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 skills add asterinas/KVerus --skill kverus-reviewgit 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-review)<a href="https://agentmods.dev/skills/asterinas/kverus/kverus-review"><img src="https://agentmods.dev/badge/skills/asterinas/kverus/kverus-review/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/skills/asterinas/kverus/kverus-review"><img src="https://agentmods.dev/badge/skills/asterinas/kverus/kverus-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00047 | $0.03199 |
| Opus 5.5 | $0.00019 | $0.01280 |
| Sonnet 5.5 | $0.00009 | $0.00640 |
| Haiku 4.5 | $0.00005 | $0.00320 |
Grade A, and why
kverus-review 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 1mo 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Verus code changes for exec semantics, =~= usage, and verification quality before committing.
Preferred invocation:
$kverus-review verify="<verification command>"
$kverus-review commit=abc1234 verify="<verification command>"
If verify is missing, ask for it and stop. commit is optional.
Objective
Check uncommitted changes (or changes since a given commit) for four categories of issues and produce a structured report:
- Exec code modifications, whether they change runtime semantics, and whether their preservation comments are compliant.
- New
=~=introductions and whether they can be replaced by==. - Deleted comments and whether the deletion is justified.
- Verification pass/fail and problematic warnings.
Arguments
commit(optional): A git commit hash. When provided, review changes from that commit to HEAD. When omitted, review all uncommitted changes (unstaged + staged).verify(required): The target repository's documented verification command.
Shared Verus References
Locate reference files under the kverus-common skill's references/ directory by topic:
| Topic | Reference File |
|---|---|
Set / extensional equality / =~= vs == |
set-reasoning.md |
| Verus syntax / modes / exec-vs-spec-vs-proof | verus-syntax-quickref.md |
| Ghost / tracked / erasure | ghost-tracked.md |
| Verification error triage | common-errors.md |
| Exec-code reason and original-source comments | exec-code-preservation.md |
When evaluating =~= usage, read the "Set Extensional Equality via Bidirectional Forall" section from the set-reasoning.md reference.
When the diff modifies exec code, read and apply exec-code-preservation.md.
Required Workflow
Step 0: Collect Change Set
Determine the diff scope:
With commit argument:
# List changed .rs files
git diff <commit>..HEAD --name-only -- '*.rs'
# Get diff content for a specific file
git diff <commit>..HEAD -- <file>
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.
- 1mo ago Changed · +11 lines 5d4ecf91e381
- 1mo ago Changed · +1 lines dc2a96b039b4
- 1mo ago First seen · 289 lines · 47 tokens per session scan A 2ab80306253e
kverus-review is a skill published in the GitHub repository asterinas/KVerus (27 stars, last pushed 15d ago), licensed MIT. It adds 47 tokens to every session and 3,199 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 2026-08-30.
Other skills, from other repositories
github-code-review
Review code changes by analyzing git diffs, leaving inline comments on PRs, and performing thorough pre-push review. Works with gh CLI or falls back to git + GitHub REST API via curl.
github
GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…
requesting-code-review
Pre-commit verification pipeline — static security scan, baseline-aware quality gates, independent reviewer subagent, and auto-fix loop. Use after code changes and before committing, pushing, or opening a PR.
review
Review code changes, pull requests, patches, or a scoped code area for actionable correctness, security, compatibility, and test risks with file and line evidence. Use for review or audit requests; do not use for general proofreading, feature implementation, or debugging a reported failure when the user wants a fix.
code-review-feedback
Use when receiving code-review feedback, before implementing suggestions — especially when feedback seems unclear or technically questionable. Verify against the codebase and reason about each item instead of agreeing performatively or implementing blindly.
debug
Diagnose a concrete failure, regression, crash, hang, flaky test, or incorrect runtime behavior by reproducing it, testing hypotheses, and identifying the evidence-backed root cause. Use when symptoms or failing output exist; do not use for feature implementation without a failure, general code review, or a conceptual…