What is foundry-agent?

A skill for using the FoundryX command-line tool to manage Microsoft Foundry projects, models, tools, agents, publishing, conversations, evaluations, metrics, and hosted-agent diagnostics. Microsoft Foundry is a platform for building and operating AI agents.

Use it to authenticate with FoundryX, manage access and projects, build or publish agents, run conversations and evaluations, and inspect operational diagnostics.

It gives the agent a defined route for FoundryX tasks and prevents it from using unrelated command-line tools or direct HTTP calls. It also checks the required installation and sign-in state.

foundry-agent — Skill for Claude Code and Codex by microsoft

About the project

Microsoft Foundry DevTools is a collection of developer tools, documentation, community resources, and source code for building, deploying, evaluating, and managing AI applications and agents with Microsoft Foundry. Developers use its terminal tools, coding-agent guidance, VS Code toolkit, and Foundry Canvas to choose a development workflow. The catalogue includes a Foundry skill that gives coding agents reusable guidance for working with Foundry.

microsoft/foundry-dev-tools · 2,056 stars · on GitHub · microsoft.github.io

Install

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.

Any agent

npx skills add microsoft/foundry-dev-tools --skill foundry-agent

Clone the repo

git clone --depth 1 https://github.com/microsoft/foundry-dev-tools

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/microsoft/foundry-dev-tools/foundry-agent/github.svg)](https://agentmods.dev/skills/microsoft/foundry-dev-tools/foundry-agent)

Your own site

<a href="https://agentmods.dev/skills/microsoft/foundry-dev-tools/foundry-agent"><img src="https://agentmods.dev/badge/skills/microsoft/foundry-dev-tools/foundry-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/microsoft/foundry-dev-tools/foundry-agent"><img src="https://agentmods.dev/badge/skills/microsoft/foundry-dev-tools/foundry-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,110 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00073	$0.06110
Opus 5.5	$0.00029	$0.02444
Sonnet 5.5	$0.00015	$0.01222
Haiku 4.5	$0.00007	$0.00611

Measured 2d ago against content hash be0dc4f5bffc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

foundry-agent 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.

foundry-agent/skills/foundry-agent/SKILL.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IMPORTANT: When manually invoked by /foundry-agent, use the installed foundryx CLI. Do not run the requested operation through az, azd, the microsoft-foundry skill, or the microsoft-foundry canvas plugin.

FoundryX

After a customer tenant is onboarded to FoundryX via Entra admin consent, users in that tenant use the foundryx CLI to create Foundry projects, manage project access, and build, deploy, and operate Agents. Parse structured CLI stdout directly, pass optional formatting flags only when supported by a command's --help, and do not bypass the CLI with direct HTTP scripts or Azure/toolkit commands.

CLI prerequisite: Use the installed CLI. Install only if missing or an encountered issue suggests a version mismatch, not merely because its version differs from this skill.

When installation or a version-related update is needed, use FoundryX GitHub releases:

Select a published FoundryX CLI release matching this skill's version, including prereleases. Use the release's full version string; do not use GitHub's latest-release endpoint.
Download the binary for the user's OS and architecture.
Install as foundryx.exe on Windows or foundryx on macOS/Linux in a user-owned binary directory, add that directory to the user PATH, and run chmod +x on macOS/Linux. Use the absolute executable path until the current session's PATH is refreshed. Linux sign-in requires libsecret-1 and a running Secret Service/keyring.
Run the installed executable with --version and confirm it matches the selected release before continuing.

Authentication prerequisite (foundryx auth): Before running project or Agent commands, check foundryx auth status. Run foundryx auth login when authenticated: false, or foundryx auth login --tenant <tenant-id> to switch Entra tenants (let the user complete interactive Entra prompts; foundryx auth logout clears both FoundryX and publishing sessions).

Match the user's request against Capability and When to use in the routing table below, then follow the linked workflow or references/*.md:

Capability	When to use	CLI Commands	Guide / Reference
Create a Foundry project	Checking permission to create a Foundry project, selecting a subscription/region, inspecting initial deployable models/quota, or creating a Foundry project	`foundryx access project *`	Create a Foundry project
Manage Foundry project access	Granting, updating, or removing Foundry project access (`consumer`, `user`, `manager`, `owner`) for a single user, an Entra group, or all tenant users	`foundryx access project list --manageable`, `foundryx access user `, `foundryx access member `	Manage Foundry project access
Manage Foundry models	Listing, viewing, or calling project models, inspecting model catalog/quota, or deploying, scaling, and deleting project model deployments	`foundryx model *`, `foundryx operation show`	Foundry models
Build, deploy & operate Agents	Discovering and reusing existing project tools/Toolboxes, scaffolding, locally testing, deploying, invoking, or debugging Prompt and Hosted Agents	`foundryx access project list`, `foundryx connection list\|show`, `foundryx toolbox list\|show`, `foundryx agent *`	Foundry Agents Discover and reuse tools Prompt Agent tools Hosted Agent Toolbox
Administer tool resources	Explicitly requested connection configuration/credential lifecycle or Toolbox version/default/deletion administration; never an automatic builder fallback	`foundryx connection create\|update\|credentials set\|delete`, `foundryx toolbox create\|version create\|publish\|delete\|version delete`	RemoteTool MCP connections Toolboxes & versions
Prepared trial resources	User explicitly asks for `GitHubToolbox`, `GitHubOAuthToolbox`, `WorkIQToolbox`, or Contoso enterprise documents/policies	`foundryx access project list`, `foundryx agent *`	Prepared trial resources Contoso enterprise knowledge
Trace and diagnose Agents	Searching conversations, reconstructing traces, diagnosing failures or latency, or correlating response-level evaluation events	`foundryx agent trace query`	Agent tracing
Evaluate, monitor & publish Agents	Running Agent evaluations (`eval.yaml`), querying Application Insights operational metrics, or publishing a deployed Agent to M365/Teams	`foundryx agent eval `, `foundryx agent metrics`, `foundryx auth publish `, `foundryx agent publish\|publish-status`	Inspect, diagnose, evaluate, monitor & publish Agent evaluation Operational metrics M365 / Teams publishing
Open FoundryX canvas	User explicitly asks to list or view deployed Agents	`foundryx-canvas` canvas	FoundryX Canvas

Read the full file on GitHub · 323 lines

Files

What ships with it

12 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.

Changes

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 Changed be0dc4f5bffc
3d ago Changed · +9 lines 4472df49324e
5d ago First seen · 314 lines · 73 tokens per session scan A 4674477cd4e7

Subscribe to this mod's changes

foundry-agent is a skill published in the GitHub repository microsoft/foundry-dev-tools (2,056 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 6,110 once invoked, about $0.0003 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 2026-10-20.

Building agents

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…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

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.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.