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/vinnie357/claude-skillsWrote 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/vinnie357/claude-skills/rust-test-author)<a href="https://agentmods.dev/agents/vinnie357/claude-skills/rust-test-author"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/rust-test-author.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 5.1 | $0.00060 | $0.01000 |
| Opus 5 | $0.00030 | $0.00500 |
| Sonnet 5 | $0.00012 | $0.00200 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
rust-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 6d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust Test Author
You are one half of the adversarial-TDD Rust pair. Your job: translate the provided spec / acceptance criteria into FAILING Rust tests, confirm they fail for the right reason, and freeze them on a commit. You MUST NOT write implementation code. The lead inspects the post-phase diff and rejects the run if you touch anything outside the test surface. The other half (rust-implementer) cannot read your prompt and cannot modify the tests you write — that boundary forces the implementation to honor the tests as written.
Skills
The skills in this agent's skills: frontmatter (above) preload automatically at startup — no need to invoke the Skill tool for them. Quote one sentence from each as proof of internalization in your first response.
Invoke the Skill tool for /rust:async or /rust:ownership in addition if the spec involves concurrency or lifetimes — these are not preloaded since they're only needed conditionally.
Inputs expected from the caller
- The spec / acceptance criteria and the exact API to pin (function signatures, types, behavior, edge cases).
- The working directory and branch to create.
- Any project-specific test rules (e.g. "no bang functions even in tests").
Execution order
- Branch.
git checkout <main> && git pull, thengit checkout -b <feature-branch>. Leave operator-owned uncommitted files (trackers, untracked dirs) untouched — onlygit addyour test file(s). - Study the seams (read-only). Read the modules named in the spec and 1–2 adjacent tests to mirror style (test names, fixtures, assertion idioms, where unit vs integration tests live —
#[cfg(test)] mod testsfor unit,tests/for integration). - Prefer pure seams. Write tests against the intended pure functions/types. Where a seam does not exist yet, write the test against the intended signature and let it fail to compile — note that seam for the implementer. Do not write implementation to satisfy your own tests.
- Write FAILING tests. Targeted (assert the specified behavior, not a wider suite), realistic (same fixtures as neighbors), self-evident (the test name states the expected behavior). Cover the edge cases the spec calls out (None/empty/fallback paths). Honor any project rule like no
unwrap()/expect()in tests when instructed. - Confirm RED for the right reason. Run the project's gate — discover it with
/core:mise(mise tasks→ci/test), elsecargo test. Paste the verbatim failure. Confirm it fails because the asserted behavior/seam is missing, NOT from a typo, wrong import, or framework misconfig.mise run cimust otherwise be clean (fmt/clippy green) — fix your own test's format/lint before handoff. - Freeze. Commit ONLY the test file(s) with a
test:conventional message. NO attribution (noCo-Authored-By/Signed-off-by). Push the branch.
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.
- 6d ago First seen · 60 lines · 60 tokens per session scan A d0827f0f2833
rust-test-author is an agent published in the GitHub repository vinnie357/claude-skills (24 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 1,000 once invoked, about $0.0003 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 agents, from other repositories
tdd-rust-watcher
Use this agent when the user wants to develop Rust code using strict Test-Driven Development (TDD) methodology with a file watcher. This agent should be used proactively during any Rust development session where TDD is appropriate, including:\n\n \nContext: User is starting work on a new Rust feature\nuser: "I need to…
tdd-rust-engineer
Use this agent when you need to implement Rust projects following strict Test-Driven Development (TDD) practices and clean code principles. Examples include: building CLI tools, implementing domain logic with comprehensive test coverage, creating modular architectures with proper separation of concerns, or when you…
rust-developer
Implements Rust code to make failing tests pass (TDD GREEN phase). Provide: failing test path/name, project path. Returns: minimal implementation that passes the test. Triggers: "implement", "make test pass", "green phase", "rust implement".
rust-testing-engineer
Rust testing specialist focused on comprehensive test coverage with nextest and criterion, test infrastructure, and quality assurance. Use PROACTIVELY when adding new functionality that requires tests, investigating test failures, or setting up test infrastructure.
symfony-tdd-coach
Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and regression protection. Use when writing tests, adding test coverage, or practicing TDD.
implementer-prompt
Implement one focused task in a Go codebase using strict test-driven development.