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/seo-auditgit 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 | $0.02242 |
| Opus 5 | $0.00000 | $0.01121 |
| Sonnet 5 | $0.00000 | $0.00448 |
| Haiku 4.5 | $0.00000 | $0.00224 |
Grade A, and why
seo-audit 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 yesterday.
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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO/AEO/GEO Audit — Search and AI Discoverability Check
Use this command to audit a doc for SEO, AEO, and GEO signals — run it before any PR on new or updated content, even if you're not focused on search optimization.
Signal definitions
SEO (Search Engine Optimization): signals that help traditional search engines rank and surface pages.
AEO (Answer Engine Optimization): signals that help search engines display the page as a direct answer (featured snippets, knowledge panels, "People also ask" boxes).
GEO (Generative Engine Optimization): signals that help LLM-powered tools (ChatGPT, Perplexity, Gemini, Claude) cite and quote the page accurately in generated responses.
Workflow
Step 1: Identify the file or directory
If the user provides a file path, read that file. If they provide a directory, find all .md files in it and audit each one, then produce a summary.
If no argument is given, ask the user for the file path.
Step 2: Read the file(s)
Use the Read tool to read the complete file content including frontmatter.
Step 3: Run SEO checks
Frontmatter
-
titlepresent -
titleis under 60 characters — Critical if missing or over 60 -
titleincludes the primary keyword or product/feature name -
descriptionpresent — Critical if missing -
descriptionis 140–160 characters — Warning if under 100 or over 160; Suggestion if 100–139 (functional but below target) -
descriptionleads with an action verb or product name (not "This page" or "This doc") -
keywordsfield present with 3–5 relevant terms — Suggestion if missing - No
slugon a regular content page (breaks sidebar linking) — Critical if present
Headings
- No H1 in body — title frontmatter generates H1; a second H1 breaks SEO — Critical if present
- At least 2 H2 headings for pages over 500 words — Suggestion if none
- No duplicate headings at the same level — Warning if duplicated
- Headings are under 60 characters — Suggestion if over
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.
- yesterday First seen · 206 lines · 0 tokens per session scan A d7e8a6cc8827
seo-audit is a command published in the GitHub repository SumoLogic/sumologic-documentation (42 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,242 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.