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 mblode/agent-skills --skill optimise-seogit clone --depth 1 https://github.com/mblode/agent-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/mblode/agent-skills/optimise-seo)<a href="https://agentmods.dev/skills/mblode/agent-skills/optimise-seo"><img src="https://agentmods.dev/badge/skills/mblode/agent-skills/optimise-seo.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium MCP Rug Pull · line 86 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00077 | $0.05070 |
| Opus 5 | $0.00039 | $0.02535 |
| Sonnet 5 | $0.00015 | $0.01014 |
| Haiku 4.5 | $0.00008 | $0.00507 |
Grade A, and why
optimise-seo 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 2d 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.
- HTML-limited bots (`Twitterbot`, `Bingbot`, `facebookexternalhit`, and Next's default list) skip the prerendered shell and get the whole page rendered dynamically at request time. Anything the shell reads only at build How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimise SEO
- IS: crawlability, metadata, structured data, canonicals, redirects, status codes, hreflang, AI-crawler policy and extractable page structure, Core Web Vitals, programmatic SEO, security and privacy headers, and error-page behaviour, implemented in a Next.js App Router codebase.
- IS NOT: visual redesign, layout, or page-level UI quality (
ui-designDirection, Build, and Audit modes), demand research, briefs, question maps, or Search Console monitoring (seo-program), tenant routing forrobots.txtandsitemap.xml(multi-tenant-architecture), or writing the article (externalghostwriter).
Allowed surface: metadata and generateMetadata, JSON-LD, semantic HTML, internal links, alt text, app/sitemap.ts, app/robots.ts, app/feed.xml/route.ts, app/llms.txt/route.ts, proxy.ts, next.config.ts redirects and headers, error pages, and performance work. Component styling and layout stay as they are; when a fix needs a layout change, name it as a handoff to ui-design.
Before writing code, read the matching guide in node_modules/next/dist/docs/ (resolved from the app directory; in a monorepo the next package is not visible from the repo root). The bundled docs match the installed version; the notes in references/nextjs-implementation.md were checked against 16.3 and say where behaviour changed.
References
| File | Read when |
|---|---|
| references/indexing-policy.md | Redirects, duplicate URLs, index decisions, or pages generated at scale |
| references/nextjs-implementation.md | Before writing code in steps 2-4: metadata, sitemap and robots, redirects, indexing, streaming 404s, JSON-LD, OG images, CSP |
| references/answer-engines.md | The task touches AI crawlers, robots.ts rules for GPTBot or ClaudeBot, llms.txt, Content-Signal, or "why are we not cited" |
| references/internationalisation.md | The site has more than one locale |
| references/technical-hardening.md | Headers, cookies, consent, GPC, security.txt, or maintenance and error-status tasks |
| references/validation-evidence.md | Step 5: served-page commands and evidence expectations |
| references/seo-checklist.md | Step 5: copy into the report and mark each line with evidence |
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.
- 2d ago Changed · -26 lines · -166 tokens per session 67dd5a6e72be
- 8d ago First seen · 157 lines · 243 tokens per session scan A b7acecc4b07a
optimise-seo is a skill published in the GitHub repository mblode/agent-skills (105 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 5,070 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
pretext
Build creative browser demos with DOM-free text layout.
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
inspecting-hermes-desktop-dom
Read the live Hermes desktop DOM/CSS over CDP.
impeccable
Frontend design guidance, upstream-maintained (impeccable).