neurolink: Skill for Claude Code

.claude/skills/adding-tests/SKILL.md

adding-tests is a skill for Claude Code from juspay/neurolink. It costs 85 tokens per session (4,759 once invoked), scanned A, original, MIT.

A guide for adding tests to an existing TypeScript test suite when introducing an AI provider, a model capability such as vision or speech, or an SDK feature. It explains which test file and shared helpers to use.

In plain words
What is it for?
Use it when extending tests for providers, vision, embeddings, text-to-speech, speech-to-text, realtime, image, or video features.
Why use it?
It prevents new tests from using the wrong harness, confusing skipped tests with failures, or missing required capability settings.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; positional $N argument.

This is juspay/neurolink's own configuration. It tells Claude Code how to work on neurolink 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 neurolink configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { NeuroLink } from "../dist/index.js";.

Reuse

Borrowing it

Nothing to install: this file belongs to juspay/neurolink. 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/juspay/neurolink/release/.claude/skills/adding-tests/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/juspay/neurolink

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 adding-tests

README.md
[![agentmods](https://agentmods.dev/badge/skills/juspay/neurolink/adding-tests/github.svg)](https://agentmods.dev/skills/juspay/neurolink/adding-tests)
Your own site
<a href="https://agentmods.dev/skills/juspay/neurolink/adding-tests"><img src="https://agentmods.dev/badge/skills/juspay/neurolink/adding-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.

agentmods 80×15 button for adding-tests

Your own site · 80×15
<a href="https://agentmods.dev/skills/juspay/neurolink/adding-tests"><img src="https://agentmods.dev/badge/skills/juspay/neurolink/adding-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,759 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 $0.00085 $0.04759
Opus 5.5 $0.00034 $0.01904
Sonnet 5.5 $0.00017 $0.00952
Haiku 4.5 $0.00009 $0.00476

Measured 4d ago against content hash 39bd3b4c5166, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adding-tests 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 4d 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/adding-tests/SKILL.md · 451 lines

How it starts

The opening of the file, as written. The whole thing — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal: extend test/continuous-test-suite-*.ts without re-inventing harness code, without breaking the canonical patterns the May 2026 consolidation locked in, and without creating SKIP/FAIL confusion in CI.


0. Mental model in one paragraph

Tests are plain tsx scripts — no Jest/Vitest. Every suite is a single test/continuous-test-suite-<domain>.ts file invoked via pnpm exec tsx <path> or pnpm run test:<domain>. All shared logic lives in test/helpers/*.ts. The harness defines a tri-state result:

  • PASS — test fn returns/resolves normally
  • FAIL — test fn throws an Error that doesn't look like a skip
  • SKIP — test fn throws new Skip(reason), OR a known provider error (isExpectedProviderError), OR an env-missing string starting with "SKIP:"

You never write a new suite directory, never add a runner config, never introduce a new logger. You add code to an existing per-domain file OR write one new file with the same canonical shape.


1. Decision tree — where does my test go?

What are you adding?
│
├── New AI provider (e.g. "Together AI", "Cerebras")
│   → Edit test/helpers/providerMatrix.ts (add PROVIDERS entry)
│   → Edit test/continuous-test-suite-new-providers.ts (live smoke)
│   → pnpm run test:matrix picks it up automatically
│
├── New modality on an existing provider
│   ├── vision input          → test/continuous-test-suite-providers.ts
│   │                            (+ flip `vision: true` in providerMatrix)
│   ├── image generation      → test/continuous-test-suite-media-gen.ts
│   ├── video generation      → test/continuous-test-suite-media-gen.ts
│   ├── TTS                   → test/continuous-test-suite-tts.ts
│   ├── STT / realtime / voice→ test/continuous-test-suite-voice.ts
│   ├── embeddings            → test/continuous-test-suite-provider-matrix.ts
│   │                            (auto-discovered when `embeddings: true`)
│   └── thinking / reasoning  → test/continuous-test-suite-providers.ts
│
├── New file processor (e.g. .heic, .protobuf, .xlsx variant)
│   → test/continuous-test-suite-context.ts
│
├── New SDK feature
│   ├── tool / MCP            → test/continuous-test-suite-mcp-sdk.ts
│   ├── tool reliability      → test/continuous-test-suite-tool-reliability.ts
│   ├── memory / sessions     → test/continuous-test-suite-memory.ts
│   ├── RAG / chunking        → test/continuous-test-suite-rag.ts
│   ├── workflow              → test/continuous-test-suite-workflow.ts
│   ├── observability / OTEL  → test/continuous-test-suite-observability.ts
│   ├── HITL                  → test/continuous-test-suite-hitl.ts
│   ├── credentials surface   → test/continuous-test-suite-credentials.ts
│   ├── proxy / fallback      → test/continuous-test-suite-proxy.ts
│   ├── server (HTTP)         → test/continuous-test-suite-servers.ts
│   ├── evaluation / RAGAS    → test/continuous-test-suite-evaluation.ts
│   ├── autoresearch          → test/continuous-test-suite-autoresearch.ts
│   ├── middleware            → test/continuous-test-suite-middleware.ts
│   └── client SDK surface    → test/continuous-test-suite-client.ts
│
└── A whole new domain that doesn't fit above?
    → Create test/continuous-test-suite-<name>.ts (use § 2 template),
      add `test:<name>` script to package.json, add to test/README.md § 3.

Read the full file on GitHub · 451 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. 4d ago First seen · 451 lines · 85 tokens per session scan A 39bd3b4c5166

Subscribe to this mod's changes

adding-tests is a skill published in the GitHub repository juspay/neurolink (168 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 4,759 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-02.

Related

adding-tests compared with skills from other repositories

adding-tests next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
adding-testsjuspay/neurolinkSkill168yesterdayMITA85Claude Code
tautullijmagar/claude-homelabSkill871mo agoMITA74Claude Code
notebooklmjmagar/claude-homelabSkill871mo agoMITA67Claude Code
gh-address-commentsjmagar/claude-homelabSkill871mo agoMITA85Claude Code, Codex
linkdingjmagar/claude-homelabSkill871mo agoMITA69Claude Code
plexjmagar/claude-homelabSkill871mo agoMITA76Claude Code
prowlarrjmagar/claude-homelabSkill871mo agoMITA68Claude Code