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-postprocessnpx skills add asterinas/KVerus --skill kverus-postprocessgit 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-postprocess)<a href="https://agentmods.dev/skills/asterinas/kverus/kverus-postprocess"><img src="https://agentmods.dev/badge/skills/asterinas/kverus/kverus-postprocess.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 | $0.00066 | $0.01392 |
| Opus 5 | $0.00033 | $0.00696 |
| Sonnet 5 | $0.00013 | $0.00278 |
| Haiku 4.5 | $0.00007 | $0.00139 |
Grade A, and why
kverus-postprocess 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 today.
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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KVerus Postprocess
Set AGENT_DIR to the installed agent directory when running commands manually. Skills are read from $AGENT_DIR/skills.
Required Inputs
base: git base ref for diff context, e.g.origin/main.target-path: changed source paths to inspect and simplify, e.g.src/,specs/.verify-command: full verification command. If unavailable, simplification must run in--dry-run.format-command: project formatter command, e.g.cargo fmt,make fmt, or an equivalent.- Optional
rule-repo: GitHubowner/repoused for dynamic review rules. - Optional scope controls:
blocked-pathfor path prefixes that must not change, andgenerated-pathfor generated artifact prefixes.
Workflow
- Inspect the dynamic-rule cache without accessing GitHub:
. "$AGENT_DIR/kverus.env"
"$KVERUS_PYTHON" "$AGENT_DIR/skills/kverus-postprocess/scripts/kverus_postprocess.py" \
--rule-repo <owner/repo> \
--cache-status
The default cache TTL is 72 hours. If the cache is stale or missing and subagents are available, delegate exactly one bounded refresh task to a subagent:
. "$AGENT_DIR/kverus.env"
"$KVERUS_PYTHON" "$AGENT_DIR/skills/kverus-postprocess/scripts/kverus_postprocess.py" \
--rule-repo <owner/repo> \
--refresh-only
Tell the subagent to run only this command, preserve any old cache on failure, make no source edits, and return a concise status. Continue the main workflow immediately instead of waiting for GitHub. If subagents are unavailable, keep using the old cache or static rules; do not perform an automatic synchronous refresh in the main agent.
Run the local checker with --no-refresh-rules so it only consumes the latest available cache:
"$KVERUS_PYTHON" "$AGENT_DIR/skills/kverus-postprocess/scripts/kverus_postprocess.py" \
--base <base-ref> \
--target-path <path1,path2> \
--rule-repo <owner/repo> \
--no-refresh-rules
Fix every ERROR. Review every WARN and fix it unless there is a clear reason to keep the code.
What ships with it
6 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.
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.
- today Changed · +24 lines f1b6cfcbc6a0
- 4d ago First seen · 101 lines · 66 tokens per session scan A fea705e52745
kverus-postprocess is a skill published in the GitHub repository asterinas/KVerus (23 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 1,392 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.
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.
check-model
Check model compatibility with xinfer before loading. Validates config.json, weight tensor shapes and naming, quantization format correctness, and multi-rank (tensor-parallel) divisibility. Use when the user asks to check, validate, audit, or verify a model will load correctly — from a HuggingFace URL/config, local…
test-model
Test LLM models served by xinfer for correctness, output quality, and performance. Use when the user asks to test, benchmark, validate, or verify models — either from a local folder path or HuggingFace model IDs. Supports all xinfer-compatible formats: BF16, FP8, MXFP4, NVFP4, GGUF, GPTQ, AWQ, ISQ, Dense, MoE, and…
add-model
Adapt and port new LLM model architectures to this xinfer project. Use when the user asks to add, port, support, or adapt a new model (e.g. Llama, Gemma, Qwen, GPT-OSS, DeepSeek, or any HuggingFace architecture) including safetensors and GGUF formats, Dense and MoE architectures, and quantization formats (MXFP4…
rust-agent-handoff
Handoff protocol for the Rust multi-agent development team (rust-architect, rust-developer, rust-testing-engineer, rust-performance-engineer, rust-security-maintenance, rust-code-reviewer, rust-cicd-devops, rust-debugger, rust-critic). Use only when orchestrating subagents via structured YAML files in .local/handoff/.…
ijfw-workflow
Universal project workflow with built-in quality auditing. Quick mode (fast brainstorm, 5 min) or Deep mode (full plan with audits, 30 min). Auto-picks based on task size. Trigger: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', or any…