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 skills/asterinas/kverus/kverus-evalnpx skills add asterinas/KVerus --skill kverus-evalgit clone --depth 1 https://github.com/asterinas/KVerusWrote 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/skills/asterinas/kverus/kverus-eval)<a href="https://agentmods.dev/skills/asterinas/kverus/kverus-eval"><img src="https://agentmods.dev/badge/skills/asterinas/kverus/kverus-eval.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 5.1 | $0.00038 | $0.00496 |
| Opus 5 | $0.00019 | $0.00248 |
| Sonnet 5 | $0.00008 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
kverus-eval 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.
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.
What it actually says
Evaluate spec modifications in current unstaged changes.
Preferred invocation:
$kverus-eval target=path/to/entry.rs context="<original spec intent>"
If target is provided, prioritize that file but include closely related unstaged spec edits when necessary.
If context is missing, infer original intent from nearby comments, names, and unchanged surrounding code.
Evaluation Scope
Review current unstaged spec-related modifications from these aspects:
- Whether the modification strengthens or weakens the spec.
- Whether the modification changes the original purpose of the spec.
- Whether unnecessary spec content is added.
Required Workflow
- Inspect unstaged diff first.
- Isolate spec-related changes (
requires,ensures, invariants,decreases,recommends, spec/ghost declarations). - Compare modified clauses with previous intent from unchanged code and nearby context.
- Evaluate the three aspects.
- Produce a final score out of 10 with concise justification.
Scoring Policy (Max 10)
Start from 10 and subtract deductions:
- Weakens safety/correctness guarantees without justification: minus 2 to 5.
- Changes original spec purpose or contract intent: minus 2 to 5.
- Adds redundant or unused spec clauses that increase maintenance burden: minus 1 to 3.
- If a change is neutral but clearer, no penalty.
- If a change strengthens spec while preserving intent and avoids redundancy, keep 9 to 10.
Clamp final score to range [0, 10].
Output Format
Return:
- Strength assessment: stronger, weaker, or mixed.
- Intent preservation assessment: preserved or changed.
- Redundancy assessment: none, minor, or significant.
- Score: X/10.
- Short rationale with concrete diff references.
Keep output concise and review-focused.
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.
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.
- 5d ago First seen · 64 lines · 38 tokens per session scan A 460b8c0505a2
kverus-eval is a skill published in the GitHub repository asterinas/KVerus (23 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 496 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.
Other skills, from other repositories
vera-language
Write programs in the Vera programming language. Use when asked to write, edit, debug, or review Vera code (.vera files). Vera is a statically typed, purely functional language with algebraic effects, mandatory contracts, and typed slot references (@T.n) instead of variable names.
vera-language
Write programs in the Vera programming language. Use when asked to write, edit, debug, or review Vera code (.vera files). Vera is a statically typed, purely functional language with algebraic effects, mandatory contracts, and typed slot references (@T.n) instead of variable names.
test-generator
Generate comprehensive test suites including static analysis, unit tests, integration tests, E2E tests, and coverage reports. Triggers: TG, test, 測試, 寫測試, coverage, 覆蓋率, pytest, unittest, 驗證.
code-refactor
Proactively detect and execute code refactoring to maintain DDD architecture and code quality. Triggers: RF, refactor, 重構, 拆分, split, 模組化, modularize, 太長, cleanup.
nsforge-quick-calculate
快速計算（無需會話）。觸發詞：計算, 簡化, 求解, 微分, 積分, 極限, 級數, 不等式, 機率。.
nsforge-usolver-collab
ID: nsforge-usolver-collab Version: 1.0.0 Trigger: 優化, optimize, 最佳解, optimal, 約束求解, constraint solving, USolver.