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 commands/huifer/claude-code-seo/workflow-automationgit clone --depth 1 https://github.com/huifer/claude-code-seoWrote 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/commands/huifer/claude-code-seo/workflow-automation)<a href="https://agentmods.dev/commands/huifer/claude-code-seo/workflow-automation"><img src="https://agentmods.dev/badge/commands/huifer/claude-code-seo/workflow-automation.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 | $0.00024 | $0.04590 |
| Opus 5 | $0.00012 | $0.02295 |
| Sonnet 5 | $0.00005 | $0.00918 |
| Haiku 4.5 | $0.00002 | $0.00459 |
Grade A, and why
workflow-automation 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.
How it starts
The opening of the file, as written. The whole thing — 702 lines — stays where its author put it; the contents beside it link to each section on GitHub.
完整实现
工作流定义
工作流是多个任务的有序编排,支持:
- 顺序执行 - 任务按定义顺序依次执行
- 并行执行 - 多个任务同时执行
- 条件分支 - 根据条件执行不同路径
- 错误处理 - 失败重试和回滚
- 数据传递 - 任务间传递数据
工作流结构
name: "comprehensive-geo-workflow"
description: "完整的 GEO 优化工作流"
version: "1.0.0"
author: "SEO Team"
created: "2024-02-15"
# 触发器配置
triggers:
- type: "schedule"
cron: "0 9 * * 1" # 每周一上午 9:00
enabled: true
- type: "event"
event: "competitor-surpassed"
enabled: true
- type: "manual"
enabled: true
# 全局变量
variables:
domain: "yoursite.com"
competitors: "comp1.com,comp2.com,comp3.com"
team_email: "[email protected]"
slack_channel: "#seo-alerts"
# 全局配置
config:
timeout: 3600 # 总超时时间(秒)
retry_on_failure: true
max_retries: 3
parallel_tasks: 5
notify_on_complete: true
# 工作流步骤
steps:
# 第一步:内容审计
- id: audit
name: "GEO 内容审计"
description: "对网站进行全面的内容审计"
command: "/geo-content-audit"
params:
domain: "{{variables.domain}}"
detailed: true
timeout: 300
retry: 3
on_success: citation-monitor
on_failure: notify-error
continue_on_failure: false
# 第二步:引用监控
- id: citation-monitor
name: "AI 引用监控"
description: "监控 AI 搜索引擎的引用情况"
command: "/geo-citation-monitor"
params:
url: "https://{{variables.domain}}"
period: 7
timeout: 180
retry: 2
depends_on: audit
on_success: competitor-compare
on_failure: notify-error
# 第三步:竞争对手对比
- id: competitor-compare
name: "竞争对手对比"
description: "对比分析竞争对手表现"
command: "/geo-competitor-compare"
params:
you: "{{variables.domain}}"
competitors: "{{variables.competitors}}"
timeout: 240
retry: 2
depends_on: citation-monitor
on_success: generate-report
on_failure: notify-error
# 第四步:生成报告(并行)
- id: generate-report
name: "生成综合报告"
description: "生成多格式 GEO 综合报告"
parallel:
# 子步骤 4a:执行摘要
- id: exec-summary
name: "生成执行摘要"
command: "/generate-report"
params:
type: "executive-summary"
domain: "{{variables.domain}}"
period: 30
format: "pdf"
timeout: 120
on_complete: send-report
# 子步骤 4b:技术分析
- id: tech-analysis
name: "生成技术分析"
command: "/generate-report"
params:
type: "technical-analysis"
domain: "{{variables.domain}}"
format: "html"
include-charts: true
timeout: 180
on_complete: send-report
# 子步骤 4c:交互式报告
- id: interactive-report
name: "生成交互式报告"
command: "/generate-report"
params:
type: "geo-comprehensive"
domain: "{{variables.domain}}"
period: 30
format: "html"
interactive: true
timeout: 150
on_complete: send-report
# 第五步:发送报告
- id: send-report
name: "发送报告给团队"
description: "通过邮件发送生成的报告"
action: "send_email"
params:
to: "{{variables.team_email}}"
subject: "📊 GEO 综合报告 - {{date}}"
body: |
亲爱的团队,
附件是最新的 GEO 综合报告,包含以下内容:
1. 执行摘要(PDF)
2. 技术分析(HTML)
3. 交互式报告(HTML)
主要发现:
- 整体 GEO 评分:72/100
- AI 引用次数:677(+45%)
- 行业排名:Top 10%
请查看附件了解详情。
祝好,
SEO Assistant
attachments:
- "{{steps.exec-summary.output}}"
- "{{steps.tech-analysis.output}}"
- "{{steps.interactive-report.output}}"
timeout: 60
depends_on: generate-report
on_success: notify-success
on_failure: notify-error
# 错误处理
- id: notify-error
name: "发送错误通知"
description: "工作流执行失败时发送通知"
action: "send_slack"
params:
channel: "{{variables.slack_channel}}"
message: |
❌ 工作流执行失败
工作流:{{workflow.name}}
失败步骤:{{failed_step.name}}
错误信息:{{error.message}}
时间:{{timestamp}}
请立即检查!
priority: "high"
# 成功通知
- id: notify-success
name: "发送成功通知"
description: "工作流执行成功时发送通知"
action: "send_slack"
params:
channel: "{{variables.slack_channel}}"
message: |
✅ 工作流执行成功
工作流:{{workflow.name}}
执行时间:{{duration}}
生成报告:{{report_count}}
时间:{{timestamp}}
priority: "info"
# 工作流输出
output:
format: "json"
path: ".claude-flow/cache/workflows/{{workflow.name}}/{{timestamp}}.json"
include:
- execution_summary
- step_outputs
- alerts
- metrics
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 · 702 lines · 24 tokens per session scan A 081a2bfced27
workflow-automation is a command published in the GitHub repository huifer/claude-code-seo (110 stars, last pushed 8mo ago), licensed MIT. It adds 24 tokens to every session and 4,590 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.