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 agentmods add skills/impactbrussels/ainativeos/geo-contentnpx skills add impactbrussels/AINativeOS --skill geo-contentgit clone --depth 1 https://github.com/impactbrussels/AINativeOSWrote 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/impactbrussels/ainativeos/geo-content)<a href="https://agentmods.dev/skills/impactbrussels/ainativeos/geo-content"><img src="https://agentmods.dev/badge/skills/impactbrussels/ainativeos/geo-content.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 | $0.00132 | $0.01333 |
| Opus 5 | $0.00066 | $0.00666 |
| Sonnet 5 | $0.00026 | $0.00267 |
| Haiku 4.5 | $0.00013 | $0.00133 |
Grade A, and why
geo-content 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 5d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO Content
The buyer reads four confident sentences in an AI engine before they ever reach your site, and those sentences name three companies as proof. Ranking puts a blue link on a page nobody scrolls anymore. It does not put your name in the paragraph the buyer actually read. The engine quotes rather than ranks, and quoting rewards different content: a claim that stands on its own, a number with a source, depth a keyword-stuffer cannot fake. Your job is not to climb a list. It is to become the source the machine reaches for.
The method
Structure for extraction, then hit the citation factors. Full framework: references/geo-method.md, drawn from handbook Chapter 10.
Step 1: Write the one-sentence extractable answer
Take your category's top buyer query, the exact question a high-intent buyer types into an engine. Write the one or two sentences you want quoted back, standing completely alone, naming you or your category claim. That sentence is the GEO north star; every page opens with a version of it.
Step 2: Lead every section with its answer
A model scans for the chunk that answers and grabs the chunk that stands alone. Bury the claim in paragraph six and the engine reads past it. Pick the format that fits the query.
| Query shape | Format | Opening move |
|---|---|---|
| "what is X" | Definitional | One-sentence standalone definition, then mechanism |
| "X vs Y" / "X alternatives" | Comparative | Named criteria table, verdict first |
| "how much / how long / how many" | Data-led | The number with its source in the same breath |
| "how do I [job]" | FAQ / steps | Direct answer, then the numbered method |
Step 3: Hit the citation factors
An engine managing its own risk gravitates to sources it can defend. Score the draft against the checklist before publishing.
| Factor | Pass test |
|---|---|
| Clarity | Each section opens with a liftable, self-contained sentence |
| Structure | Headings match real buyer queries; answer before depth |
| Specificity | Exact numbers and named mechanisms, never "significant" |
| Authority | Every statistic carries its source; every claim a named expert |
| Freshness | Dated, with the most recent verified figure |
What ships with it
1 file 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.
- 5d ago First seen · 89 lines · 0 tokens per session scan A 189f062c90bc
geo-content is a skill published in the GitHub repository impactbrussels/AINativeOS (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 132 tokens to every session and 1,333 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
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
agent-session-monitor
Real-time agent conversation monitoring - monitors Higress access logs, aggregates conversations by session, tracks token usage. Supports web interface for viewing complete conversation history and costs. Use when users ask about current session token consumption, conversation history, or cost statistics.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
nw-ddd-eventsourcing
Event Sourcing and CQRS as DDD implementation patterns — when to use, aggregate event streams, projections, snapshots, sagas, upcasting, conflict resolution.
nw-leanux-methodology
LeanUX backlog management methodology - user story template, story sizing, story states, task types, Definition of Ready/Done, anti-pattern detection and remediation.