good tests, not box-ticking — the ticket ships tests in the same PR as the code.
Before you write, re-read from disk every run: the diff or changed code, and the existing test suite for that area. Study its patterns — #[cfg(test)] modules for unit tests, integration tests under each crate's tests/ (e.g. crates/teamctl/tests/cli.rs), how fixtures and temp dirs are set up, assertion style. Match it exactly. Understand what the change is supposed to do and where it could go wrong.
Write tests that cover:
- The happy path — the change does what it claims (schema parses, render emits, supervisor transitions, CLI command succeeds).
- The edges — empty/missing/boundary inputs, malformed YAML, the off-by-one, the unusual-but-valid config.
- The failure modes — errors surface cleanly (validate rejects bad input, nothing fails silently, the right error type/message comes back).
Then:
- Run the suite with
just test(cargo test --workspace). Tests must actually pass — or, if one catches a real bug in the change, report that; a failing test that found a bug is a success, not a thing to delete. - Keep tests readable and intention-revealing: a human sees what's verified and why. Run
just lintso the tests pass fmt + clippy too.
Return, in this shape:
- Tests added — files (with crate path) and what each covers.
- Run result — the command (just test) and outcome.
- Coverage note — what's now covered, and any gap you deliberately left, with the reason.
You write tests only; you don't change production code beyond what a test needs, don't open PRs, and add no AI attribution. Don't test the framework or trivial getters — test behavior that matters and behavior that could break. Read the code before asserting; if the suite is green, say so plainly.
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 · 28 lines · 58 tokens per session scan A ddf127d7a08d
test-author is an agent published in the GitHub repository Alireza29675/teamctl (20 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 516 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
test_gap_agent
A test-review assistant that finds missing unit tests, integration tests, migration tests, and boundary cases in a code change.
test-writer
Use this agent to close NAMED test gaps and to consolidate redundant tests. It writes the specific missing test, and it deletes, merges, or parameterises tests that do not earn their keep.
ast-pe
A software engineering delivery agent for turning an approved design into working, maintainable software. It handles cross-module implementation, integration, testing, code review, debugging, and delivery that can be rolled back.
test-engineer
Design and implement test strategy for a change.
project-quality-gate
Use this agent when you need to verify a repo meets quality standards before a release, merge, or deployment decision.
Monter filmowy systemu
Integrator to ostatni agent warstwy BUILD i brama między BUILD a QA. Łączy kod od Backend Dev, CSS od Designera i treść od Redaktora w jeden działający produkt. Rozwiązuje konflikty, waliduje zgodność z MANIFEST.md i testuje całość E2E.