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 workflowgit 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/workflow)<a href="https://agentmods.dev/skills/inclusionai/avernet/workflow"><img src="https://agentmods.dev/badge/skills/inclusionai/avernet/workflow/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/workflow"><img src="https://agentmods.dev/badge/skills/inclusionai/avernet/workflow.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 | $0.00052 | $0.00654 |
| Opus 5.5 | $0.00021 | $0.00262 |
| Sonnet 5.5 | $0.00010 | $0.00131 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
workflow 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
工作流引擎核心命令
管理工作流生命周期，支持以下子命令：
子命令
| 子命令 | 说明 | 示例 |
|---|---|---|
run |
启动工作流 | /workflow run <workflow-id> |
confirm |
确认人工节点（可带 choice） | /workflow confirm --flow-id <id> |
confirm choice: <value> |
选择分支并确认 | /workflow confirm choice: fast --flow-id <id> |
reject |
拒绝当前节点 | /workflow reject --flow-id <id> |
skip |
跳过当前节点 | /workflow skip --flow-id <id> |
retry |
重试当前节点 | /workflow retry --flow-id <id> |
revise |
修改并重新提交 | /workflow revise --flow-id <id> |
submit |
提交表单数据 | /workflow submit --flow-id <id> |
resume |
恢复挂起的工作流 | /workflow resume --flow-id <id> |
workflow_choice 工具
当人工节点处于 waiting 状态且 L1 关键词匹配未命中时，Agent 应使用 workflow_choice 工具解读用户自然语言意图。
参数
flowId(string, required): 等待中的工作流 IDchoice(string, required): 解读后的选择值，必须匹配 inputSchema 中的 enum 值reason(string, optional): 选择原因或用户附加说明
使用时机
- 工作流有人工节点处于 waiting 状态
- 用户发送了自然语言消息（如「批准」「快速处理」「我选深入分析」）
- L1 Hook 关键词匹配未命中（inputSchema 无 keywordAliases 或关键词未匹配）
- Agent 需要解读用户意图并调用 workflow_choice 完成选择
示例
- 用户说「批准」→
workflow_choice(flowId="...", choice="approve") - 用户说「我选方案B」→
workflow_choice(flowId="...", choice="thorough") - 用户说「算了不要了」→ 调用
/workflow reject --flow-id <id>
意图识别规则
- 用户输入
/workflow <子命令>→ 调用 workflow_engine_dispatch 工具，command 参数为原始输入 - 用户在等待中工作流上下文说自然语言 → 先尝试 L1 关键词匹配，未命中则使用 workflow_choice 工具
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 · 55 lines · 52 tokens per session scan A b765a0dff1a7
workflow is a skill published in the GitHub repository inclusionAI/Avernet (593 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 654 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
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, files and bash over the agent-fs drive (ctx.fs…
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…
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…