agentmods.dev

test-local

test-local is a skill for Claude Code from microsoft/agent365-skills. It costs 133 tokens per session (4,397 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 Code ✓ vendor

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the agent365 plugin — 8 skills shipped together

not rated 51repo +1 changed 22d ago D scan 133 tokens original MIT

Good fit Use it to build-check an agent, start it locally, send test messages, and inspect observability logs when available.

Compare 6 skills from other repositories ↓
View source ↗ microsoft/agent365-skills
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 · 51 stars · on GitHub

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add microsoft/agent365-skills
Claude Code
/plugin install agent365

Made for: Claude Code.

Or install agent365, the plugin that ships this one along with the rest of its 8 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/github.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/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.

agentmods 80×15 button for test-local

Your own site · 80×15
<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="Reviewed on agentmods" width="80" 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 4,397 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00133 $0.04397
Opus 5.5 $0.00053 $0.01759
Sonnet 5.5 $0.00027 $0.00879
Haiku 4.5 $0.00013 $0.00440

Measured 22d ago against content hash 30ac573c4dc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 22d 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 · 418 lines

How it starts

The opening of the file, as written. The whole thing — 418 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 · 418 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. 22d ago Changed 30ac573c4dc6
  2. 1mo ago Changed · +1 lines d0d402f127fa
  3. 2mo 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 (51 stars, last pushed 17d ago), licensed MIT. It adds 133 tokens to every session and 4,397 once invoked, about $0.0005 per session on Opus 5.5. 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.

Building agentsE2E testingTesting
Related

test-local compared with skills from other repositories

test-local next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
test-localmicrosoft/agent365-skillsSkill5117d agoMITD133Claude Code
verify-omnigentomnigent-ai/omnigentSkill11ktodayApache-2.0A100Claude Code, Codex
test-masterJeffallan/claude-skillsSkill12k8d agoMITA104Claude Code
eval-dataset-designbojieli/ai-agent-bookSkill57k1mo agoApache-2.0A138Claude Code, Codex
dogfoodcallstack/agent-deviceSkill5.3ktodayMITA55Claude Code
cua-driverdavidondrej/skillsSkill4.3ktodayMITA68Claude Code, Codex
test-warp-uiwarpdotdev/warpSkill66ktodayAGPL-3.0A55Claude Code