live-tests

A skill for writing integration tests that call the real GitHub Copilot API and save its responses as reusable test fixtures.

In plain words
What is it for?
It helps test new agent behavior, provider integrations, tool calls, multi-turn conversations, and error handling against real API responses.
Why use it?
It provides recorded responses for repeatable tests, so most test runs do not need to call the live service.

Skill for Claude CodeCodex

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/matteing/opal/live-tests
Any agent
npx skills add matteing/opal --skill live-tests
Clone the repo
git clone --depth 1 https://github.com/matteing/opal

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,468 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00044 $0.01468
Opus 5 $0.00022 $0.00734
Sonnet 5 $0.00009 $0.00294
Haiku 4.5 $0.00004 $0.00147

Measured 2d ago against content hash e2d6d98e58b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

live-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 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.

.claude/skills/live-tests/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Live Test & Fixture Recording Skill

You write live integration tests that exercise the real GitHub Copilot API and capture responses as JSON fixtures for deterministic replay. This is the project's VCR-like system for ensuring tests stay grounded in real API behavior.

Architecture overview

Live test (mix test --include live --include save_fixtures)
  │
  ├─ RecordingProvider  ← wraps real Copilot provider, captures SSE events
  │     │
  │     └─ persistent_term storage ← events buffered here during stream
  │
  └─ FixtureHelper.save_fixture/2  ← writes events to JSON file
        │
        └─ test/support/fixtures/<name>.json

Fixture-based test (mix test)
  │
  ├─ FixtureProvider  ← reads fixture JSON, replays events via Req.Response.Async
  │     │
  │     └─ FixtureHelper.build_fixture_response/1 ← spawns process to send SSE events
  │
  └─ Assertions on agent behavior, events, tool calls, etc.

When to act

  • Adding a new agent behavior that needs a new fixture (e.g., new tool call pattern, multi-turn conversation, error handling).
  • Adding or changing provider integration logic.
  • When the user asks to "record a fixture", "add a live test", or "capture API responses".
  • When an existing fixture is stale and needs re-recording.

Writing a live test

Live tests go in test/opal/live_test.exs. They require @moduletag :live (excluded by default) and use the RecordingProvider to capture real SSE events.

Template

describe "live API — <scenario description>" do
  @tag :save_fixtures
  @tag timeout: 30_000
  test "records <what this captures>" do
    RecordingProvider.start_recording()

    {:ok, pid} =
      Opal.start_session(%{
        model: {:copilot, "claude-sonnet-4"},
        system_prompt: "<constrained prompt that produces deterministic output>",
        tools: [<tool modules if needed>],
        working_dir: System.tmp_dir!(),
        provider: RecordingProvider
      })

    {:ok, response} = Opal.prompt_sync(pid, "<user message>", 25_000)
    Opal.stop_session(pid)

    events = RecordingProvider.stop_recording()
    assert length(events) > 0

    # Save as a fixture for replay
    path = FixtureHelper.save_fixture("<descriptive_name>.json", events)
    assert File.exists?(path)

    # Assertions on the live response
    assert is_binary(response)
    assert String.contains?(response, "<expected content>")
  end
end

Read the full file on GitHub · 168 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. 2d ago First seen · 168 lines · 44 tokens per session scan A e2d6d98e58b1

Subscribe to this mod's changes

live-tests is a skill published in the GitHub repository matteing/opal (59 stars, last pushed 20d ago), licensed MIT. It adds 44 tokens to every session and 1,468 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

agent-pattern-verification

Verify AI agent code for dangerous patterns including infinite loops, unbounded retries, tool hallucinations, and context overflow. Use before deploying agent workflows or when reviewing agent code.

aryaminus/controlkeel · 39 tokens

cloudflare-agent

Enable ControlKeel governance for Cloudflare Agents with policy gates, budget enforcement, PII detection, and secure execution.

aryaminus/controlkeel · 28 tokens

continuity

Learn, record, audit, and apply codebase patterns consistently across a repo by comparing current code to canonical local examples stored in CK memory. Use when asked to preserve continuity, learn a pattern, check drift, fix inconsistent implementations, or enforce local conventions.

aryaminus/controlkeel · 54 tokens

controlkeel-governance

Operate inside a ControlKeel-governed session. Use this before code edits, shell execution, delegation, deploy work, or any task that needs CK validation, findings, budget, proof, or routing context.

aryaminus/controlkeel · 50 tokens

plan-slice

Decompose an aligned goal into independently executable vertical slices with explicit blocking relationships. Each slice must cross all touched system layers — not a single layer. Submit for human approval before any implementation begins.

aryaminus/controlkeel · 42 tokens

bounded-loop

Run objective, repeatable improvement work under an immutable verifier and hard iteration, cost, time, and no-progress limits. Use for approved experiments with an automated metric and sandboxed worker.

aryaminus/controlkeel · 40 tokens