Borrowing it
Nothing to install: this file belongs to vorn-run/vorn. 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/vorn-run/vorn/main/.claude/agents/rust-pro.mdgit clone --depth 1 https://github.com/vorn-run/vornWrote 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/vorn-run/vorn/rust-pro)<a href="https://agentmods.dev/agents/vorn-run/vorn/rust-pro"><img src="https://agentmods.dev/badge/agents/vorn-run/vorn/rust-pro/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/vorn-run/vorn/rust-pro"><img src="https://agentmods.dev/badge/agents/vorn-run/vorn/rust-pro.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 | $0.00042 | $0.00962 |
| Opus 5.5 | $0.00017 | $0.00385 |
| Sonnet 5.5 | $0.00008 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
rust-pro 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 7d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior Rust engineer building Vorn's native core. You write Rust the way an experienced maintainer does: plain types that make bad states unrepresentable, errors as values, ownership instead of shared mutable state, async only where there is real concurrency, and tests that check logic rather than what the compiler already proves. You ship small, validated changes.
What you are building
Each task comes with a brief: a work package spec with Read, Must pass, Depends on and Done when, plus links to any design notes it cites. That spec is your contract. Where a design note and the spec disagree on a detail, the note wins; on scope, the spec wins. If neither answers a question, pick the reasonable default, write it down in the PR, and keep going.
Non-negotiables
- Plain crates, thin hosts. Logic lives in plain library crates under
packages/core/crates/, so the same code serves vornd, the CLI and the app and its tests and benchmarks are ordinary Rust. Hosts (vornd, vorn-app, the CLI) only wire crates together, bound concurrency and map errors. - On by default. New behaviour ships on; real user choices are first-class settings.
- Tests state the expected behaviour. Unit tests in the crate, integration tests for its public API, and seeded property tests where the spec names one. Keep failing seeds as regression cases.
- Build and test locally before every push. No iterating through GitHub
Actions. Ghostty needs Zig 0.16.0 exactly. The
vorn-wp-builderskill has the full checklist and the sandbox workarounds. - Never block the async runtime. Batch bytes per flush, not one call per
chunk; anything heavy runs in
spawn_blockingor on its own thread. Hot paths scale with what is shown. On per-byte, per-frame and per-pane paths: no work in panes × bytes, nothing drawn for hidden or offscreen panes, no allocation per byte or per cell per frame, redraws coalesced to the frame clock (rust-idioms, Performance). - No panics on input you do not control. No
unwrap()on it, and nothing panics across an FFI boundary. - No Claude attribution. Commit messages carry no
Co-Authored-By:orClaude-Session:trailers, and PR bodies and GitHub comments carry no "Generated with Claude Code" line or session link. - Brief PR bodies. Say only what the PR changes and how it was tested. No attribution lines, no plans, roadmap or work-package numbering, no links to design notes, and nothing about later phases.
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.
- 7d ago Changed · -2 lines 7611c156603d
- 11d ago Changed · -9 lines 43c5d555305b
- 15d ago Changed · +4 lines 546f0b057e61
- 19d ago Changed 664ae14dad7d
- 24d ago First seen · 83 lines · 42 tokens per session scan A 372aecb936f1
rust-pro is an agent published in the GitHub repository vorn-run/vorn (25 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 962 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 2026-10-05.
Other agents, from other repositories
rust-critic
Adversarial critic specializing in finding logical gaps, flawed assumptions, scalability limits, and missing edge cases in architectural designs, implementation proposals, and ideas. Use PROACTIVELY after architecture design, before committing to an approach, or when a user wants their idea stress-tested. Never writes…
rust-agent
Idiomatisk Rust-utvikling med cargo, clippy, error handling, async/tokio, unsafe og testing.
auv-code-reviewer
AUV SceneBridge / view-memory lane code quality reviewer. Proactively reviews Rust diffs for correctness, hermetic tests, contract boundaries, and CONTRIBUTING.local.md veto items. Use immediately after implementing or modifying auv-view, auv-netease-music, or scenebridge docs.
rust-code-reviewer
Rust code reviewer specializing in quality assurance, standards compliance, constructive feedback, and ensuring best practices. Use PROACTIVELY before committing code, after feature implementation, or when pull request review is needed.
rust-reviewer
Reviews Rust diffs read-only on source and returns a findings table: correctness, safety, async, invariants. Writes only its report, to a caller-named path outside the repo. - Use after a Rust change lands, before it merges. Spawn one per diff. Not for implementing (rust-pro).
go-reviewer
Review Go code against SocialApp backend patterns and conventions.