universal-mcp-sync: Skill for Claude Code

.claude/skills/add-provider/SKILL.md

add-provider is a skill for Claude Code from nawodyaishan/universal-mcp-sync. It costs 70 tokens per session (656 once invoked), scanned A, original, MIT.

A guided procedure for adding a new provider to usync, a tool that connects to MCP servers. MCP servers are services that provide tools or data to an AI application.

In plain words
What is it for?
Use it when supporting a new MCP server, including checking its official configuration, handling API keys and environment variables, choosing its connection method, and registering authentication headers.
Why use it?
It reduces missed configuration details and inconsistent provider implementations by requiring documentation, scaffolding, registration, testing, and updates to contributor docs.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is nawodyaishan/universal-mcp-sync's own configuration. It tells Claude Code how to work on universal-mcp-sync 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 universal-mcp-sync configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nawodyaishan/universal-mcp-sync. 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/nawodyaishan/universal-mcp-sync/main/.claude/skills/add-provider/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nawodyaishan/universal-mcp-sync

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 add-provider

README.md
[![agentmods](https://agentmods.dev/badge/skills/nawodyaishan/universal-mcp-sync/add-provider/github.svg)](https://agentmods.dev/skills/nawodyaishan/universal-mcp-sync/add-provider)
Your own site
<a href="https://agentmods.dev/skills/nawodyaishan/universal-mcp-sync/add-provider"><img src="https://agentmods.dev/badge/skills/nawodyaishan/universal-mcp-sync/add-provider/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 add-provider

Your own site · 80×15
<a href="https://agentmods.dev/skills/nawodyaishan/universal-mcp-sync/add-provider"><img src="https://agentmods.dev/badge/skills/nawodyaishan/universal-mcp-sync/add-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 656 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 $0.00070 $0.00656
Opus 5 $0.00035 $0.00328
Sonnet 5 $0.00014 $0.00131
Haiku 4.5 $0.00007 $0.00066

Measured 11d ago against content hash 12aa189503bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

add-provider 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 11d 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/add-provider/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Provider Procedure

We follow a strict Spec-Driven Development (SDD) workflow. When requested to add a new MCP provider to usync, strictly follow these steps:

0. SDD Pre-requisite

Ensure an approved specification document exists (e.g., docs/specs/add-<name>-provider.md). If it doesn't exist or hasn't been approved, use the agentic-sdd-router or agentic-sdd-spec skill to create and refine the spec first. Do not proceed to implementation without a spec.

1. STOP and gather

Read the following files to understand the system context:

  • pkg/provider/types.go
  • pkg/provider/exa.go
  • pkg/provider/context7.go
  • docs/contributors/adding-a-provider.md
  • docs/specs/providers/add-context7-provider.md

2. Look up official docs

Use your search tools (or the Context7 MCP if available) to query the target server's configuration schema. Identify if it requires an API key, env vars, or specific arguments.

3. Decide capabilities

Use the decision tree from adding-a-provider.md:

  • Is it stdio or a remote transport?
  • Does it use URL query auth or Header auth?
  • Is it a single-key or multi-key setup?

4. Scaffold helpers

If necessary, create a package at pkg/<id>/ for validation logic (e.g., keys.go, keys_test.go). Reference: references/code-templates.md (Template 1).

5. Implement provider

Create pkg/provider/<id>.go implementing the MCPProvider interface. Reference: references/code-templates.md (Template 2).

6. Register

Register your new provider in DefaultRegistry() inside pkg/provider/registry.go.

7. Per-client adaptation

If the provider uses headers, verify if any client-specific adaptations are needed in pkg/client/adapter.go (e.g., HeadersFor).

8. QA scenarios

Write end-to-end scenarios in pkg/app/qa_scenarios_test.go confirming the config gets emitted accurately. Reference: references/code-templates.md (Template 3).

9. Docs

Add a row to the Provider Matrix in README.md. Update docs/contributors/adding-a-provider.md if the architectural approach expands.

Read the full file on GitHub · 60 lines

Files

What ships with it

3 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.

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. 11d ago First seen · 60 lines · 70 tokens per session scan A 12aa189503bf

Subscribe to this mod's changes

add-provider is a skill published in the GitHub repository nawodyaishan/universal-mcp-sync (6 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 656 once invoked, about $0.0003 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 2026-08-31.