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 skills add Citlyze/citlyze-skills --skill aeo-page-auditgit clone --depth 1 https://github.com/Citlyze/citlyze-skillsWrote 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/citlyze/citlyze-skills/aeo-page-audit)<a href="https://agentmods.dev/skills/citlyze/citlyze-skills/aeo-page-audit"><img src="https://agentmods.dev/badge/skills/citlyze/citlyze-skills/aeo-page-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/citlyze/citlyze-skills/aeo-page-audit"><img src="https://agentmods.dev/badge/skills/citlyze/citlyze-skills/aeo-page-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00078 | $0.00901 |
| Opus 5.5 | $0.00031 | $0.00360 |
| Sonnet 5.5 | $0.00016 | $0.00180 |
| Haiku 4.5 | $0.00008 | $0.00090 |
Grade A, and why
aeo-page-audit scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Only fetch tools (WebFetch, curl, or equivalent). Fetch raw HTML and judge it as served: AI crawlers generally do not execute JavaScript, so content that only appears after hydration does not count. How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AEO page audit
Grade a page on the two things that decide whether AI engines use it: crawlability (can AI bots fetch it) and extractability (can an engine lift a clean answer from it). Scored out of 100 using the same public checklist as the free Citlyze AEO grader.
What you need
Only fetch tools (WebFetch, curl, or equivalent). Fetch raw HTML and judge it as served: AI crawlers generally do not execute JavaScript, so content that only appears after hydration does not count.
Checks and scoring
Fetch https://<domain>/robots.txt, the page HTML, and probe https://<domain>/llms.txt, then score:
| # | Check | Max | Pass condition |
|---|---|---|---|
| 1 | AI crawler access | 25 | robots.txt does not block major AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, Bingbot, CCBot, and similar) for this path. Any blocked major crawler scores 0. |
| 2 | Reachable and indexable | 15 | HTTP status below 400 and no noindex in meta robots or X-Robots-Tag. |
| 3 | One descriptive H1 | 10 | Exactly one H1 with at least 3 words. Multiple H1s: half credit. None: 0. |
| 4 | Question-shaped headings | 12 | At least 2 subheadings phrased as questions users would ask. Exactly 1: half credit. |
| 5 | Extractable answer blocks | 15 | At least 2 headings immediately followed by a direct 25-90 word answer. Exactly 1: half credit. |
| 6 | Entity structured data | 10 | JSON-LD declaring who/what the page is about (Organization, Product, Article, or similar entity types). |
| 7 | Tables and lists | 8 | Content uses tables or lists AI engines can lift verbatim, where the content type calls for them. |
| 8 | Title and meta description | 5 | Title at least 15 characters and meta description at least 50, both describing the page honestly. |
| - | llms.txt | 0 | Informational only: note whether it exists. There is no strong evidence engines consume it yet, so it earns no points. |
Report format
- Score: N/100 with a one-sentence verdict.
- Check table: each check with pass/warn/fail, points earned, and a one-line finding quoting the evidence (the robots rule matched, the H1 text, the failing heading).
- Fix list, ordered by points recoverable: concrete edits ("add a 40-word direct answer under 'How does X work?'", "unblock GPTBot for /blog/*"), not generalities.
- If several pages were audited, add a comparison table.
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.
- 2mo ago First seen · 47 lines · 78 tokens per session scan A 4cda1258932f
aeo-page-audit is a skill published in the GitHub repository Citlyze/citlyze-skills (0 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 901 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
aeo-page-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aeo-page-auditCitlyze/citlyze-skills | Skill | 0 | 1mo ago | MIT | A | 78 | Claude Code, Codex |
| ganhuo-geo-engineeryuanyuanyuan430/ganhuo-geo-skill | Skill | 2 | 4mo ago | MIT | A | 99 | Claude Code, Codex |
| fire-your-seo-agencyleopard627/fire-your-seo-agency | Skill | 997 | 5d ago | MIT | A | 240 | Claude Code |
| ansvisor-aeo-coach-standaloneansvisor/ansvisor | Skill | 234 | yesterday | MIT | A | 148 | Claude Code, Codex |
| geo-loopmverab/eGEOagents | Skill | 218 | today | MIT | A | 62 | Claude Code |
| competitive-analysismverab/eGEOagents | Skill | 218 | today | MIT | A | 29 | Claude Code |
| validation-doctormverab/eGEOagents | Skill | 218 | today | MIT | A | 28 | Claude Code |