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 magnus919/agent-skills --skill seogit clone --depth 1 https://github.com/magnus919/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/magnus919/agent-skills/seo)<a href="https://agentmods.dev/skills/magnus919/agent-skills/seo"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/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/magnus919/agent-skills/seo"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/seo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 System Prompt Leakage · line 75 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00081 | $0.01568 |
| Opus 5 | $0.00041 | $0.00784 |
| Sonnet 5 | $0.00016 | $0.00314 |
| Haiku 4.5 | $0.00008 | $0.00157 |
Grade A, and why
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 9d 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.
Asks the agent to reveal its instructionslowSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
python3 scripts/build_prompt_matrix.py <topics.json> --output prompt-matrix.json Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO
A full-spectrum search visibility skill. It treats traditional SEO, Answer Engine Optimization (AEO), and Generative Engine Optimization (GEO) as overlapping work across different search and answer surfaces, not as separate collections of ranking hacks.
Operating model
- Scope the surface and outcome. Name the provider, product or search surface, audience, entity, questions, business outcome, and exclusions. Define whether success means crawl access, index eligibility, retrieval, mention, citation, citation correctness, share of voice, referral, or conversion.
- Inspect and research. Audit the public/rendered page and technical delivery. Read current first-party provider guidance and authoritative subject sources. Treat practitioner claims and vendor studies as hypotheses unless methods and scope support more.
- Map intent to canonical content. Use topics and question clusters, but avoid manufacturing near-duplicate pages. Assign one canonical answer location, entity ownership, evidence, freshness owner, and internal links.
- Improve people-first content and structure. Put a concise answer near the relevant heading, then supporting evidence, qualifications, and useful detail. Preserve natural prose, distinct point of view, accessibility, and human value.
- Implement only supported controls. Fix crawlability, indexability, metadata, internal links, page experience, textual content, structured-data parity, sitemaps, freshness, and provider-specific crawler or preview controls. Optional files such as
llms.txtor Markdown representations are provider-scoped proposals, not universal requirements. - Measure at the correct boundary. Freeze prompts and versions, capture exact answers and citations, score citation correctness, and use provider-native reports where available. Separate implementation evidence from observed visibility and causal claims.
- Verify and learn. Recheck the rendered/public boundary, validate structured data, inspect search-console or provider evidence, and run bounded one-variable experiments. Do not declare success from HTTP 200, parseable JSON-LD, a single answer, or a third-party score.
What ships with it
26 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.
- assets/audit-report-template.md 1.3 KB
- evals/evals.json 5.7 KB
- README.md 2.7 KB
- references/aeo-methodology.md 9.3 KB
- references/agent-readable-content.md 1.7 KB
- references/content-and-entity-architecture.md 3.8 KB
- references/content-strategy-seo.md 7.9 KB
- references/discovery-and-freshness.md 2.6 KB
- references/evidence-boundaries.md 4.3 KB
- references/ghost-metadata.md 9.5 KB
- references/implementation-playbook.md 5.8 KB
- references/measurement-and-experimentation.md 2.8 KB
- references/onpage-seo.md 8.3 KB
- references/platform-guidance.md 2.6 KB
- references/schema-markup.md 6.3 KB
- references/source-index.md 3.6 KB
- references/structured-data.md 3.0 KB
- references/technical-seo.md 5.3 KB
- scripts/aeo_audit.py 5.3 KB runs code
- scripts/build_prompt_matrix.py 2.2 KB runs code
- scripts/test_aeo_scripts.py 2.0 KB runs code
- templates/aeo-implementation-plan.md 1.3 KB
- templates/citation-observation-log.md 825 B
- templates/llms.txt.template 556 B
- templates/question-cluster.md 796 B
- templates/robots-ai-crawlers.txt 953 B
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.
- 9d ago First seen · 97 lines · 81 tokens per session scan A 6abe5e0005c6
seo is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 1,568 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…