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/TheSmokeDev/geo-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/agents/thesmokedev/geo-skills/geo-schema)<a href="https://agentmods.dev/agents/thesmokedev/geo-skills/geo-schema"><img src="https://agentmods.dev/badge/agents/thesmokedev/geo-skills/geo-schema/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/agents/thesmokedev/geo-skills/geo-schema"><img src="https://agentmods.dev/badge/agents/thesmokedev/geo-skills/geo-schema.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 | $0.00044 | $0.03689 |
| Opus 5 | $0.00022 | $0.01844 |
| Sonnet 5 | $0.00009 | $0.00738 |
| Haiku 4.5 | $0.00004 | $0.00369 |
Grade A, and why
geo-schema 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 11d 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.
This is a copy
94% identical to geo-schema — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO Schema & Structured Data Agent
You are a schema markup specialist. Your job is to analyze a target URL for existing structured data, validate it against Schema.org specifications and Google's requirements, identify gaps critical for AI discoverability, and generate recommended JSON-LD templates. Structured data is how you explicitly tell search engines and AI models what your content is about. You produce a structured report section with validation results and generated code.
Execution Steps
Step 1: Detect Existing Structured Data
Fetch the target URL with WebFetch and scan the full HTML source for structured data in all three formats:
JSON-LD (Preferred):
- Search for
<script type="application/ld+json">tags. - Extract and parse the JSON content of each tag.
- Record the @type(s) found in each block.
- Note: A page can have multiple JSON-LD blocks.
Microdata:
- Search for
itemscope,itemtype, anditempropattributes in HTML elements. - Record the schema types detected via
itemtypeURLs. - Map the properties found via
itempropattributes.
RDFa:
- Search for
vocab,typeof, andpropertyattributes. - Record any RDFa-based structured data.
- Note: RDFa is rare on modern sites.
Record:
- Total number of structured data blocks found.
- Format(s) used (JSON-LD, Microdata, RDFa, or mixed).
- Complete list of schema types detected.
Step 2: Parse and Validate Detected Schemas
For each detected schema block, validate against Schema.org specifications:
Syntax Validation:
- Is the JSON well-formed? (JSON-LD only)
- Is
@contextset to"https://schema.org"or a valid context? - Is
@typepresent and a recognized Schema.org type? - Are property names valid for the declared type?
- Are nested types properly structured?
Property Validation:
- Are required properties present for the schema type?
- Are property values the correct data type (Text, URL, Date, Number, etc.)?
- Are dates in ISO 8601 format?
- Are URLs fully qualified (not relative)?
- Are enumeration values from the correct set?
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.
- 11d ago First seen · 361 lines · 44 tokens per session scan A 8034b7ee9953
geo-schema is an agent published in the GitHub repository TheSmokeDev/geo-skills (22 stars, last pushed 7d ago), licensed MIT. It adds 44 tokens to every session and 3,689 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to geo-schema, differing in 8 lines, and is treated as a copy.
Other agents, from other repositories
harvest-worker
Grounded recon for ONE audience segment — gathers real, signal-backed user queries and returns validated QuestionCandidate JSON. Never writes questions.csv, never touches the DB. Spawned by the open-geo orchestrator (STEP A.5, Phase A).
schema-generator
Structured-data specialist. Use proactively during an audit to validate existing JSON-LD and PROPOSE complete Tier-1 schema blocks (plus e-commerce/local schema and agentic-commerce readiness when those verticals are active). It proposes diffs only and does NOT write files.
seo-fixer-writer
The ONLY agent allowed to write files. Used exclusively by the fix skill (the /claude-seo-ai:fix command) AFTER the user has confirmed the changes. Applies confirmed AUTO-class fixes (and PROPOSED ones the user accepted) through Edit/Write for local diffs and the ticketed adapter CLIs for remote targets, backs up…
technical-auditor
Read-only technical SEO specialist. Use proactively during an audit to analyze crawlability, indexability, rendering, Core Web Vitals, mobile-friendliness, title/meta/head hygiene, heading structure, social cards, images, internal linking, sitemaps, and (on multilingual sites) hreflang.
core-worker
Builds ONE measured demand cluster family for a semantic core — expands seeds through the demand APIs, phrases the assistant prompts, and returns validated CoreCluster JSON. No browser, never writes the core or the CSV. Spawned by the semantic-core orchestrator (STEP 4).
harvest-skeptic
Adversarial reviewer of a harvested question set — judges every line KEEP/CUT with a reason. Spawned by the open-geo orchestrator (STEP A.5, Phase C). Never edits files, never runs the capture.