kverus-run

kverus-run is a skill for Claude Code, Codex from asterinas/KVerus. It costs 47 tokens per session (3,462 once invoked), scanned A, original, MIT.

An end-to-end workflow for converting Rust code into Verus code and checking it with formal proofs. Formal verification checks whether code meets stated rules, beyond ordinary tests.

In plain words
What is it for?
Use it on a Rust file or directory when you need migrated Verus code with specifications and verification results.
Why use it?
It brings migration, specification, error fixing, evaluation, semantic review, and final cleanup into one documented process.

Skill for Claude CodeCodex

Written for Claude Code and Codex: user-invocable in frontmatter, but also agents/openai.yaml present. Also seen: mentions subagents; mentions Codex; $skill-name invocation.

Good fit Use it on a Rust file or directory when you need migrated Verus code with specifications and verification results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/asterinas/kverus/kverus-run
Install

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.

Any agent
npx skills add asterinas/KVerus --skill kverus-run
Clone the repo
git clone --depth 1 https://github.com/asterinas/KVerus

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for kverus-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/asterinas/kverus/kverus-run.svg)](https://agentmods.dev/skills/asterinas/kverus/kverus-run)
Your own site
<a href="https://agentmods.dev/skills/asterinas/kverus/kverus-run"><img src="https://agentmods.dev/badge/skills/asterinas/kverus/kverus-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,462 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 271
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.03462
Opus 5 $0.00023 $0.01731
Sonnet 5 $0.00009 $0.00692
Haiku 4.5 $0.00005 $0.00346

Measured 3d ago against content hash 144a5234880e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

kverus-run 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 3d 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.

skills/kverus-run/SKILL.md · 325 lines

How it starts

The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the complete Rust-to-Verus pipeline for one file or a directory of .rs files.

Preferred invocation:

$kverus-run target=path/to/file_or_dir verify="<verification command>"

If either target or verify is missing, ask for the missing value and stop.

If out_dir is missing, default to .kverus-run-output/ under the workspace root.

Pipeline Overview

Phase 0  Pre-flight ─────── validate inputs, snapshot originals
Phase 1  Migrate ─────────── Rust → Verus compatible code
Phase 2  Stage ──────────── git add migrated files
Phase 3  Spec ───────────── add requires/ensures/invariants
Phase 4  Fix ────────────── repair verification failures from spec
Phase 5  Eval ───────────── score spec quality (unstaged changes)
Phase 6  Semantic Audit ──── verify migration preserved runtime behavior
         ── QUALITY GATE ──  pause if critical semantic changes found
Phase 7  Postprocess ────── final review rules, assert simplification, fmt
Phase 8  Report ─────────── final summary

Shared Verus References

All phases that edit Verus code should consult ../kverus-common/references/ when encountering unfamiliar Verus syntax, modes, ghost/tracked values, loop invariants, quantifiers, or tokenized state-machine rules.


Phase 0: Pre-flight

  1. Verify target exists.
  2. Detect input type:
    • If target is a single .rs file: single-file mode. Set FILE_LIST = [target].
    • If target is a directory: directory mode. Discover all .rs files recursively. Sort by dependency order when possible (leaf modules first), otherwise alphabetical. Set FILE_LIST accordingly.
  3. Verify the git workspace is clean for the files in FILE_LIST (no uncommitted changes). If dirty, warn the user and ask whether to continue.
  4. Snapshot originals for audit:
    • Create a temporary directory: ORIG_DIR=$(mktemp -d).
    • Copy each file from FILE_LIST into ORIG_DIR preserving relative path structure.
    • Example: if target=src/lib.rs, copy to $ORIG_DIR/src/lib.rs.
  5. Create out_dir if it does not exist.
  6. Set AGENT_DIR to the installed agent directory for script calls. Skills are read from $AGENT_DIR/skills.
  7. If KVERUS_POSTPROCESS_RULE_REPO is configured, run the postprocess checker with --cache-status. When the cache is stale or missing and subagents are available, delegate one --refresh-only command to a subagent. The subagent must make no source edits and preserve the old cache on failure. Continue the pipeline immediately; never perform or wait for a GitHub request in the main agent. If no subagent is available, proceed with cached or static rules.
  8. Print a summary: mode (single/directory), file count, target path, verify command.

Read the full file on GitHub · 325 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 3d ago Changed · +1 lines 144a5234880e
  2. 8d ago First seen · 324 lines · 47 tokens per session scan A fc003fe18e5c

Subscribe to this mod's changes

kverus-run is a skill published in the GitHub repository asterinas/KVerus (23 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 3,462 once invoked, about $0.0002 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.