Microsoft Discovery is an extensible platform for scientific research and research-and-development workflows that combines agent orchestration, reasoning, graph-based knowledge, and high-performance computing. Researchers, partners, and product users use its Azure enterprise platform or local Windows app to explore and build research workflows. The catalogue entries provide skills and instructions for working with the Discovery community and platform.
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 microsoft/discovery --skill add-example-agentsgit clone --depth 1 https://github.com/microsoft/discoveryWrote 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/microsoft/discovery/add-example-agents)<a href="https://agentmods.dev/skills/microsoft/discovery/add-example-agents"><img src="https://agentmods.dev/badge/skills/microsoft/discovery/add-example-agents/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/microsoft/discovery/add-example-agents"><img src="https://agentmods.dev/badge/skills/microsoft/discovery/add-example-agents.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 | $0.00622 | $0.36126 |
| Opus 5.5 | $0.00249 | $0.14450 |
| Sonnet 5.5 | $0.00124 | $0.07225 |
| Haiku 4.5 | $0.00062 | $0.03613 |
Grade A, and why
add-example-agents 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 29d 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 — 2,677 lines — stays where its author put it; the contents beside it link to each section on GitHub.
add-example-agents
Add agents from the public microsoft/discovery repository to this
workspace, then deploy each selected agent to exactly one of two targets:
- Local Copilot - emit a
.github/agents/<name>.agent.mdcompanion for every agent so it can be invoked as a Copilot subagent viarunSubagent. Tool container images are built lazily on first invocation, locally only. - Microsoft Discovery + Azure - pre-flight every tool the agent
declares via
GetDiscoveryToolagainst the workspace's RG. When a tool ARM resource already exists (common for shared catalog images on registries likemdqacr), skip Docker build / ACR push / AcrPull RBAC entirely and bind the existing ARM ID. When a tool is missing, build + push viaaz acr build, register the tool ARM, grant AcrPull. Either way, create the agent in the target Discovery project viaUpsertAgentand pollGetAgentuntilprovisioningState=Succeeded. Local Discovery runtime registration (agents action=create) is optional and skipped by default. - Local app → Microsoft Discovery + Azure (promote) - take an agent
that is already added to the local Copilot app (present under
discovery_catalog/<name>/with a.github/agents/<name>.agent.mdcompanion and, for tool-bearing agents, a locally-built container image) and register it in a specific Discovery project. The local folder is the source of truth - the upstreammicrosoft/discoveryrepo is not fetched or refreshed, so any local edits are preserved. Tool container(s) are pushed to ACR from the local build context / locally-built image, then the agent is created viaUpsertAgentand polled withGetAgentexactly as in the upstream-sourced Discovery path.
The user picks the deployment target first (Step 4c), then — only for a Discovery-class target (Discovery or LocalToDiscovery) — confirms the destination workspace + project (Step 4d), and then chooses which agents to add (Step 4e).
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.
- 29d ago First seen · 2,677 lines · 622 tokens per session scan A 20b302fec6f8
add-example-agents is a skill published in the GitHub repository microsoft/discovery (267 stars, last pushed today), licensed MIT. It adds 622 tokens to every session and 36,126 once invoked, about $0.0025 per session on Opus 5.5. 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 2026-09-23.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".