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/moat-strategynpx skills add impactbrussels/AINativeOS --skill moat-strategygit 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/moat-strategy)<a href="https://agentmods.dev/skills/impactbrussels/ainativeos/moat-strategy"><img src="https://agentmods.dev/badge/skills/impactbrussels/ainativeos/moat-strategy.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 | $0.00129 | $0.01494 |
| Opus 5 | $0.00064 | $0.00747 |
| Sonnet 5 | $0.00026 | $0.00299 |
| Haiku 4.5 | $0.00013 | $0.00149 |
Grade A, and why
moat-strategy 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moat Strategy
The thing you were defending stopped being defensible. You and the giant down the road rent the same model, at the same price, on the same terms; what took a quarter takes a Friday. A wrapper looks identical to a moat on launch day, which is the trap that funds the wrong companies. Three months on, one product is sharper than it was at launch and the other is exactly as good as the day it shipped, while four clones crowd in beside it. The demo could not tell them apart. The loop is the only thing that could.
The method
Find the loop, rank the moat, ledger it. Full framework: references/moat-method.md. Source: Handbook Chapter 14. Output destination: knowledge-base/MOATS-LEDGER.md.
Step 1: Name the flywheel, or admit you have a feature
Write the one sentence where a customer's use today makes the product measurably better next month. If you cannot write it, you do not have a moat yet. Spell out the loop: what use produces what proprietary data that makes what better.
Step 2: Rank the moat type by durability
Pick the moat you are actually building, hardest first.
| Moat type | The test it must pass | Durability |
|---|---|---|
| Data flywheel | Does each use compound, widening the gap while a rival catches up? | Highest |
| Vertical / proprietary data | Can a horizontal giant not collect this (consent, regulation, sensor, relationship)? | High |
| Data consortium | In a fragmented sector, is the pooled set larger than any member could build, and governed? | High |
| Trust and compliance | Does the audit trail, validation record, or clearance take years and survive scrutiny? | High, slow |
| Brand / switching cost | Does leaving cost the customer real, accumulated work, not just a logo change? | Medium |
Step 3: Run the Remove-the-AI test on the whole company
Delete the model call. If what is left is a generic chatbot, the moat is rented. If what is left is a flywheel of proprietary data and a record of earned trust, it is load-bearing.
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 · 85 lines · 129 tokens per session scan A 233231bd9877
moat-strategy is a skill published in the GitHub repository impactbrussels/AINativeOS (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 129 tokens to every session and 1,494 once invoked, about $0.0006 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.