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/backlink-analysis/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/backlink-analysis)<a href="https://agentmods.dev/skills/prashishh/seo-geo-report-engine/backlink-analysis"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/backlink-analysis/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/backlink-analysis"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/backlink-analysis.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 | $0.00102 | $0.01045 |
| Opus 5 | $0.00051 | $0.00522 |
| Sonnet 5 | $0.00020 | $0.00209 |
| Haiku 4.5 | $0.00010 | $0.00104 |
Grade A, and why
backlink-analysis 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
backlink-analysis
Reads a domain's backlink profile, judges its health and growth, and turns competitor link
data into a prioritized prospect list. Output is projects/<client>/research/backlinks.md.
Ahrefs MCP is the engine (see knowledge/ahrefs-mcp-map.md).
Methodology is PERCEIVE → ANALYZE → VALIDATE → ACT. Every prospect is falsifiable: state why the link is plausible (it links to ≥2 competitors / it's a dead page we can replace), and the signal that would tell us the outreach failed.
Inputs
projects/<client>/client.yml—domain,competitors[],ahrefs.project_id. Resolve with./bin/mkt config show --project <client>. Today is absolute (e.g.2026-06-23); calldocon a tool before first use; monetary values are USD cents (÷100).- Prior snapshots in
data/(refdomains history) to measure growth.
Workflow
1. PERCEIVE — our profile and its trend
site-explorer-backlinks-stats+site-explorer-referring-domains— total backlinks, ref domains, DR distribution of linking domains.site-explorer-refdomains-history— ref-domain growth/decay over the window (the health signal: net new linking domains, not raw backlink count).site-explorer-anchors/-linked-anchors-external— anchor distribution (over-optimized exact-match or branded/natural?).site-explorer-pages-by-backlinks— our own most-linked pages (what earns links today).
2. ANALYZE — health verdict
- Velocity — is ref-domain growth positive and steady, or spiky/declining? Spikes can be spam; declines can be link rot.
- Quality — share of links from DR≥30 domains vs low-DR/spam; topical relevance.
- Anchors — flag exact-match anchor ratios that risk over-optimization.
- State a one-line verdict (healthy / at-risk / thin) with the numbers behind it.
3. VALIDATE — find prospects (link gap) and reclaim targets
- Link gap — for each competitor run
site-explorer-referring-domains; find domains linking to ≥2 competitors but not us (warm prospects). Usesite-explorer-pages-by-backlinkson competitors to see which page earned each link (the content you'd pitch). For a full gap with scoring, coordinate withcompetitor-analysis— reuse its backlink-gap pull, don't duplicate it. - Broken-link reclaim —
site-explorer-broken-backlinkson our domain (lost links to reclaim) and on competitors (dead pages with live links = recreate-and-pitch targets).
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 · 75 lines · 102 tokens per session scan A 7d062e99235a
backlink-analysis is a skill published in the GitHub repository prashishh/seo-geo-report-engine (5 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 1,045 once invoked, about $0.0005 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…
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…
preference-frequency-manager
Use when the user asks to "build a preference center", "set up a frequency opt-down ladder", "give people a step-down instead of unsubscribe", or "design a topic/cadence preference page"; produces a preference-center field spec, a frequency/topic opt-down ladder (down-tier paths that substitute for a hard…
reactivation-specialist
Use when the user asks to "build a win-back campaign", "re-engage lapsed subscribers", "run a re-permission / re-consent sweep", or "sunset my dead list"; produces a closed-loop reactivation program — a lapsed-cohort definition, a staged offer ladder, a re-consent (re-permission) capture step, and a sunset-confirm /…