MoAI-ADK is a Go-based harness that organizes and verifies Claude Code work across planning, implementation, synchronization, and review stages. Developers use it to structure agentic coding tasks, apply quality gates, and route work across language models, while the catalogue entries extend its workflow with skills, hooks, commands, MCP servers, instructions, and settings.
Borrowing it
Nothing to install: this file belongs to modu-ai/moai-adk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/modu-ai/moai-adk/main/.claude/skills/moai-ref-seo/SKILL.mdgit clone --depth 1 https://github.com/modu-ai/moai-adkWrote 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/modu-ai/moai-adk/moai-ref-seo)<a href="https://agentmods.dev/skills/modu-ai/moai-adk/moai-ref-seo"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-adk/moai-ref-seo/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/modu-ai/moai-adk/moai-ref-seo"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-adk/moai-ref-seo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 165 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 179 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00178 | $0.02820 |
| Opus 5 | $0.00089 | $0.01410 |
| Sonnet 5 | $0.00036 | $0.00564 |
| Haiku 4.5 | $0.00018 | $0.00282 |
Grade A, and why
moai-ref-seo 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 10d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Visibility Reference
Target Agents
manager-develop— applies these rules while implementing pages, routes, and serialized metadata output/moai review— pre-ship indexing review surface; equivalently available as a per-spawnAgent(general-purpose)with web-output review instructions
Core Principle
A page is indexed on what a machine can fetch and parse, not on what a person sees once everything has finished loading. Two failures dominate everything below: the same content reachable at more than one address, and a claim asserted in serialized data that nothing on the page corroborates. Every rule here is a specialization of one of those two.
Figures that engines publish and then quietly revise — truncation widths, ranking weights, crawl allowances — are deliberately absent. Where a limit matters, this reference gives the decision rule and the measurement to take, so the guidance outlives the figure.
Document Semantics
The structure a parser reads before it reaches any content signal. Cheapest class of defect to introduce, and the cheapest to detect.
| Rule | How to check it | Failure it prevents |
|---|---|---|
Exactly one h1 per document |
Count h1 elements in the rendered output of each page |
Competing topic signals leave the subject ambiguous |
| No skipped heading level | Walk the heading sequence; each descent moves by at most one level | Section nesting a parser cannot reconstruct |
Every image carries alt text |
Each image element has a non-empty alt attribute, or an empty one paired with an explicit decorative marker |
Meaning locked inside a binary the parser cannot open |
| Anchor text names its destination | Read each link's text with the surrounding sentence hidden, then ask where it goes | Instruction-shaped link text carries no signal about the target |
| Fragment targets resolve | For each in-page fragment link, confirm a matching identifier exists in the same rendered output | Navigation that silently lands nowhere |
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.
- 10d ago First seen · 208 lines · 178 tokens per session scan A 39d3ad2b348d
moai-ref-seo is a skill published in the GitHub repository modu-ai/moai-adk (1,204 stars, last pushed yesterday), licensed Apache-2.0. It adds 178 tokens to every session and 2,820 once invoked, about $0.0009 per session on Opus 5. 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 skills, from other repositories
mcp-app-scaffolding
Scaffolds MCP App project structure with correct directory layout, dependencies, entry points, and framework-specific templates. Handles React (useApp hook), Vanilla JS, Vue, Svelte, Preact, and Solid.
api-documenter
Auto-generate API documentation from code and comments. Use when API endpoints change, or user mentions API docs. Creates OpenAPI/Swagger specs from code. Triggers on API file changes, documentation requests, endpoint additions.
readme-updater
Keep README files current with project changes. Use when project structure changes, features added, or setup instructions modified. Suggests README updates based on code changes. Triggers on significant project changes, new features, dependency changes.
security-auditor
Continuous security vulnerability scanning for OWASP Top 10, common vulnerabilities, and insecure patterns. Use when reviewing code, before deployments, or on file changes. Scans for SQL injection, XSS, secrets exposure, auth issues. Triggers on file changes, security mentions, deployment prep.
gha
Analyze GitHub Actions failures and identify root causes.
review-claudemd
Review recent conversations to find improvements for CLAUDE.md files.