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/zistica/korveo/skillnpx skills add zistica/korveo --skill skillgit clone --depth 1 https://github.com/zistica/korveoWrote 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/zistica/korveo/skill)<a href="https://agentmods.dev/skills/zistica/korveo/skill"><img src="https://agentmods.dev/badge/skills/zistica/korveo/skill.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 | $0.00087 | $0.00757 |
| Opus 5 | $0.00044 | $0.00378 |
| Sonnet 5 | $0.00017 | $0.00151 |
| Haiku 4.5 | $0.00009 | $0.00076 |
Grade A, and why
korveo 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 4d 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
Korveo — Local Agent Observability
Korveo records every LLM call, tool call, and decision your OpenClaw agent makes. View them at http://localhost:3000. Data never leaves the machine — everything runs in a single Docker container.
This skill provides three commands that hit Korveo's local HTTP API so you can check status and pull trace data without leaving the chat.
Check if Korveo is running
Run: node $SKILL_DIR/korveo.mjs status
Returns one of:
Korveo is running on http://localhost:8000Korveo is not running on …. Start with: docker run -p 3000:3000 -p 8000:8000 zistica/korveo
Show recent traces
Run: node $SKILL_DIR/korveo.mjs traces
Returns the last 5 agent traces formatted like:
Recent agent traces:
1. openclaw_session 3.2s $0.0023 OK
2. openclaw_session 1.8s $0.0011 OK
3. openclaw_session 5.1s $0.0089 ERROR
…
Open http://localhost:3000/traces for the full list.
Show one trace's spans
Run: node $SKILL_DIR/korveo.mjs trace <id>
Returns the trace metadata plus every span with type, model, tokens, cost, and any error message.
Wire OpenClaw to Korveo
This skill only reads from Korveo. To get your OpenClaw agent's traces into Korveo, install the companion exporter:
npm install @korveo/openclaw
…and pass korveoProcessor() into your OpenClaw OTel config. See
https://github.com/zistica/korveo/tree/main/packages/integrations/openclaw.
Start Korveo (if not running)
docker run -p 3000:3000 -p 8000:8000 zistica/korveo
Then open http://localhost:3000.
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.
- 4d ago First seen · 91 lines · 87 tokens per session scan A bf37daad6d55
korveo is a skill published in the GitHub repository zistica/korveo (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 87 tokens to every session and 757 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
aig-agent-redteam
当用户要求 AI/Agent 安全评估、蓝军演习、AI 安全审查、提示词注入测试、MCP/Skill/插件/代码包审计、Agent 工具链滥用测试，或需要生成类似渗透测试报告的 Markdown/HTML 时，必须使用本 skill。本 skill 让 Agent 以授权蓝军视角成为 AI 安全专家，面向 AI 产品、Agent、MCP Server、Skill、代码仓库和 AI 基础设施进行安全演习。优先使用第一性原理推理和真实证据，而不是机械跑 payload 库；脚本只用于 HTTP 指纹识别、证据聚合、报告渲染等确定性辅助任务。.
edgeone skill scanner
Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…
web-exfiltration-detection
Detect data exfiltration via URL path encoding and chained webfetch navigation. Covers fake trusted UI injection, letter-level URL path exfiltration, and multi-hop navigation hijacking. Use when the agent has web/URL fetch capability and stores user memory or personal context.
data-leakage-detection
Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.
indirect-injection-detection
Detect indirect prompt injection (goal hijack). Instructions hidden in "external" content (documents, RAG, web) that the agent processes. Use when the agent has document/RAG/web/file input.
agentic-supply-chain-detection
Detect agentic supply-chain risks: compromised dependencies, malicious plugins/tools/models, and untrusted update sources.