streaming-testing

streaming-testing is a skill for Claude Code, Codex from caipe-io/ai-platform-engineering. It costs 40 tokens per session (1,541 once invoked), scanned A, original, Apache-2.0.

A testing toolkit for comparing how different versions of an agent-to-agent service send live responses. It records server-sent events, checks message metadata, and creates a side-by-side Markdown report.

In plain words
What is it for?
Use it to capture and validate streaming responses from two running supervisor versions, then compare their event timelines and metadata.
Why use it?
It makes differences between service versions visible, including whether messages are narration or the final answer.

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/caipe-io/ai-platform-engineering/streaming-testing
Any agent
npx skills add caipe-io/ai-platform-engineering --skill streaming-testing
Clone the repo
git clone --depth 1 https://github.com/caipe-io/ai-platform-engineering

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.

agentmods badge for streaming-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/caipe-io/ai-platform-engineering/streaming-testing.svg)](https://agentmods.dev/skills/caipe-io/ai-platform-engineering/streaming-testing)
Your own site
<a href="https://agentmods.dev/skills/caipe-io/ai-platform-engineering/streaming-testing"><img src="https://agentmods.dev/badge/skills/caipe-io/ai-platform-engineering/streaming-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,541 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00040 $0.01541
Opus 5 $0.00020 $0.00771
Sonnet 5 $0.00008 $0.00308
Haiku 4.5 $0.00004 $0.00154

Measured 5d ago against content hash c7a4e907ec0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

streaming-testing scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 1 executable file (run_comparison.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

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

1. Verify the supervisor is healthy: `curl http://localhost:8000/.well-known/agent.json`
.claude/skills/streaming-testing/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Streaming Testing

Compare A2A streaming behaviour across supervisor versions (e.g. 0.3.0 vs 0.2.41). Captures SSE events, analyzes metadata correctness, and generates side-by-side markdown reports.

Prerequisites

  • Docker Compose dev stack running (docker-compose.dev.yaml)
  • 0.3.0 supervisor on port 8000 (caipe-supervisor)
  • 0.2.41 supervisor on port 8041 (caipe-supervisor-041)
  • Python 3.10+ (scripts use stdlib only — no pip install needed)

Quick Start

# One command — captures from both supervisors, analyzes, compares
./skills/streaming-testing/run_comparison.sh "what can you do?"

# Output lands in /tmp/streaming-comparison-<timestamp>.md

Individual Scripts

All scripts live in scripts/ and use Python stdlib only.

Script Purpose Usage
trace_a2a_streaming.py SSE timeline with summary stats python3 scripts/trace_a2a_streaming.py 8000 "query"
capture_a2a_events.py Save raw A2A events to JSON python3 scripts/capture_a2a_events.py http://localhost:8000/ "query" /tmp/out.json
analyze_a2a_metadata.py Validate metadata flags in a capture python3 scripts/analyze_a2a_metadata.py /tmp/out.json
compare_a2a_events.py Side-by-side comparison of two captures python3 scripts/compare_a2a_events.py /tmp/a.json /tmp/b.json
analyze_accumulation_flow.py Content accumulation + duplicate detection python3 scripts/analyze_accumulation_flow.py "query" --port 8000
validate_artifacts.py Parse/validate artifact reports python3 scripts/validate_artifacts.py --query "query" --port 8000

Workflow

Step 1: Capture events from both supervisors

python3 scripts/capture_a2a_events.py http://localhost:8000/ "what can you do?" /tmp/cap-030.json
python3 scripts/capture_a2a_events.py http://localhost:8041/ "what can you do?" /tmp/cap-041.json

Step 2: Analyze metadata on each capture

python3 scripts/analyze_a2a_metadata.py /tmp/cap-030.json
python3 scripts/analyze_a2a_metadata.py /tmp/cap-041.json

Read the full file on GitHub · 151 lines

Files

What ships with it

1 file 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.

  1. 5d ago First seen · 151 lines · 40 tokens per session scan A c7a4e907ec0a

Subscribe to this mod's changes

streaming-testing is a skill published in the GitHub repository caipe-io/ai-platform-engineering (405 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 1,541 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (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

verify

Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.

Hmbown/CodeWhale · 25 tokens

webapp-testing

Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.

Hmbown/CodeWhale · 32 tokens

tutti-record-agent-session-replay

From a Tutti checkout, run, audit, freshly replay, publish, or diagnose Session Replay cassettes that are driven by case-repository scenario scripts (CDP), not by interactive UI recording. Use for real-Provider capture while a scenario.mjs executes, cassette transport or semantic-state mismatches, fresh replay…

tutti-os/tutti · 127 tokens

local-frontend-check

Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.

ascending-llc/jarvis-registry · 52 tokens

qa

Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).

SethGammon/Citadel · 56 tokens

live-preview

Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.

SethGammon/Citadel · 40 tokens