local-integration-testing

local-integration-testing is a skill for Claude Code, Codex from caipe-io/ai-platform-engineering. It costs 44 tokens per session (1,917 once invoked), scanned A, original, Apache-2.0.

A local end-to-end test setup for a multi-agent application running in Docker Compose. It checks whether agents can be found, routed to, and resumed with saved checkpoints.

In plain words
What is it for?
Use it to validate agent discovery, routing, saved progress, and follow-up conversations across the full stack.
Why use it?
It tests the complete local system instead of checking agents one at a time, helping reveal integration failures between services.

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/integration-testing
Any agent
npx skills add caipe-io/ai-platform-engineering --skill integration-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 local-integration-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/caipe-io/ai-platform-engineering/integration-testing.svg)](https://agentmods.dev/skills/caipe-io/ai-platform-engineering/integration-testing)
Your own site
<a href="https://agentmods.dev/skills/caipe-io/ai-platform-engineering/integration-testing"><img src="https://agentmods.dev/badge/skills/caipe-io/ai-platform-engineering/integration-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,917 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 $0.01917
Opus 5 $0.00022 $0.00958
Sonnet 5 $0.00009 $0.00383
Haiku 4.5 $0.00004 $0.00192

Measured 5d ago against content hash faef312c6293, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

local-integration-testing 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 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.

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/integration-testing/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Local Integration Testing — All Agents

Run end-to-end integration tests against the full CAIPE multi-agent stack in the local Docker Compose dev environment.

Prerequisites

  • Docker Desktop running with sufficient resources (16 GB+ RAM recommended for all 15 agents)
  • docker-compose.dev.yaml present in the repo root
  • .env file configured with required API keys and agent enable flags
  • MongoDB container (caipe-mongodb-dev) running

Instructions

Phase 1: Enable All Agents

  1. Edit .env — ensure all agent flags are enabled:

    ENABLE_ARGOCD=true
    ENABLE_AWS=true
    ENABLE_BACKSTAGE=true
    ENABLE_CONFLUENCE=true
    ENABLE_GITHUB=true
    ENABLE_GITLAB=true
    ENABLE_JIRA=true
    ENABLE_KOMODOR=true
    ENABLE_NETUTILS=true
    ENABLE_PAGERDUTY=true
    ENABLE_SLACK=true
    ENABLE_SPLUNK=true
    ENABLE_VICTOROPS=true
    ENABLE_WEATHER=true
    ENABLE_WEBEX=true
    
  2. Verify MongoDB checkpoint type:

    grep "^LANGGRAPH_CHECKPOINT_TYPE=" .env
    # Should output: LANGGRAPH_CHECKPOINT_TYPE=mongodb
    

Phase 2: Start the Stack

  1. Bring up all containers:

    IMAGE_TAG=latest docker compose -f docker-compose.dev.yaml up -d
    
  2. Wait for agents to be healthy (agents take 15-30 seconds to initialize):

    # Check all agent containers are running
    docker ps --filter "name=agent-" --format "table {{.Names}}\t{{.Status}}" | sort
    
  3. Restart supervisor after agents are warm (avoids race condition where supervisor starts before agents are ready):

    docker restart caipe-supervisor
    
  4. Verify supervisor discovered all agents:

    docker logs caipe-supervisor 2>&1 | grep -E "(ONLINE|subagents|tools)" | tail -5
    

    Expected: Deep agent updated with 15 tools and 15 subagents

Phase 3: Validate Per-Agent Checkpoint Isolation

Run the checkpoint validation script:

./skills/persistence/validate_agent_checkpoints.sh

This checks:

  • Each agent container is running
  • Auto-prefix log present (per-agent MongoDB collection names)
  • Collections exist with documents
  • No InMemorySaver fallback
  • No cross-contamination between agent collections

Read the full file on GitHub · 217 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. 5d ago First seen · 217 lines · 44 tokens per session scan A faef312c6293

Subscribe to this mod's changes

local-integration-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 44 tokens to every session and 1,917 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.