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/prashishh/seo-geo-report-enginenpx agentmods add skills/prashishh/seo-geo-report-engine/human-seo-editorWrote 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/human-seo-editor)<a href="https://agentmods.dev/skills/prashishh/seo-geo-report-engine/human-seo-editor"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/human-seo-editor/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/human-seo-editor"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/human-seo-editor.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 | $0.00100 | $0.01238 |
| Opus 5 | $0.00050 | $0.00619 |
| Sonnet 5 | $0.00020 | $0.00248 |
| Haiku 4.5 | $0.00010 | $0.00124 |
Grade A, and why
human-seo-editor 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 11d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
human-seo-editor
Turn generated SEO/GEO drafts into credible human articles without weakening search intent, citability, or factual discipline. This is an editorial QA skill, not an "AI detector" evasion skill. The goal is useful, specific, sourced, natural writing.
Inputs
- Draft page(s): HTML/Markdown in
projects/<client>/deliverables/orresearch/. projects/<client>/client.ymlfor positioning and brand voice.projects/<client>/research/voc.mdfromcustomer-researchwhenever available.- Briefs from
content-briefand page-level AEO specs fromaeo-content-patterns.
Resolve context first:
./bin/mkt config show --project <client>
Editorial Method
1. Diagnose the AI-ish pattern
Scan the draft and record concrete issues:
- Rhythm sameness: every paragraph is 1-2 short punchy sentences.
- Disconnected blocks: sections state facts but do not explain why the next idea follows.
- Consultant fog: abstract phrases like "foundation debt", "digital transformation", "unlock value", or "not X, but Y" when a concrete system, page, metric, or buyer problem should be named.
- Generic transitions: "In today's world", "That is where X comes in", "It matters because".
- Brochure voice: claims sound like sales copy, not an operator explaining a real workflow.
- Template residue: sibling pages repeat the same CTA, sentence shapes, examples, or proof.
- Unsupported confidence: broad claims without a named source, product fact, or example.
- Over-optimized headings: headings match keywords but do not match a real reader's question.
Use rg across siblings to catch repeated phrases before editing.
2. Ground the page before rewriting
Add at least one grounding source to each major section:
- A first-party product fact or workflow detail.
- A real customer/VOC phrase from
voc.md. - A cited external source with a date.
- A concrete scenario, example, edge case, or failure mode.
- A role-specific detail that makes the page differ from siblings.
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.
- 11d ago First seen · 129 lines · 100 tokens per session scan A 8fcb73e5406c
human-seo-editor is a skill published in the GitHub repository prashishh/seo-geo-report-engine (5 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 1,238 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…
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)…
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 /…
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…
product-feed-optimizer
Use when the user asks to "optimize my Shopping feed", "fix product disapprovals", "improve product titles/attributes", or "build feed-driven PMax asset groups"; audits and rewrites the Shopping/Performance Max product feed — title/description patterns, required and recommended attributes, GTIN/availability/price…
cold-outbound-sequencer
Use when the user asks to "build a B2B cold-outbound sequence", "design reply-triage branching", "plan a domain warmup / sending throttle", or "make my outbound CAN-SPAM / opt-in compliant"; produces a multi-step outbound sequence with reply-triage branches (positive / objection / referral / not-now / opt-out), a…