Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Jasper0122/agent-seo-kitnpx agentmods add skills/jasper0122/agent-seo-kit/backlink-outreachWrote 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/jasper0122/agent-seo-kit/backlink-outreach)<a href="https://agentmods.dev/skills/jasper0122/agent-seo-kit/backlink-outreach"><img src="https://agentmods.dev/badge/skills/jasper0122/agent-seo-kit/backlink-outreach.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 | $0.00133 | $0.02720 |
| Opus 5 | $0.00067 | $0.01360 |
| Sonnet 5 | $0.00027 | $0.00544 |
| Haiku 4.5 | $0.00013 | $0.00272 |
Grade A, and why
backlink-outreach 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 8d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlink outreach
Build editorially useful partnerships. A backlink is the result of a content collaboration that helps a reader, not a swap.
The one rule that must never break
research -> evaluate -> draft -> approve -> send
-> receive materials -> write -> review -> publish -> verify
No stage advances without the user saying so. In particular:
- "look at", "review", "draft a reply", "who should we contact" are read-only or draft-only. They never authorise a send.
- A finished draft is not permission to send it. Sending needs its own yes.
- Never promise placement, guarantee a followed link, or say you will "definitely include" a partner before editorial review.
- Never edit or publish a live article as part of an outreach commitment without explicit approval.
Editorial independence outranks the partnership. Mention a product when it helps the reader, and the writing pipeline's honesty rules still apply: no invented traffic, ranking, funding, customer or performance claims about anyone.
Step 1: take prospects from the GEO data, do not re-derive them
node scripts/prospects-from-geo.mjs --min 2
node scripts/prospects-from-geo.mjs --min 2 --authority # paid, adds Domain Rating
This reads data/geo-latest.json and returns the hosts an AI actually cited
when answering your registry questions, ranked by how often you were absent
from those answers.
That ranking is the point. A host cited on a question where the engine named two rivals and not you is a page actively shaping an answer you are losing. A generic search for " blogs" finds a similar set with none of that evidence attached.
Four tiers, and the tier decides the play:
| Tier | What it means | The play |
|---|---|---|
| Partner | Already a customer, supplier, integration or existing relationship | Warmest. A contact and a reason to talk exist. |
| Prospect | Cited, not a competitor or a platform | The normal research and pitch path. |
| Competitor | Sells what you sell | Never pitch. Read what they publish; that is the gap. |
| Directory | Review sites, listicle farms | Getting listed is a different task, not an article email. |
What ships with it
4 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.
- 8d ago First seen · 263 lines · 0 tokens per session scan A b5c63f195d87
backlink-outreach is a skill published in the GitHub repository Jasper0122/agent-seo-kit (6 stars, last pushed 17d ago), licensed MIT. It adds 133 tokens to every session and 2,720 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
fire-your-seo-agency
A procedure for improving how a website appears in search engines and how AI answer systems find and cite it. It covers search, answer-engine, generative-AI, and Naver visibility.
seo-audit
A checklist-based SEO review for a website. SEO, or search engine optimization, is the work of improving a site so search engines can understand and rank it.
bytesagain-geo-seo
GEO SEO — Generative Engine Optimization reference. Complete guide for optimizing websites for AI search engines. Covers llms.txt spec, GEO checklist, automated scanning, AI bot tracking with nginx, AEO (Answer Engine Optimization) for getting cited by ChatGPT/Perplexity/Gemini, citation monitoring, and content…
geo-content-research
Researches what prompts people ask AI engines (ChatGPT, Gemini, Perplexity, Claude) about a product category and produces a prompts.csv artifact — a prioritized, strictly-schema'd list of the queries where the brand should be cited. Feeds the monitor workflow.
ultimate-seo-geo-skill
Use this skill when running SEO audits, optimizing for AI search engines (AI Overviews, ChatGPT, Perplexity), generating schema markup, diagnosing traffic drops, fixing Core Web Vitals, managing site migrations, or building keyword strategies. Runs scored full-site audits (0-100 Health Score) across 21 modules…
improve-aeo-geo
Audits a website codebase and makes code changes so AI engines (ChatGPT, Claude, Perplexity, Google AI Overviews) can better discover, parse, quote, and cite the site. Covers structured data, content structure, technical signals, and freshness.