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-geminiweb-adapter/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-geminiweb-adapter)<a href="https://agentmods.dev/skills/alphabitcore/nexus-gateway/test-geminiweb-adapter"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/test-geminiweb-adapter/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-geminiweb-adapter"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/test-geminiweb-adapter.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 | $0.00237 | $0.01209 |
| Opus 5 | $0.00118 | $0.00605 |
| Sonnet 5 | $0.00047 | $0.00242 |
| Haiku 4.5 | $0.00024 | $0.00121 |
Grade A, and why
test-geminiweb-adapter 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 9d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Gemini Web Adapter
Synthetic batchexecute round-trip for the Gemini Web Tier-1 normalizer.
Companion to test-cursor-adapter (cursor protobuf synthetic).
When to use
- After editing
packages/shared/traffic/adapters/web/geminiweb/normalize.goorpackages/shared/transport/normalize/extract/detector.go::BatchExecuteDetector. - After redeploying Hub / CP / compliance-proxy to confirm gemini-web Tier 1 is wired.
- When you want a Gemini-web-shaped audit row without driving real gemini.google.com traffic.
How to run
python3 tests/manual/geminiweb_synthetic_chat.py
Flags: --proxy (default: the deployment's compliance proxy on :3128), --target
(default StreamGenerate URL), --prompt, --locale, --secure
(default insecure — Nexus CA may not be in certifi).
Verification (after the script prints its trace id)
A. Control Plane UI
the Control Plane Traffic page (https://cp.<your-domain>/traffic) → filter
target_host=gemini.google.com:443. Open the row. Expected:
- Tier-1 badge (green):
Tier 1 · gemini-web · 0.85 - Kind:
ai-chat - 1 user Message with the
--prompttext - Model: empty on request side (carried in response chunks only)
B. DB cross-check
ssh -o StrictHostKeyChecking=no ${NEXUS_SSH_HOST} "
PGPASSWORD=$NEXUS_SSH_PGPASSWORD psql -h localhost -U $NEXUS_SSH_PGUSER -d $NEXUS_SSH_PGDB -c \
\"SELECT ten.request_normalized->>'kind' AS kind,
ten.request_normalized->>'detectedSpec' AS spec,
ten.request_normalized->>'confidence' AS conf,
ten.request_normalized->'messages'->0->'content'->0->>'text' AS prompt
FROM traffic_event te JOIN traffic_event_normalized ten ON ten.traffic_event_id = te.id
WHERE te.target_host LIKE '%gemini.google.com%' AND te.timestamp > now() - interval '5 minutes'
ORDER BY te.timestamp DESC LIMIT 5;\"
"
Expected: kind=ai-chat, spec=gemini-web, conf≈0.85,
prompt matches --prompt flag.
Failure modes
| Symptom | Cause |
|---|---|
| No new row | Source IP not in allowlist, or gemini.google.com removed from interception_domain |
kind=http-text |
Tier-1 wiring missing — verify adapters.RegisterTier1AdapterNormalizers runs in binary main |
spec=pattern:google-batchexecute-chat (amber) |
Tier-1 returned ErrUnsupported; Tier-2 detector caught it instead. Still works; investigate adapter route |
msg_count=0 |
Google changed f.req inner index — update BatchExecuteDetector.decodeRequest |
kind=http-binary |
Body byte-sniff failed both f.req= and )]}' — different endpoint? compressed? |
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.
- 9d ago First seen · 103 lines · 237 tokens per session scan A f23c7c18dda4
test-geminiweb-adapter is a skill published in the GitHub repository AlphaBitCore/nexus-gateway (23 stars, last pushed 7d ago), licensed Apache-2.0. It adds 237 tokens to every session and 1,209 once invoked, about $0.0012 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
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…
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.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.