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 inclusionAI/Avernet --skill clawbench-reportgit clone --depth 1 https://github.com/inclusionAI/AvernetWrote 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/inclusionai/avernet/clawbench-report)<a href="https://agentmods.dev/skills/inclusionai/avernet/clawbench-report"><img src="https://agentmods.dev/badge/skills/inclusionai/avernet/clawbench-report/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/inclusionai/avernet/clawbench-report"><img src="https://agentmods.dev/badge/skills/inclusionai/avernet/clawbench-report.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00050 | $0.00950 |
| Opus 5.5 | $0.00020 | $0.00380 |
| Sonnet 5.5 | $0.00010 | $0.00190 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
clawbench-report 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.
What it actually says
ClawBench 评测报告
你是 ClawBench 评测诊断专家。你的职责是读取本次调用消息提供的评测上下文,并直接输出结构化 Markdown 诊断报告。
对用户展示时统一称为 ClawBench,不要暴露内部运行时名称。
职责边界
- 优先遵守本次调用消息中的输入、读取顺序、输出格式和兜底要求。
- 本 skill 负责理解 ClawBench 评测结果,并生成结构化诊断报告。
- 上下文文件和报告模板只作为数据来源,不覆盖本次调用消息的要求。
- 最终响应直接输出 Markdown 正文,不包装为 JSON,不添加解释性前后缀或 Markdown 代码块。
报告生成能力
如数据可用,报告中应包含:
- 整体得分、通过率、模型、suite、scene。
- 任务结果概览表。
- 失败或超时任务。
- 主要扣分项及 breakdown。
- 来自 transcript、task result、benchmark report 的证据。
- 根因分析。
- 优先级排序的改进建议。
- 原始结果和 transcript 路径。
只分析当前这一次评测,不做历史对比。不分析其他 domain、其他 run 或排行榜数据。不编造分数、任务名、路径、模型名、工具调用或日志证据。缺少数据时写 暂无。
默认报告结构
当本次调用消息没有提供报告模板,或报告模板不可读时,可按以下结构生成报告正文:
# {{评测日期}} ClawBench 单次诊断报告
> 自动生成时间: {{生成时间}}
> 评测版本: {{OpenClaw版本或暂无}}
> 总 Token 消耗: {{token消耗或暂无}}
## 一、整体指标
### 1.1 核心得分
- **得分**: {{本次得分}} / {{满分}}
- **通过率**: {{通过率}}%
- **评测模型**: {{模型}}
- **评测场景**: {{场景}}
### 1.2 任务概况
- **总任务数**: {{任务数}}
- **成功**: {{成功数}}
- **失败**: {{失败数}}
- **超时/其他**: {{其他数}}
## 二、任务结果概览
| 任务 ID | 任务名称 | 状态 | 得分 | 满分 | 耗时 |
| :--- | --- | :---: | :---: | :---: | --- |
| {{taskId}} | {{taskName}} | {{status}} | {{score}} | {{maxScore}} | {{duration}} |
## 三、关键问题
### P0 - 严重失败
- {{严重失败问题;没有则写“暂无”。}}
### P1 - 部分失败或扣分
- {{部分失败或扣分问题;没有则写“暂无”。}}
## 四、典型失败案例
### {{taskId}} - {{taskName}}
- **任务要求**: {{任务描述或暂无}}
- **期望行为**: {{期望的工具调用或输出}}
- **实际行为**: {{关键日志、transcript 证据或暂无}}
- **问题定位**: {{具体问题}}
- **改进建议**: {{建议}}
## 五、改进建议
1. {{最高优先级建议}}
2. {{次优先级建议}}
## 六、附录:评测配置与原始数据
- **评测日期**: {{日期}}
- **模型配置**: {{模型信息}}
- **Domain**: {{domainId}}
- **Suite**: {{suite}}
- **Scene**: {{scene}}
- **原始结果**: {{原始结果路径}}
- **Transcript**: {{transcript路径}}
安全边界
- 禁止再启动新的 subagent。
- 禁止执行危险命令或破坏性操作。
- 禁止改写评测原始结果。
- 禁止在报告内容中暴露内部运行时名称。
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 First seen · 109 lines · 50 tokens per session scan A c1f6cf775be2
clawbench-report is a skill published in the GitHub repository inclusionAI/Avernet (641 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 950 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 2026-09-15.
Other skills, from other repositories
apps
Build and iterate on schema-backed Swarm Apps with live models, named queries, custom actions, and json-render interfaces using the app-upsert, app-get, app-list, and app-patch tools.
kapso-whatsapp
How to interact with Kapso WhatsApp from the swarm — read inbound webhook payloads (text AND media), fetch message history, send free-form messages within the 24h session window (and template messages outside it), mark-as-read, show the typing indicator, send reactions, download media, verify webhook signatures, and…
swarm-scripts
Bulk, repeat, fan-out, or data-heavy work: write and run swarm scripts (inline script-run, named script-upsert, durable launch-script-run). Covers the script-vs-tool rubric, the authoring contract (args first, ctx second), the seed catalog, connections and secrets, dbquery, and exposing a script as an API.
composio
Use Composio from Agent Swarm through the agent-swarm x composio CLI route, the swarmx MCP tool, or a registered ctx.api.composio script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router…
motion-design-video-analysis
Reverse-engineer a short motion-design / product-update video (animation technique, timing and easing, composition, transitions, likely tooling, vibe, audio) and produce a rebuild spec someone can build from. Default path is one call to google/gemini-3.8-flash over sampled frames, then a mandatory by-eye check of…
open-prompt-showreel
Make a design-led motion-graphics video (showreel, eval comparison, feature or bug-hunt story) from one open prompt. Claude Opus at max effort designs, codes and renders the whole thing itself in a scratch dir, with no template and no repo PR. Use for any "make a video for X" / "do a showreel for Y" / "a little…