qa-e2e-perf

A live-cluster performance check for MCP Runtime, measuring request speed and throughput under controlled concurrent use.

In plain words
What is it for?
Use it to compare MCP tool-call latency, gateway throughput, analytics latency, and operator reconciliation speed.
Why use it?
It shows whether a code change made the system slower compared with a saved branch baseline, rather than relying only on unit tests.

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/agent-hellboy/mcp-runtime/qa-e2e-perf
Any agent
npx skills add Agent-Hellboy/mcp-runtime --skill qa-e2e-perf
Clone the repo
git clone --depth 1 https://github.com/Agent-Hellboy/mcp-runtime

Made for: Claude Code, Codex.

Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,166 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 $0.00124 $0.03166
Opus 5 $0.00062 $0.01583
Sonnet 5 $0.00025 $0.00633
Haiku 4.5 $0.00012 $0.00317

Measured 2d ago against content hash 9be8999c7a26, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-e2e-perf 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 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.

Makes network callslowCapability

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

import json, time, urllib.request, sys
.codex/skills/qa-e2e-perf/SKILL.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA — E2E Performance (live cluster)

Overview

Performance regressions hide between unit tests (no concurrency, no real gateway) and full load tests (rare, expensive). This skill runs a short, deterministic perf matrix against the live contributor cluster and compares results to a stored baseline. It is not a load test — it does not saturate the cluster; it measures whether a change moved the curve.

Numbers measured on a Kind cluster are not production numbers. The point is relative: did this branch regress vs main or vs the last recorded baseline.

Regression evidence contract: do not report a perf pass from a single request or current-branch-only sample. A pass requires baseline comparison, warmup, scenario sample counts, p50/p95/p99, and the configured regression threshold; missing baseline or live cluster access is blocked unless the user accepts baseline creation as the task.

Step 1 — Confirm precondition

kubectl config current-context | grep -qx kind-mcp-runtime \
  || { echo "Run qa-cluster-bringup first"; exit 1; }
./bin/mcp-runtime cluster doctor
# Quiet the cluster: drain any leftover concurrent traffic from prior skills.
sleep 5

Record the environment (CPU, mem, kernel, kind node count, image SHAs) into the report. Perf numbers without an environment line are not comparable.

sysctl -n hw.ncpu 2>/dev/null || nproc
kubectl get nodes -o wide
kubectl -n mcp-sentinel get deploy -o jsonpath='{range .items[*]}{.metadata.name}={.spec.template.spec.containers[0].image}{"\n"}{end}'

Step 2 — Choose mode

  • head-only. Run all four scenarios.
  • git-range (BASE=<merge-base>, default origin/main). Trim by diff:
Diff touches Scenarios to run
services/mcp-gateway/**, pkg/access/** S1, S2 (gateway hot path)
internal/operator/** S4 (reconcile burst)
services/platform-api/**, services/runtime-api/**, services/analytics-api/**, services/processor/**, services/ingest/** S3 (analytics)
services/ui/** static only Skip — UI is not the hot path
config/ingress/** S1, S2 (Traefik path-routing)

Read the full file on GitHub · 254 lines

Files

What ships with it

3 files 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. 2d ago First seen · 254 lines · 124 tokens per session scan A 9be8999c7a26

Subscribe to this mod's changes

qa-e2e-perf is a skill published in the GitHub repository Agent-Hellboy/mcp-runtime (5 stars, last pushed 8d ago), licensed Apache-2.0. It adds 124 tokens to every session and 3,166 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

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

release-notes

Create release notes for a new version tag. Gathers all commits, PRs, issues fixed, and breaking changes since a previous release. Creates the release notes markdown file, tags the repo, and pushes. Asks the user to confirm the base version to diff against.

agentic-community/mcp-gateway-registry · 59 tokens

agentcore-register

Given an MCP server URL, probe the server via curl to discover its metadata and tools, then generate a markdown file with copy-pasteable content for each field in the Amazon Bedrock AgentCore "Create record" form.

agentic-community/mcp-gateway-registry · 49 tokens

debug

Debug issues in the MCP Gateway Registry using first-principles thinking. Invoke when something is broken, timing out, returning errors, or behaving unexpectedly. Forces structured root-cause analysis before any code change is proposed.

agentic-community/mcp-gateway-registry · 45 tokens

search-benchmark

Generate a search quality benchmark for the AI Registry. Generates ground truth from the registry's assets, runs 100+ queries against the semantic search API, evaluates results using NDCG@10/MRR/Recall, and produces a markdown report. Use when you want to measure search quality after changes to the scoring algorithm…

agentic-community/mcp-gateway-registry · 75 tokens

benchmark-report

Generate a benchmark report from stress test results (registration, API performance, search concurrency). Reads JSON result files and produces a markdown report suitable for docs/benchmarks/.

agentic-community/mcp-gateway-registry · 36 tokens