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/sumologic/sumologic-documentation/geo-optimizegit clone --depth 1 https://github.com/SumoLogic/sumologic-documentationWhat 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 | $0.00000 | $0.02326 |
| Opus 5 | $0.00000 | $0.01163 |
| Sonnet 5 | $0.00000 | $0.00465 |
| Haiku 4.5 | $0.00000 | $0.00233 |
Grade A, and why
geo-optimize 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 2d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO Optimize — Generative Engine Optimization (AEO + GEO)
Rewrites and restructures documentation to improve discoverability in AI-powered search tools (ChatGPT, Perplexity, Gemini, Claude, and similar) and to surface content as direct answers in traditional search results. Covers both AEO (Answer Engine Optimization — featured snippets, "People also ask") and GEO (Generative Engine Optimization — LLM citation and extraction).
What this command does
When you invoke /geo-optimize, Claude will:
- Read the doc
- Diagnose the current state. Identify AEO and GEO gaps before making changes
- Propose specific improvements. Show the user what will change and why
- Apply approved changes. Rewrite only the sections the user approves
- Validate the result. Confirm the doc is more answer- and citation-ready without breaking accuracy
When to use this command
- New docs for features that are frequently searched in AI tools or voice search
- High-traffic docs that rarely appear in AI-generated answers or featured snippets
- Concept and reference docs where accuracy and citability matter most
- After
/seo-auditflags AEO or GEO suggestions - Before a product launch to maximize early visibility
What this command does NOT change
- Technical accuracy — never alter facts, steps, code, or configuration values
- Voice and tone — keep the Sumo Logic style; do not introduce formal or robotic language
- Doc structure beyond adding or enhancing specific sections
- Content the user has not approved
Workflow
Step 1: Get the file
Ask for the file path if not provided. Read the complete file including frontmatter.
Step 2: Diagnose AEO and GEO gaps
Before proposing changes, assess the doc against the Five GEO Principles defined in geo-guide/SKILL.md — answer-first (BLUF), one page one question, question-style headings, FAQ sections, and structured metadata — and tell the user what you found.
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.
- 2d ago First seen · 219 lines · 0 tokens per session scan A fa00c2b77c83
geo-optimize is a command published in the GitHub repository SumoLogic/sumologic-documentation (42 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,326 tokens. 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
add-scaffold
按 14-phase 工作流为指定 app 编写清理 scaffold（含需求采集、实测勘测、TOML、safety test、UI 集成）.
scaffold-review
Command "scaffold-review" from cccyd2003-qwq/pinkbin, covering 诊断 checklist, phase 1-2 类别需求, phase 5-7 实测勘测, phase 8 toml 本身 and phase 10 safety test.
monitor-ci
Monitors pull request CI checks until they are resolved (pass or fail).
loci-scan
Refresh the current project's local Loci memory.
adr-supersede
Create a new ADR that supersedes an existing one.
spec-forge
Use when generating software specifications — full chain (Idea→Decompose→Tech Design + Feature Specs) or individual documents.