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 manu14357/zskills --skill azure-hosted-copilot-sdkgit clone --depth 1 https://github.com/manu14357/zskillsWrote 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/manu14357/zskills/azure-hosted-copilot-sdk)<a href="https://agentmods.dev/skills/manu14357/zskills/azure-hosted-copilot-sdk"><img src="https://agentmods.dev/badge/skills/manu14357/zskills/azure-hosted-copilot-sdk/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/manu14357/zskills/azure-hosted-copilot-sdk"><img src="https://agentmods.dev/badge/skills/manu14357/zskills/azure-hosted-copilot-sdk.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 | $0.00062 | $0.03023 |
| Opus 5 | $0.00031 | $0.01511 |
| Sonnet 5 | $0.00012 | $0.00605 |
| Haiku 4.5 | $0.00006 | $0.00302 |
Grade A, and why
azure-hosted-copilot-sdk 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure Hosted Copilot SDK
Build production-grade copilots on Azure with enterprise controls, tool safety, and predictable operations.
Use This Skill When
- The user wants to build a customer-facing or internal assistant
- The user needs architecture for prompts, tools, retrieval, and safety
- The user needs deployment guidance and cost controls for copilot workloads
- The user asks about model routing, fallback, or multi-turn conversations
Context: Copilot Maturity
Immature: Hardcoded prompt, single model, no tool safety
Developing: Template-based system prompt, basic tool whitelist
Managed: Versioned prompts, tool isolation, token budgets, structured logging → Target
Optimized: Dynamic prompt selection, multi-model routing, real-time safety evaluation, feedback loops
Required Inputs
- Use case: Customer support? Data analyst? Content generator? Internal ops?
- User scale: <100 users? 1M+ concurrent users?
- Model provider: Azure OpenAI? Third-party API? Mixed?
- Tool access: What actions should the copilot take? (Email, DB query, file access?)
- Data scope: Should it access company data? User files? Public internet?
- Budget: Cost per user? Token budget per session?
- Latency: Real-time (<1s)? Batch acceptable?
- Compliance: PII handling? Data residency? Audit requirements?
Decision Tree
What's the primary use case?
├─ Customer support (knowledge base, FAQ) → Retrieval augmented generation (RAG)
├─ Data analysis (SQL queries, spreadsheets) → Tool calling + sandbox
├─ Content generation (marketing, docs) → Fine-tuned or prompt-engineered
├─ Internal assistant (ops, IT help) → Multi-tool + controlled access
└─ Specialized domain (medical, legal) → Compliance checks + audit trail
How many users will this serve?
├─ < 100 (pilot) → Single model, shared prompt, simple logging
├─ 100-10K (growing) → Multi-instance, load balancing, token budgets
└─ 10K+ (scale) → Multi-region, model fallback, cost controls
What data should the copilot access?
├─ None (generic) → Just prompt engineering
├─ Public data → Semantic search, embeddings
├─ Private company data → Secure retrieval, managed identity, auditable
└─ User-specific data → Tenant isolation, row-level access control
What actions can the copilot take?
├─ Read-only (analyze, explain) → No tool safety needed
├─ Read-write (email, create docs) → Tool sandboxing, approval workflows
└─ Restricted (delete, financial) → Explicit approval, audit trail, rate limits
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 · 387 lines · 62 tokens per session scan A 096d931a3467
azure-hosted-copilot-sdk is a skill published in the GitHub repository manu14357/zskills (16 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 3,023 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…