Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ashish7802/awesome-api-skills/neonnpx skills add ashish7802/awesome-api-skills --skill neongit clone --depth 1 https://github.com/ashish7802/awesome-api-skillsWhat 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 | $0.00000 | $0.00654 |
| Opus 5 | $0.00000 | $0.00327 |
| Sonnet 5 | $0.00000 | $0.00131 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
neon 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 yesterday.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neon API Skill
Quick Start
Neon separates compute and storage, allowing instant database branching and autoscaling. For most Node.js applications, use the @neondatabase/serverless driver over standard pg to leverage WebSocket connections, which bypass serverless environment connection limits.
npm install @neondatabase/serverless
Common Workflows
Instant Branching
Neon allows you to create isolated database branches for preview environments. In Vercel or GitHub Actions, trigger the Neon API to branch your primary DB instantly before running integration tests, then delete the branch upon PR merge.
Production Patterns
Connection Pooling vs WebSockets
In traditional long-running servers (like Express on EC2), standard connection pooling with pg is acceptable. In Edge environments (Cloudflare Workers, Vercel Edge), always utilize the Neon WebSocket driver to eliminate connection exhaustion.
Error Recovery
Handle standard PostgreSQL error codes (e.g., 23505 for Unique Violation). If encountering connection timeouts (ETIMEDOUT) during cold starts in serverless functions, implement a retry wrapper using an exponential backoff strategy (e.g., async-retry package).
Security Notes
Never expose your raw Neon connection string in client-facing applications. Restrict database access by explicitly binding to static IP ranges where possible, though serverless environments may require 0.0.0.0/0 with strict password enforcement.
Performance Considerations
Neon's compute scales down to zero when inactive. The first query after scale-to-zero will experience a 'cold start' latency (typically 500ms-1s). To mitigate this for user-facing routes, implement keep-alive cron jobs or utilize read replicas for globally distributed edge applications.
Testing Guidance
Do not mock the database. Instead, integrate Neon API calls into your test setup phase to instantly provision an exact clone of your production schema, run tests against it, and destroy the branch in the teardown phase.
What ships with it
7 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.
- yesterday First seen · 59 lines · 0 tokens per session scan A f07ecc52c497
neon is a skill published in the GitHub repository ashish7802/awesome-api-skills (13 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 654 tokens. 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
create-canvas-extension
Create or register a canvas extension in the awesome-copilot repository. Use when asked to scaffold a new canvas extension, create its plugin.json, add a reusable extension to one or more plugins, or migrate extension metadata. Extensions are reusable source under extensions/; shippable plugin manifests belong under…
presentation
Turn a tech-spec directory into an interactive, marketing-grade web presentation — built so engineers understand the design, the reader is convinced of the why, and the result is shareable in public. Use when someone wants a spec turned into a deck.
iii-core-primitives
Use when registering iii functions, binding triggers, selecting sync/void/enqueue invocation, creating workers, inspecting the live worker registry, installing registry workers, authoring custom triggers, moving channel data, or adapting external HTTP functions across TypeScript, Python, and Rust.
iii-sandbox
Ephemeral microVM sandboxes for running untrusted or agent-generated code in isolation — a one-call run path, a create/exec/stop lifecycle, and a set of filesystem operations.
iii-architecture-patterns
Use when composing iii primitives into backend architectures: durable workflows, reactive backends, agentic pipelines, event-driven CQRS, effect pipelines, and trigger-transform-action automation.
iii-error-handling
Handle iii engine and SDK errors across Node, Python, Rust, and browser workers. Use when interpreting error codes, retryability, RBAC denial, timeouts, handler failures, or SDK-specific exception surfaces.