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/integration-testingnpx skills add caipe-io/ai-platform-engineering --skill integration-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/integration-testing)<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>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 | $0.00044 | $0.01917 |
| Opus 5 | $0.00022 | $0.00958 |
| Sonnet 5 | $0.00009 | $0.00383 |
| Haiku 4.5 | $0.00004 | $0.00192 |
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.
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.yamlpresent in the repo root.envfile configured with required API keys and agent enable flags- MongoDB container (
caipe-mongodb-dev) running
Instructions
Phase 1: Enable All Agents
-
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 -
Verify MongoDB checkpoint type:
grep "^LANGGRAPH_CHECKPOINT_TYPE=" .env # Should output: LANGGRAPH_CHECKPOINT_TYPE=mongodb
Phase 2: Start the Stack
-
Bring up all containers:
IMAGE_TAG=latest docker compose -f docker-compose.dev.yaml up -d -
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 -
Restart supervisor after agents are warm (avoids race condition where supervisor starts before agents are ready):
docker restart caipe-supervisor -
Verify supervisor discovered all agents:
docker logs caipe-supervisor 2>&1 | grep -E "(ONLINE|subagents|tools)" | tail -5Expected:
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
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 · 217 lines · 44 tokens per session scan A faef312c6293
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.
Other skills, from other repositories
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…
product-test
Use this skill to define the observable behavior that must be true for a story or feature to be considered done. It turns product context into concise, testable Given/When/Then scenarios that engineers and QA can verify without guessing intent.
test-automation
Execute Vitest and Playwright test suites with result collection and failure analysis.
qa-testing
Generate and execute API and E2E tests with quality gate assessment.
run-dashboard-e2e-local-changes
Run Playwright E2E (tests/e2e/) against the docker/ all-in-one harness so it reflects LOCAL code changes, not a stale cached image.
voyager
Authoring web and native E2E tests, including Playwright, Appium, XCUITest, device farms, visual regression, and App Store screenshot pipelines. Not for unit/load tests.