nexus-gateway: Skill for Claude Code

.claude/skills/test-cursor-adapter/SKILL.md

test-cursor-adapter is a skill for Claude Code from AlphaBitCore/nexus-gateway. It costs 196 tokens per session (1,837 once invoked), scanned A, original, Apache-2.0.

A synthetic test for checking the Nexus adapter that decodes Cursor IDE chat requests encoded with Protocol Buffers, a compact data format used for structured messages. It sends a made-up request through the compliance proxy and checks the recorded audit result.

In plain words
What is it for?
Use it after changing Cursor adapter or shared normalization code, redeploying related services, or when you need an audit row to inspect in the Control Plane UI.
Why use it?
It tests the Cursor traffic path without waiting for real Cursor IDE traffic. This helps reveal broken decoding, proxy wiring, or normalization changes after code edits or redeployments.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Cursor.

This is AlphaBitCore/nexus-gateway's own configuration. It tells Claude Code how to work on nexus-gateway itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nexus-gateway configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 tests/manual/cursor_synthetic_chat.py.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/AlphaBitCore/nexus-gateway/main/.claude/skills/test-cursor-adapter/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AlphaBitCore/nexus-gateway

Made for: Claude Code.

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 test-cursor-adapter

README.md
[![agentmods](https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/test-cursor-adapter.svg)](https://agentmods.dev/skills/alphabitcore/nexus-gateway/test-cursor-adapter)
Your own site
<a href="https://agentmods.dev/skills/alphabitcore/nexus-gateway/test-cursor-adapter"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/test-cursor-adapter.svg" alt="Measured on agentmods" height="20"></a>
Per session 196 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,837 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00196 $0.01837
Opus 5 $0.00098 $0.00919
Sonnet 5 $0.00039 $0.00367
Haiku 4.5 $0.00020 $0.00184

Measured 7d ago against content hash 569fdb93cd08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

test-cursor-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 7d 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/test-cursor-adapter/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Cursor Adapter

Synthetic protobuf round-trip for the Cursor IDE Tier-1 normalizer.

When to use

  • After editing packages/shared/traffic/adapters/ide/cursor/normalize.go, cursor.go, or any of the protobuf wire schema docs.
  • After redeploying Hub / compliance-proxy / ai-gateway to confirm the Tier-1 cursor.Normalize is wired and the protobuf decode survived.
  • Whenever the user wants to see the cursor-shape audit row in the Control Plane UI but doesn't have live Cursor IDE traffic to drive.
  • As a regression probe after any change to shared/normalize/extract/ (the cursor adapter falls through to pattern probe + verbatim if Tier 1 returns ErrUnsupported, so a framework change shouldn't quietly drop confidence).

How to run

python3 tests/manual/cursor_synthetic_chat.py

Flags:

Flag Default Notes
--proxy the deployment's compliance proxy on :3128 Override for a different proxy. Local dev: --proxy localhost:3128.
--target https://api2.cursor.sh/aiserver.v1.AiService/StreamUnifiedChatWithTools The path doesn't have to exist upstream — Cursor's server returns 404 but the proxy still MITMs + audits.
--secure (off — defaults to TLS verify disabled) The Nexus MITM cert is signed by our internal CA; certifi's bundle doesn't include it even when system trust does. Pass --secure only if you've added the Nexus root CA to Python's bundle.
--model claude-sonnet-4-6 Embedded in the synthetic ModelDetails sub-message; appears in the normalized payload's model field.

The script:

  1. Hand-encodes a GetChatRequest protobuf (field 2 = repeated ConversationMessage with field 1 = text + field 2 = role enum; field 7 = ModelDetails with field 1 = model_name). No third-party protobuf library — uses stdlib varint + tag encoding.
  2. POSTs through the HTTPS proxy with Content-Type: application/connect+proto and a fake Authorization: Bearer … token. Upstream Cursor returns 401/403/404 (expected — we have no real auth), but the proxy still bumps + audits the bumped body.
  3. Prints the trace id and a checklist for verifying the resulting row in the Control Plane UI.

Read the full file on GitHub · 147 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. 7d ago First seen · 147 lines · 196 tokens per session scan A 569fdb93cd08

Subscribe to this mod's changes

test-cursor-adapter is a skill published in the GitHub repository AlphaBitCore/nexus-gateway (23 stars, last pushed 5d ago), licensed Apache-2.0. It adds 196 tokens to every session and 1,837 once invoked, about $0.0010 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.

Related

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…

RockyHong/super-bootstrap · 79 tokens

tdd-workflow

Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

affaan-m/ECC · 43 tokens

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.

diegosouzapw/OmniRoute · 34 tokens

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.

wshobson/agents · 39 tokens

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.

davila7/claude-code-templates · 34 tokens

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.

wshobson/agents · 51 tokens