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 skills/georgejieh/machineread-preview/machineread-auditnpx skills add georgejieh/MachineRead-Preview --skill machineread-auditgit clone --depth 1 https://github.com/georgejieh/MachineRead-PreviewWrote 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/georgejieh/machineread-preview/machineread-audit)<a href="https://agentmods.dev/skills/georgejieh/machineread-preview/machineread-audit"><img src="https://agentmods.dev/badge/skills/georgejieh/machineread-preview/machineread-audit.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 | $0.00127 | $0.02752 |
| Opus 5 | $0.00063 | $0.01376 |
| Sonnet 5 | $0.00025 | $0.00550 |
| Haiku 4.5 | $0.00013 | $0.00275 |
Grade A, and why
machineread-audit scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -X POST "$MACHINEREAD_API/v1/audit" \ How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MachineRead Audit Skill
Use this skill when a user asks whether a public website is ready for AI assistants, LLM crawlers, and search-discovery tooling, and wants a free, evidence-based answer. The skill covers the public machineread-audit surface only — paid tiers, OAuth, LLM-generated reports, and benchmark comparisons against private peer profiles are out of scope.
Overview
MachineRead is a free public-readiness scanner for websites. The product surface this skill uses is the Essentials audit: a deterministic check of public HTTP, DNS, robots, sitemap, HTML, structured data, and machine-readable agent surfaces, with no paid search, backlink, social, crawler, or LLM APIs.
Essentials contract (the contract this skill calls):
- 13 included Essential check groups (10 universal core rows plus 3 contextual rows:
social,wikipedia,machine_surfaces). - 56-point checked maximum across the three pillars.
- Pillar caps:
off_site30,scrapability40,seo30 (a 30/40/30 split). - Three independent score systems in every response:
overall_score— full-rubric score, including locked advanced rows reported as unavailable.benchmark.score— Essentials evidence score from included free rows only.agent_readiness.score— a stricter agent-native lens with an 8-probe default scope and a 21-probe full scope when protocol, account/auth, and commerce surfaces are all enabled.
The audit is intentionally evidence-based and deterministic. The free tier never calls paid crawlers, never authenticates provider IPs, and never verifies live ranking or citation share.
When to Use
Use this skill when the user says or implies any of:
- "Audit this URL for AI readiness" or "Check if the site is agent-friendly".
- "Run a MachineRead audit" or "Get a public-readiness score".
- "How ready is this site for LLM crawlers?" or "Will AI assistants see this site?".
- "Check robots.txt, llms.txt, JSON-LD, and machine surfaces for
<url>." - "Score this site on the MachineRead Essentials audit."
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 185 lines · 127 tokens per session scan A ec27cdaa5e84
machineread-audit is a skill published in the GitHub repository georgejieh/MachineRead-Preview (2 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 2,752 once invoked, about $0.0006 per session on Opus 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.
Other skills, from other repositories
ai-visibility-audit
When the user wants to know whether their brand or domain is cited in AI answers — AI Overviews, ChatGPT, or AI search — for the queries that matter, and how they stack up against competitors. Also use on "AI visibility audit," "am I cited in AI answers," "do I show up in ChatGPT," "AI Overviews audit," "GEO audit,"…
seo-audit
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking,"…
content-strategy
When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog strategy," "topic clusters," "content planning," "editorial calendar," "content marketing," "content…
creator-campaign-ops
When the user wants a full-funnel influencer marketing campaign workflow: campaign setup, creator matching, budget and pricing forecast, outreach/confirmation pack, content review checklist, launch tracking, or post-campaign report. Also use on "plan an influencer campaign," "run creator campaign ops," "compare…
neighborhood-guide-opportunity
When a real estate agent or brokerage wants to find the neighborhood-level search and content opportunities it can actually own — where Zillow and the big portals are weak and local intent is high. Also use on "neighborhood guide ideas," "hyperlocal SEO for realtors," "what should I write to get found locally," "rank…
keyword-research
When the user wants to research keywords, find keyword opportunities, run a keyword gap analysis, build topic clusters, or compare what competitors rank for. Also use on "keyword research," "keyword gaps," "what should I target," "competitor keywords," "search volume," "keyword difficulty," "keyword opportunities,"…