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.
git 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/geo-automation)<a href="https://agentmods.dev/commands/huifer/claude-code-seo/geo-automation"><img src="https://agentmods.dev/badge/commands/huifer/claude-code-seo/geo-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 5.1 | $0.00025 | $0.04162 |
| Opus 5 | $0.00013 | $0.02081 |
| Sonnet 5 | $0.00005 | $0.00832 |
| Haiku 4.5 | $0.00003 | $0.00416 |
Grade A, and why
geo-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 7d 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 — 604 lines — stays where its author put it; the contents beside it link to each section on GitHub.
完整实现
命令执行流程
# GEO 自动化配置执行流程
## 步骤 1: 参数解析和验证
输入:action, task, schedule, alerts
处理:
- 验证操作类型
- 检查任务名称
- 验证 cron 表达式
- 检查告警配置
输出:配置对象
## 步骤 2: 任务配置
根据 action 执行:
- enable: 启用自动化任务
- disable: 禁用任务
- status: 查看任务状态
- configure: 修改任务配置
## 步骤 3: 工作流生成
生成任务执行流程:
- 定义步骤
- 设置依赖
- 配置重试
- 设置超时
## 步骤 4: 告警规则配置
配置告警:
- 设置触发条件
- 配置通知方式
- 定义优先级
- 创建告警模板
## 步骤 5: 保存配置
保存到:.claude-flow/cache/config/automation/task-name.json
返回:配置确认和状态
可用任务类型
1. weekly-audit(每周 GEO 审计)
描述: 每周自动执行完整的 GEO 审计并生成报告
默认调度: 每周一上午 9:00 (0 9 * * 1)
任务步骤:
task: weekly-audit
schedule: "0 9 * * 1" # 每周一 9:00
enabled: true
timezone: "Asia/Shanghai"
steps:
- id: scan-content
name: "扫描网站内容"
command: "/geo-content-audit"
params:
domain: "{{domain}}"
detailed: true
timeout: 300
retry: 3
- id: monitor-citations
name: "监控 AI 引用"
command: "/geo-citation-monitor"
params:
url: "https://{{domain}}"
period: 7
timeout: 180
retry: 2
- id: compare-competitors
name: "对比竞争对手"
command: "/geo-competitor-compare"
params:
you: "{{domain}}"
competitors: "{{competitors}}"
timeout: 240
retry: 2
- id: generate-report
name: "生成综合报告"
command: "/generate-report"
params:
type: "geo-comprehensive"
domain: "{{domain}}"
period: 7
format: "html"
interactive: true
include-charts: true
timeout: 120
告警规则:
alerts:
- condition: "citation-drop > 10%"
priority: "critical"
actions:
- type: "email"
to: ["[email protected]"]
subject: "🚨 紧急:AI 引用严重下降"
- type: "slack"
channel: "#seo-critical"
message: "AI 引用 7 天内下降超过 10%"
- condition: "score < 70"
priority: "high"
actions:
- type: "slack"
channel: "#seo-alerts"
message: "GEO 评分低于 70,需要优化"
- condition: "competitor-surpassed"
priority: "warning"
actions:
- type: "email"
to: "[email protected]"
subject: "⚠️ 竞争对手超越警告"
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.
- 7d ago First seen · 604 lines · 25 tokens per session scan A 40ce3bf7e185
geo-automation is a command published in the GitHub repository huifer/claude-code-seo (110 stars, last pushed 8mo ago), licensed MIT. It adds 25 tokens to every session and 4,162 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
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.