Borrowing it
Nothing to install: this file belongs to HexamindOrganisation/hexgate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HexamindOrganisation/hexgate/main/.claude/skills/integration-tests/SKILL.mdgit clone --depth 1 https://github.com/HexamindOrganisation/hexgateWrote 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/hexamindorganisation/hexgate/integration-tests)<a href="https://agentmods.dev/skills/hexamindorganisation/hexgate/integration-tests"><img src="https://agentmods.dev/badge/skills/hexamindorganisation/hexgate/integration-tests/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hexamindorganisation/hexgate/integration-tests"><img src="https://agentmods.dev/badge/skills/hexamindorganisation/hexgate/integration-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00000 | $0.00705 |
| Opus 5.5 | $0.00000 | $0.00282 |
| Sonnet 5.5 | $0.00000 | $0.00141 |
| Haiku 4.5 | $0.00000 | $0.00071 |
Grade A, and why
integration-tests scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf http://localhost:8000/health # platform-api already up? How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Integration Tests
The local stack below is the same one docs/internals/development.md ("Run the
platform locally") documents for developers; keep the two in sync.
Before starting anything, run "$(git rev-parse --show-toplevel)/.claude/skills/run-platform/preflight.sh" --full.
It reports a missing or stopped Docker, a missing Go, and busy ports up front.
To bring the servers up, you can follow the run-platform skill in full mode instead of the
three terminals below. Minting the key and running pytest stay here.
SDK integration tests (repo root — tests/adapters/*/test_integration.py, tests/audit/test_integration.py)
Infra (idempotent):
make postgres-init
make clickhouse-up
make redpanda-topics
Mint a key — prints fty_live_… on stdout, and creates the keypair the Collector needs:
cd platform/api && DATABASE_URL=postgresql+asyncpg://hexgate:hexgate-dev-password@localhost:5433/hexgate \
PYTHONPATH=$PWD uv run python ../../deploy/provision.py
Three blocking servers, one terminal each. Check first — they bind fixed ports and die with "Address already in use":
curl -sf http://localhost:8000/health # platform-api already up?
curl -s -o /dev/null localhost:4318 && echo up # collector already up? (any HTTP answer, even 404)
make platform-api-pg # :8000 — must be -pg, never `make platform-api`
make collector-run # :4317 / :4318
make enricher-run
Run:
export HEXGATE_API_KEY=<the fty_live_… from above>
export HEXGATE_API_URL=http://localhost:8000
pytest -m integration # expect 5 passed, ~20s
Unset afterward — some unit tests require no API key:
unset HEXGATE_API_KEY HEXGATE_API_URL HEXGATE_OTLP_ENDPOINT \
LANGFUSE_PUBLIC_KEY LANGFUSE_SECRET_KEY LANGFUSE_HOST
On row never landed in ClickHouse, read the export error in the captured log, then:
curl -s "http://localhost:8124/?query=SELECT+count()+FROM+hexgate_audit.policy_decision" \
-u hexgate:hexgate-dev-password
# DLQ: want HIGH-WATERMARK 0 on every partition
docker exec hexgate-redpanda rpk topic describe hexgate.otlp.dlq -p --brokers localhost:9092
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.
- 1mo ago Changed · +5 lines b6455c6bdbe4
- 1mo ago Changed · +3 lines cc887782caa4
- 1mo ago Changed · +25 lines · -68 tokens per session 757e8a866851
- 2mo ago First seen · 34 lines · 68 tokens per session scan A 5939a0efbcd7
integration-tests is a skill published in the GitHub repository HexamindOrganisation/hexgate (23 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 705 tokens. 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
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, or before committing or creating PRs.
developing-openrig
Use when changing OpenRig's own source in a clone of the openrig repository: finding which package or file owns a behaviour, choosing which tests to run, testing a change without disturbing the OpenRig daemon your own session runs on, judging whether a diff touches a high-risk area, or preparing a pull request. Not…
testing-and-ci
Choose and run unit, E2E, Caddyfile fixture, automation, and CI checks for caddy-security. Use for coverage requirements, test evidence, failures, and report workflows; official OP conformance remains opt-in.
finishing-a-branch
Wrap up finished code work safely: confirm the tests pass, then let the Commander choose to merge it, open a pull request, or keep it for later. Nothing is deleted or overwritten without the Commander's clear go-ahead.