kverus-strip

kverus-strip is a skill for Claude Code, Codex from asterinas/KVerus. It costs 50 tokens per session (4,122 once invoked), scanned A, original, MIT.

A skill for removing unnecessary proof code from Verus programs while checking that formal verification still succeeds. Proof code gives the checker extra reasoning about program correctness.

In plain words
What is it for?
Use it to simplify selected Verus source directories or Rust files, optionally limiting the cleanup to named functions and supplying a verification command.
Why use it?
It reduces clutter from redundant assertions and proof blocks without removing reasoning that the Verus checker needs.

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 Use it to simplify selected Verus source directories or Rust files, optionally limiting the cleanup to named functions and supplying a verification command.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/asterinas/kverus/kverus-strip"><img src="https://agentmods.dev/badge/skills/asterinas/kverus/kverus-strip.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,122 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 $0.00050 $0.04122
Opus 5 $0.00025 $0.02061
Sonnet 5 $0.00010 $0.00824
Haiku 4.5 $0.00005 $0.00412

Measured 5d ago against content hash f051d32e2f2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kverus-strip 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/simplify_proof.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-strip/SKILL.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Aggressively strip redundant proof code from a Verus codebase while keeping verification passing. Be as aggressive as possible — many proof blocks and assertions exist purely for human readability and are not needed for the SMT solver to succeed.

Preferred invocation:

$kverus-strip verify="<verification command>" target-dirs="<dir1,dir2>"

If verify is missing, ask for it before editing. If target-dirs is missing, first run the proof simplification script for changed files; ask for target-dirs only before doing broader manual proof-code stripping.

Arguments

  • verify (required): The full verification command, e.g. cargo verus focus my_crate.
  • target-dirs (required for broader manual stripping): Comma-separated source directories or single .rs files to scan, e.g. src/,specs/ or src/model/owners.rs. A path the script would otherwise need to discover can be passed directly here.
  • function (optional): Comma-separated function short names to restrict stripping to, e.g. lemma_index_bounds. Only matching functions are processed; all others in the file are left untouched.
  • base (optional): Git base ref for changed-file discovery, e.g. origin/main.

Shared Verus References

If understanding Verus proof constructs (proof blocks, ghost/tracked values, spec/proof functions) is needed before deciding deletions, read the relevant reference under ../kverus-common/references/ before editing.

Proof Simplification Script

For routine redundant proof-statement cleanup, prefer the bundled script before manual stripping:

. "$AGENT_DIR/kverus.env"
"$KVERUS_PYTHON" "$AGENT_DIR/skills/kverus-strip/scripts/simplify_proof.py" \
  --base <git-base> \
  --target-dir '<dir1,dir2>' \
  --verify-command '<verification command>' \
  --format-command '<format command>'

The script scans changed .rs files when no --target-dir or --file is provided. It simplifies at function scope, matches the src/refiner/simplifier.py policy, skips runtime assert!(...), never removes assert(false), skips functions containing admit, assume, or #[verifier::external_body] unless --deep-clean is set, removes one proof statement at a time, and keeps the removal only when the verification command still succeeds. With tree-sitter-verus, candidates include standalone function-call statements in proof fn, proof {}, and assertion proof blocks; executable calls are extracted but never offered for deletion. The default mode requires tree-sitter-verus and errors out if it is missing; pass --text-only to force the lower-precision text-based (asserts-only) parser. Use --dry-run to list candidates without editing.

Read the full file on GitHub · 356 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. 5d ago Changed f051d32e2f2a
  2. 9d ago First seen · 356 lines · 50 tokens per session scan A 3e5bab256f06

Subscribe to this mod's changes

kverus-strip is a skill published in the GitHub repository asterinas/KVerus (24 stars, last pushed 5d ago), licensed MIT. It adds 50 tokens to every session and 4,122 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.