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/inclusionai/avernet/workflownpx 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.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 | $0.00052 | $0.00654 |
| Opus 5 | $0.00026 | $0.00327 |
| Sonnet 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 5d 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.
- 5d ago First seen · 55 lines · 52 tokens per session scan A b765a0dff1a7
workflow is a skill published in the GitHub repository inclusionAI/Avernet (533 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 654 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
coordinate-agents
Route Codex-native multi-agent orchestration in a Git repository through a local-first, recoverable Agent Bus. Use for role-based planning, task execution, review, recovery, adapters, and human-gated release workflows. The plugin supports Codex CLI, Google Antigravity CLI, Claude, and other configured coding agents.…
coordinate-task
Run a Coordinate Agents Task from requirement clarification through planning, implementation, review, and the human release gate. Hide Agent Bus transport details behind the durable Task API.
coordinate-recover
Diagnose and safely resume Coordinate Agents Tasks after executable failure, non-zero exit, timeout, stale claim, processing message, or Implementer ERROR. Recovery is explicit and never an automatic retry loop.
coordinate-setup
Discover coding CLIs on the current computer and configure a Coordinate Agents implementation agent. Use for setup, executable checks, registered agents, user-level configuration, and project-over-user precedence.
coordinate-review
Review a Coordinate Agents implementation as the Codex Reviewer. Verify the real commit, diff, tests, validation evidence, and specification without modifying the Implementer's product code.
deliberated-review
Review code with multiple specialist subagents, then use gemot to find where they disagree and why. Requires gemot MCP server configured.