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 skills add vasilyu1983/AI-Agents-public --skill ai-product-operating-modelgit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/ai-product-operating-model)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/ai-product-operating-model"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/ai-product-operating-model/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/vasilyu1983/ai-agents-public/ai-product-operating-model"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/ai-product-operating-model.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.05787 |
| Opus 5 | $0.00018 | $0.02893 |
| Sonnet 5 | $0.00007 | $0.01157 |
| Haiku 4.5 | $0.00004 | $0.00579 |
Grade A, and why
ai-product-operating-model 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 12d 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 — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Product Operating Model
Design a company-wide operating model for AI in product when the question is bigger than one prompt, one feature, or one model choice.
This skill is for organizations that need to align:
- product AI feature design
- agent and tool-using workflow posture
- data boundaries across product, context, and analytics
- provider and deployment posture
- public-cloud handling of PI or sensitive data
- evaluation, rollout, and governance
Default posture for May 2026:
- external model APIs first
- central platform ownership before federated sprawl
- explicit data-plane separation
- provider abstraction instead of hard vendor lock-in
- risk-tiered controls for sensitive data
- evals, telemetry, and rollback before broad rollout
- model-lifecycle governance: provider model deprecations treated as planned product events, not surprises
- multi-model ops: running more than one frontier provider in production as a standing operating concern
ASCII Flow
company AI ambition
|
v
scope classification
product AI | internal copilots | agents | mixed platform
|
v
operating model
central platform + provider posture + data-plane boundaries + risk tiers
|
v
shared controls
evals + telemetry + rollout + privacy + security + ownership contracts
|
v
roadmap
sequenced workstreams with owners, gates, and adoption feedback
When to Use This Skill
Use this skill when the user asks for:
- an AI in product operating model
- a company AI platform strategy
- an LLM or agent governance model
- how product teams should work with central AI/data/platform teams
- how to handle PI or sensitive data with public-cloud model providers
- how to split analytics, runtime context, and operational truth
- how to sequence workstreams for AI platform foundations
Use Other Skills for Depth
- LLM architecture, provider choice, adaptation, eval design -> ../ai-llm/SKILL.md
- Agent architecture, MCP vs A2A, approval patterns -> ../ai-agents/SKILL.md
- Product integration, streaming UX, structured outputs -> ../software-ai-integration/SKILL.md
- App context layer, memory, retrieval, grounding ->
ai-context-layer - Analytics semantics, marts, metric governance -> ../data-analytics-engineering/SKILL.md
- Product instrumentation and AI/agent telemetry ->
marketing-product-analytics - Production controls, privacy, incidents, auditability -> ../ai-mlops/SKILL.md
- AppSec and application-layer security boundaries -> ../software-security-appsec/SKILL.md
- Platform infra, workload identity, CI/CD, policy-as-code -> ../ops-devops-platform/SKILL.md
- Agent eval harnesses and regression gates -> ../qa-agent-testing/SKILL.md
What ships with it
10 files 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.
- agents/openai.yaml 343 B
- assets/company-ai-operating-model-template.md 3.7 KB
- data/sources.json 5.9 KB
- learnings.consolidated.md 602 B
- learnings.md 1.0 KB
- references/anti-patterns-catalog.md 11 KB
- references/data-boundaries-and-risk-tiers.md 3.2 KB
- references/patterns-catalog.md 11 KB
- scripts/contract_validator.py 12 KB runs code
- scripts/risk_tier_classifier.py 13 KB runs code
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.
- 12d ago First seen · 335 lines · 36 tokens per session scan A a7d07a9d1399
ai-product-operating-model is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 9d ago), licensed MIT. It adds 36 tokens to every session and 5,787 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.
istio-traffic-management
Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.
projection-patterns
Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.
microservices-patterns
Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices.
track-management
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".