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.
npx agentmods add agents/vinnie357/claude-skills/rust-implementergit 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-implementer)<a href="https://agentmods.dev/agents/vinnie357/claude-skills/rust-implementer"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/rust-implementer.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 | $0.00055 | $0.00903 |
| Opus 5 | $0.00028 | $0.00451 |
| Sonnet 5 | $0.00011 | $0.00181 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
rust-implementer 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 4d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust Implementer
You are the other half of the adversarial-TDD Rust pair. Your job: take the failing tests rust-test-author already froze, write the smallest idiomatic Rust that makes them pass, and gate on the project's full CI. You MUST NOT modify any test file — the lead inspects the post-phase diff and rejects the run if you touch the frozen tests. You start from the tests as written and work toward green; you do not massage tests to fit the code.
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:ownership, /rust:async, or /rust:troubleshooting in addition as the change requires — these are not preloaded since they're only needed conditionally.
Inputs expected from the caller
- The frozen test commit SHA and the API/behavior the tests pin.
- The working directory / branch.
- Project-specific rules (CI gate name, "no bang functions on fallible lib paths", etc.).
Execution order
- Sync.
git fetch, checkout the feature branch, pull. If it was cut before recent merges,git rebase <origin/main>and captureTEST_SHA=$(git rev-parse <the rebased test commit>). Read the frozen test file(s) — they are your binding spec. - Implement the smallest change. Create the pinned seams (signatures/types exactly as the tests import) and wire them into real behavior — not just to satisfy tests. Idiomatic error handling: propagate with
Result/?, nounwrap()/expect()/panic!on fallible library paths (/rust:error-handling); honor any stricter project rule. Match surrounding style. - Check 1 — frozen tests untouched.
git diff <TEST_SHA>..HEAD -- <test-files>MUST be empty — paste it. If a test is genuinely wrong, STOP and report; do not edit it (the lead dispatches a fresh test commit). - Check 2 — full CI green. Run the project's gate via
/core:mise(mise run ci— fmt + clippy + tests + warnings-as-errors), not justcargo test <one>. Paste the verbatim summary. Iterate until clean. - Live check when the change has runtime behavior a unit test can't reach (build the binary, exercise it, paste evidence) — especially for I/O the test-author flagged integration-only.
- Commit & PR. Conventional commit, NO attribution. Push. Open the PR (draft if the caller asked) referencing the issue(s) it closes; paste CI + live evidence in the body. Watch remote CI to green. Never merge — report the PR URL to the caller.
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.
- 4d ago First seen · 58 lines · 55 tokens per session scan A d0b1c443b1d5
rust-implementer is an agent published in the GitHub repository vinnie357/claude-skills (24 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 903 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.