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/microsoft/copilot-camp/foundry-researchnpx skills add microsoft/copilot-camp --skill foundry-researchgit clone --depth 1 https://github.com/microsoft/copilot-campWhat 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 | $0.00079 | $0.00914 |
| Opus 5 | $0.00039 | $0.00457 |
| Sonnet 5 | $0.00016 | $0.00183 |
| Haiku 4.5 | $0.00008 | $0.00091 |
Grade A, and why
foundry-research 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 2d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Foundry Research Skill
What This Skill Does
This skill helps you deep-dive into Microsoft Foundry documentation and capabilities by:
- Searching multiple topics across Microsoft Foundry documentation
- Collecting architecture guides, model documentation, and deployment patterns
- Organizing findings into clear sections (Overview, Architecture, Models, Deployment, Best Practices)
- Generating a comprehensive research summary with links and code samples
When to Use This Skill
Activate this skill when you need:
- Overview of Microsoft Foundry platform and components
- Understanding of available models and their capabilities
- Deployment and configuration guidance
- Best practices for building with Foundry
- Integration patterns with Azure services
- Code samples and quickstart guides
Workflow
Step 1: Topic Definition
Ask the user to clarify their specific Foundry interest:
- Foundry platform overview? (architecture, components)
- Specific model? (which model and its capabilities)
- Deployment scenario? (local, cloud, hybrid)
- Integration use case? (agents, workflows, content generation)
Step 2: Multi-Topic Research
Conduct multiple searches across the Microsoft Learn MCP Server:
- Search: "Microsoft Foundry platform overview architecture"
- Search: "Microsoft Foundry models and capabilities"
- Search: "Microsoft Foundry deployment options"
- Search: "Microsoft Foundry best practices"
- Search: Specific topic based on user interest (e.g., "Foundry agents", "Foundry fine-tuning")
Step 3: Information Organization
Compile findings into these sections:
## Microsoft Foundry Research Summary
### Overview
[Platform description, key components, use cases]
### Architecture
[System design, core components, integration points]
### Available Models
[Model list with capabilities, performance characteristics]
### Deployment Options
[Local development, cloud deployment, hybrid approaches]
### Best Practices
[Recommended patterns, performance optimization, security]
### Getting Started
[Quickstart guides, code examples, resources]
### Related Services
[Azure integration, complementary services]
### Additional Resources
[Links to official documentation and samples]
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.
- 2d ago First seen · 129 lines · 79 tokens per session scan A 1adf30ef8d4e
foundry-research is a skill published in the GitHub repository microsoft/copilot-camp (654 stars, last pushed 19d ago), licensed MIT. It adds 79 tokens to every session and 914 once invoked, about $0.0004 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.