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/aks-lab-githubcopilot/a2a-loopback-testsnpx skills add microsoft/AKS-Lab-GitHubCopilot --skill a2a-loopback-testsgit clone --depth 1 https://github.com/microsoft/AKS-Lab-GitHubCopilotWhat 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 | $0.00000 | $0.00645 |
| Opus 5 | $0.00000 | $0.00322 |
| Sonnet 5 | $0.00000 | $0.00129 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
a2a-loopback-tests 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 yesterday.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: A2A Loopback Tests
Use this skill in test-author mode when writing integration tests that exercise multiple agents without Docker.
The fixture
# tests/integration/conftest.py
import httpx
import pytest
from httpx import ASGITransport
from agent_framework.testing import MockChatClient
from src.agents.inventory.server import app as inventory_app
from src.agents.supplier.server import app as supplier_app
# ...orchestrator etc.
@pytest.fixture
async def fleet(monkeypatch):
# 1. Patch GitHubCopilotAgent at every agent's import site so the
# real SDK / bundled Node CLI never starts.
fake = MockChatClient() # exposes async .run(message) -> AgentResponse[None]
for mod in (
"src.agents.inventory.agent",
"src.agents.supplier.agent",
"src.agents.logistics.agent",
"src.agents.pricing.agent",
"src.agents.orchestrator.agent",
):
monkeypatch.setattr(f"{mod}.GitHubCopilotAgent", lambda **_: fake)
# 2. Mount each FastAPI app behind ASGITransport.
clients = {
"inventory": httpx.AsyncClient(transport=ASGITransport(app=inventory_app),
base_url="http://inventory"),
# ... etc
}
yield clients
for c in clients.values():
await c.aclose()
Rules
- Never import
GitHubCopilotAgentdirectly in a test — always patch its import site so the real SDK / Node CLI never runs. - Never start a real network server (no
uvicorn.run). ASGITransport only. - Do not patch
MCPStreamableHTTPTool— it is not used in this repo. MCP wiring lives insideGitHubCopilotOptions(mcp_servers={...}); the agent is already mocked at step 1, so MCP is short-circuited automatically. - Assert structure (
response.json()["tool_calls"]) and keyword presence ("store-101" in response.json()["output"]). No exact string equality. - Mark every test
pytest.mark.asyncio(or rely onasyncio_mode = "auto"inpyproject.toml).
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.
- yesterday First seen · 66 lines · 0 tokens per session scan A a62e38630b79
a2a-loopback-tests is a skill published in the GitHub repository microsoft/AKS-Lab-GitHubCopilot (7 stars, last pushed 27d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 645 tokens. 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…