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/caipe-io/ai-platform-engineering/streaming-testingnpx skills add caipe-io/ai-platform-engineering --skill streaming-testinggit clone --depth 1 https://github.com/caipe-io/ai-platform-engineeringWrote 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.
[](https://agentmods.dev/skills/caipe-io/ai-platform-engineering/streaming-testing)<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>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.
| Model | Per session | Once 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 |
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.
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` 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
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.
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.
- 5d ago First seen · 151 lines · 40 tokens per session scan A c7a4e907ec0a
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.
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.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
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…
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.
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).
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.