Borrowing it
Nothing to install: this file belongs to AlphaBitCore/nexus-gateway. 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/AlphaBitCore/nexus-gateway/main/.claude/skills/test-openai-responses/SKILL.mdgit clone --depth 1 https://github.com/AlphaBitCore/nexus-gatewayWrote 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/alphabitcore/nexus-gateway/test-openai-responses)<a href="https://agentmods.dev/skills/alphabitcore/nexus-gateway/test-openai-responses"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/test-openai-responses/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/alphabitcore/nexus-gateway/test-openai-responses"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/test-openai-responses.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 57 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00179 | $0.01733 |
| Opus 5 | $0.00089 | $0.00866 |
| Sonnet 5 | $0.00036 | $0.00347 |
| Haiku 4.5 | $0.00018 | $0.00173 |
Grade A, and why
test-openai-responses 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 10d 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 -fsS http://localhost:3050/healthz # ai-gateway How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test OpenAI Responses API ingress
Synthetic end-to-end test for the POST /v1/responses ingress added in
E56. Mirrors the pattern of /test-cursor-adapter and
/test-geminiweb-adapter: hand-roll a request body, send it through
the live local AI Gateway, then cross-check the resulting traffic_event
row in Postgres.
When to use
- After editing anything under
packages/ai-gateway/internal/providers/spec_openai/codec_responses*.goorstream_responses.go. - After modifying the Responses bridge wiring in
canonicalbridge/bridge.goorstream_encoders_responses.go. - After the gateway is rebuilt / restarted and you want to confirm
/v1/responsesis mounted and routable. - As a smoke gate before merging any E56 follow-up PR.
- As the regression suite for the OpenAI Responses-API surface — the broader smoke (
/smoke-gateway) only hits--responsesopt-in arm.
Prerequisites
Local stack must be healthy:
curl -fsS http://localhost:3050/healthz # ai-gateway
curl -fsS http://localhost:3001/ready # control-plane
docker ps --filter "name=postgres" -q # postgres container
A virtual key with at least one routing rule pointing at an OpenAI provider with a model in the Responses-supported list (gpt-5.x / gpt-4o family / o-series). Either:
- Use the project's standing local test VK (recorded in memory:
[Local test VK](project_local_test_vk.md)) and re-use it. - Mint a fresh VK via prod-login + research-all-models — only if a fresh key is needed for the run.
The Responses-supported model the skill exercises by default is gpt-5.2; override with --model.
How to run
# Default — uses tests/.env.local for credentials and the standing local VK.
.claude/skills/test-openai-responses/run.sh
# Or explicitly:
.claude/skills/test-openai-responses/run.sh \
--vk nvk_... \
--model gpt-5.2 \
--gw-url http://localhost:3050
Output: a Markdown report at /tmp/test-openai-responses-<UTC-timestamp>.md.
Test arms
What ships with it
2 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.
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.
- 10d ago First seen · 153 lines · 179 tokens per session scan A 34425ab14b27
test-openai-responses is a skill published in the GitHub repository AlphaBitCore/nexus-gateway (23 stars, last pushed 8d ago), licensed Apache-2.0. It adds 179 tokens to every session and 1,733 once invoked, about $0.0009 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
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…
verify
Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches…
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.