test-local

test-local is a skill for Claude Code, Codex from microsoft/agent365-skills. It costs 133 tokens per session (4,238 once invoked), scanned D, original, MIT.

A local testing workflow for AI agents that starts the agent on your computer and opens AgentsPlayground, a web interface that imitates a Microsoft Teams chat. It supports .NET, Node.js, and Python agent frameworks.

In plain words
What is it for?
Use it to build-check an agent, start it locally, send test messages, and inspect observability logs when available.
Why use it?
It lets you test and debug an agent before deploying it or setting up Bot Framework authentication.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the agent365 plugin — 7 skills shipped together

About the project

Microsoft Agent 365 Skills is a collection of coding-agent skills and MCP configuration for building and operating AI Teammates hosted in Microsoft Teams. It supports the Agent 365 lifecycle, including WorkIQ integration, registration, observability, validation, and local testing, for users of Claude Code and GitHub Copilot.

microsoft/agent365-skills · 34 stars · on GitHub

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.

agentmods
npx agentmods add skills/microsoft/agent365-skills/test-local
Any agent
npx skills add microsoft/agent365-skills --skill test-local
Clone the repo
git clone --depth 1 https://github.com/microsoft/agent365-skills

Made for: Claude Code, Codex.

Or install agent365, the plugin that ships this one along with the rest of its 7 skills.

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.

agentmods badge for test-local

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/agent365-skills/test-local.svg)](https://agentmods.dev/skills/microsoft/agent365-skills/test-local)
Your own site
<a href="https://agentmods.dev/skills/microsoft/agent365-skills/test-local"><img src="https://agentmods.dev/badge/skills/microsoft/agent365-skills/test-local.svg" alt="Measured on agentmods" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,238 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00133 $0.04238
Opus 5 $0.00067 $0.02119
Sonnet 5 $0.00027 $0.00848
Haiku 4.5 $0.00013 $0.00424

Measured 5d ago against content hash ebdcdc8e71a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

test-local scanned grade D with 3 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 5d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

Linux: sudo apt-get update && sudo apt-get install -y dotnet-sdk-8.0

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

(or via nvm: curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash && nvm install --lts)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

(or via nvm: curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash && nvm install --lts)
plugins/agent365/skills/test-local/SKILL.md · 417 lines

How it starts

The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Agent Locally (AgentsPlayground)

Trigger phrases — any of these will activate this skill automatically:

  • "test this agent locally"
  • "run my agent locally"
  • "open agentsplayground"
  • "launch agentsplayground"
  • "start a local test session"
  • "debug this agent locally"
  • "test my agent without deploying to teams"
  • "spin up a local test"

Overview

This skill starts your agent on localhost and opens AgentsPlayground — a local web UI that simulates a Teams-like chat interface without requiring a deployment or Bot Framework auth.

What it does:

  1. Detects agent language and framework (.NET, Node.js, or Python)
  2. Checks agentsplayground is installed — installs if missing
  3. Builds the agent to confirm there are no compile errors
  4. Starts the agent in the background
  5. Launches AgentsPlayground pointed at the local endpoint
  6. Guides a local test and confirms observability logs are flowing (if instrumented)

Why AgentsPlayground works for all AI Teammate stacks:

  • Web UI that matches the Teams message format
  • Connects to /api/messages over HTTP — the LLM framework on the server side does not matter
  • The -c emulator flag bypasses Bot Framework auth — no extra config needed for any stack
  • requireAuth: false in MapAgentApplicationEndpoints is the only .NET-specific prerequisite

All actions are read-only against your codebase — no code is modified.


Phase 0 — Create and Display Task List

Show the user this checklist BEFORE Phase 1. Exactly one task in_progress at a time; complete before moving on. Use whichever mechanism the runtime supports:

  • Claude Code: call TaskCreate for each item below (already in allowed-tools); the list renders natively. Use TaskUpdate to flip statuses.
  • VS Code Copilot Chat / GitHub Copilot CLI: allowed-tools is ignored — emit a markdown checklist directly in chat (- [ ] Detect agent type…) and edit items to - [x] as each phase completes.

Read the full file on GitHub · 417 lines

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.

  1. 5d ago First seen · 417 lines · 133 tokens per session scan D ebdcdc8e71a1

Subscribe to this mod's changes

test-local is a skill published in the GitHub repository microsoft/agent365-skills (34 stars, last pushed 9d ago), licensed MIT. It adds 133 tokens to every session and 4,238 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

run-integration-tests

Build, pack, and run .NET MAUI integration tests locally. Validates templates, samples, and end-to-end scenarios using the local workload.

dotnet/maui · 35 tokens

cli-e2e-testcase-writer

Use when adding or updating Go CLI E2E coverage for one tests/clie2e/{domain} domain of the compiled lark-cli, especially when the work requires live --help or schema exploration, scenario-based clie2e.RunCmd workflows, and per-domain coverage.md maintenance.

larksuite/cli · 78 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

every-app/open-seo · 35 tokens

harness-test-writer

Add regression test cases to the Bifrost provider harness (the Postman collection run via make run-provider-harness-test) based on a merged PR or a GitHub issue. Fetches the PR/issue, traces the affected wire path in the codebase, checks existing harness coverage, designs cases following harness conventions, inserts…

maximhq/bifrost · 133 tokens

agent-device-evidence

Records iOS/Android native MP4 evidence for test/repro flows extracted from an Expensify GitHub PR or issue. Use when the user asks to "record the flow for PR.

Expensify/App · 43 tokens