kverus-semantic-audit

kverus-semantic-audit is a skill for Claude Code, Codex from asterinas/KVerus. It costs 59 tokens per session (2,079 once invoked), scanned A, original, MIT.

An audit process for comparing Rust source code with a Verus rewrite. Verus is a Rust-based tool for formally checking that programs meet stated rules.

In plain words
What is it for?
Checking Rust-to-Verus migrations, reviewing matched source files, and writing per-file reports about possible behavior changes.
Why use it?
It finds executable-code differences that could change what the program does after migration, without treating proof-only changes as runtime changes.

Skill for Claude CodeCodex

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

Good fit Checking Rust-to-Verus migrations, reviewing matched source files, and writing per-file reports about possible behavior changes.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/asterinas/kverus/kverus-semantic-audit/github.svg)](https://agentmods.dev/skills/asterinas/kverus/kverus-semantic-audit)
Your own site
<a href="https://agentmods.dev/skills/asterinas/kverus/kverus-semantic-audit"><img src="https://agentmods.dev/badge/skills/asterinas/kverus/kverus-semantic-audit/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.

agentmods 80×15 button for kverus-semantic-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/asterinas/kverus/kverus-semantic-audit"><img src="https://agentmods.dev/badge/skills/asterinas/kverus/kverus-semantic-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,079 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 pass 7 Sept 2026
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 $0.00059 $0.02079
Opus 5 $0.00030 $0.01040
Sonnet 5 $0.00012 $0.00416
Haiku 4.5 $0.00006 $0.00208

Measured 9d ago against content hash 36de15cd5ffa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kverus-semantic-audit 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/collect_exec_diffs.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-semantic-audit/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit whether a Rust-to-Verus migration preserved executable semantics.

Preferred invocation:

$kverus-semantic-audit rust_dir=path/to/rust verus_dir=path/to/verus out_dir=path/to/out

If any of rust_dir, verus_dir, or out_dir is missing, ask for the missing value and stop.

Objective

Compare each Rust source file with its Verus counterpart and report cases where executable behavior appears different.

This skill is not a style review and not a proof review. Ignore differences that only affect Verus specifications, proofs, ghost state, attributes, wrappers, or verifier annotations unless they also change executable behavior.

Required Workflow

  1. Run the bundled diff collector:

    . "$AGENT_DIR/kverus.env"
    

"$KVERUS_PYTHON" "$AGENT_DIR/skills/kverus-semantic-audit/scripts/collect_exec_diffs.py"
--rust-dir <rust_dir>
--verus-dir <verus_dir>
--out-dir <out_dir>


2. Read `<out_dir>/audit_index.json` first. It lists matched files, missing files, files with normalized executable-code diffs, and files with critical declaration-token diffs.
3. Before reading the full diff, inspect each file entry's `key_token_changes`. These flag changes to critical Rust API/safety tokens such as `unsafe`, `pub(...)` visibility, public modules/re-exports, `async`, `const fn`, `extern`, ABI strings, and `static mut`.
4. For each file with `has_exec_diff: true`, read the generated markdown under `<out_dir>/file_diffs/`. The markdown includes a "Key Token Changes" section when the collector detected critical token changes.
5. Inspect the original files directly when a diff is ambiguous. Use `rg`, `sed`, and nearby dependencies as needed.
6. Decide whether each executable difference is:
- `semantic-change`: runtime behavior, side effects, panic behavior, return values, control flow, aliasing/mutation, memory ordering, concurrency behavior, or error handling changed.
- `likely-equivalent`: syntax or structure changed but executable behavior is preserved.
- `uncertain`: more context, build configuration, macro expansion, or domain knowledge is needed.
7. Write the final reports into `<out_dir>`:
- `<out_dir>/semantic_audit_summary.md`
- `<out_dir>/semantic_audit_findings.json`
- optional per-file detail reports under `<out_dir>/semantic_reports/`.

Read the full file on GitHub · 160 lines

Files

What ships with it

2 files 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. 9d ago First seen · 160 lines · 59 tokens per session scan A 36de15cd5ffa

Subscribe to this mod's changes

kverus-semantic-audit is a skill published in the GitHub repository asterinas/KVerus (24 stars, last pushed 6d ago), licensed MIT. It adds 59 tokens to every session and 2,079 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.