Borrowing it
Nothing to install: this file belongs to prashishh/seo-geo-report-engine. 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/prashishh/seo-geo-report-engine/main/.agents/skills/internal-linking/SKILL.mdgit clone --depth 1 https://github.com/prashishh/seo-geo-report-engineWrote 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/prashishh/seo-geo-report-engine/internal-linking)<a href="https://agentmods.dev/skills/prashishh/seo-geo-report-engine/internal-linking"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/internal-linking/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/prashishh/seo-geo-report-engine/internal-linking"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/internal-linking.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00139 | $0.01490 |
| Opus 5 | $0.00069 | $0.00745 |
| Sonnet 5 | $0.00028 | $0.00298 |
| Haiku 4.5 | $0.00014 | $0.00149 |
Grade A, and why
internal-linking 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 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.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
internal-linking
Designs the link architecture that connects keyword clusters and programmatic pages into
crawlable, equity-flowing silos — and routes that equity toward money/conversion pages. This is
planning, not auditing: technical-seo-audit flags broken/orphaned links as issues; this skill
decides the target graph. Prefer Ahrefs MCP (knowledge/ahrefs-mcp-map.md); call doc on a tool
before first use. Reuse the hub-spoke seed in playbooks/programmatic-seo.md §7.
Inputs
projects/<client>/research/keyword-map.md+keywords.csv(fromkeyword-research) — clusters, intent, target pages. One cluster = one pillar candidate.client.yml— domain, money/conversion pages (sales, pricing, demo, signup, key services).
Methodology (PERCEIVE → ANALYZE → VALIDATE → ACT)
PERCEIVE — map the current graph. Resolve project (./bin/mkt config show --project <client>).
Pull the live internal-link structure:
site-explorer-pages-by-internal-links— inbound internal links per URL. Sort it: the long tail with 0–1 inbound internal links = orphans / near-orphans; the top fat-head pages are where equity is hoarded.site-explorer-linked-anchors-internal— the internal anchor-text profile (what text currently points where). Flags exact-match over-optimization and generic "click here / read more" waste.site-explorer-pages-by-traffic+site-explorer-top-pages— which pages actually hold equity and traffic, so we link from strength into targets.- Cross-check orphans against
keywords.csv— an orphan that's a real cluster target is high-value rescue; an orphan with no demand may just be prunable.
ANALYZE — design the target graph.
- Cluster → hub-and-spoke. Each keyword-research cluster becomes one pillar (hub) ↔ N
spokes. Pillar = the broad/commercial head target; spokes = the informational long-tail pages.
Where
keyword-researchused SERP-overlap to group terms, that same overlap defines which spokes are sibling-related and should cross-link. - Link rules (the silo): every spoke links up to its pillar; pillar links down to every spoke; siblings within a cluster cross-link where contextually relevant; pillars link laterally to adjacent pillars only when topically justified (avoid diluting the silo).
- Equity flow to money pages. Identify high-equity/high-traffic pages from PERCEIVE and route contextual links into money/conversion pages from them. Money pages are the sink of the graph, not just nav-linked.
- Anchor distribution. Vary anchors per target: a mix of exact, partial, and
semantic/branded — relevance-scored to the destination's primary keyword. Replace generic anchors
surfaced by
-linked-anchors-internal. No single exact-match anchor should dominate a target (over-optimization risk). - Cannibalization flag. If two pages target the same intent/keyword (same
target_pagecollision inkeywords.csv, or both rank for one term insite-explorer-organic-keywords), don't cross-link them as equals — pick the canonical, point the other's equity into it, and flag for consolidation.
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 · 95 lines · 139 tokens per session scan A 9d9f06c76b96
internal-linking is a skill published in the GitHub repository prashishh/seo-geo-report-engine (5 stars, last pushed 2mo ago), licensed MIT. It adds 139 tokens to every session and 1,490 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
content-amplifier
Use when the user asks to "amplify influencer content with paid media", "set up whitelisting or Spark Ads", "decide which posts to boost", "repurpose influencer content", "turn one video into multiple ads", or "build a UGC asset library"; produces (paid mode) a content-selection scorecard, a paid amplification…
campaign-planner
Use when the user asks to "plan an influencer campaign", "build a campaign blueprint", "track or close a creator campaign", or "record a late campaign correction"; produces the plan and, when requested, a non-canonical evidence tracker with scoped identity, publication, reconciliation, close, and reopen receipts. Not…
inbox-placement-monitor
Use when the user asks to "track where my emails are actually landing after I send", "read my seed-list inbox vs spam vs promotions results", "trend my Gmail Postmaster / Microsoft SNDS reputation", or "did placement drop after my last send"; produces a per-provider inbox/spam/promotions placement read, a domain/IP…
subject-line-lab
Use when the user asks to "generate subject line variants", "pre-score my subject lines", or "will this subject get truncated / trigger spam filters"; produces a labeled subject + preheader variant set and a per-variant heuristic pre-score card — spam-trigger flags, length/truncation across desktop + mobile…
email-sequence-designer
Use when the user asks to "design a welcome flow", "set up an abandoned-cart sequence", "build a light re-engagement branch inside a lifecycle flow", or "plan a cold-outbound sequence"; produces general lifecycle automation flows (welcome, cart, browse-abandon, post-purchase, in-flow re-engagement, B2B cold outbound)…
newsletter-monetization-planner
Use when the user asks to "monetize my newsletter", "build a sponsorship rate card", or "model paid-subscription revenue"; produces a revenue model (paid tiers, ad/sponsorship inventory + CPM/flat rate card, referral/boost loops), a list-growth ↔ revenue projection, and honest-offer / disclosure checks for the SEND-D…