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/agentworkforce/relay/github-oauth-nango-integrationnpx skills add AgentWorkforce/relay --skill github-oauth-nango-integrationgit clone --depth 1 https://github.com/AgentWorkforce/relayWhat 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 | $0.00037 | $0.03193 |
| Opus 5 | $0.00018 | $0.01597 |
| Sonnet 5 | $0.00007 | $0.00639 |
| Haiku 4.5 | $0.00004 | $0.00319 |
Grade A, and why
github-oauth-nango-integration 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 2d 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 — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub OAuth + Nango Integration
Overview
Implements dual-connection OAuth pattern: one for user identity (github integration), another for repository access (github-app-oauth integration). This separation enables secure login while maintaining granular repo permissions through GitHub App installations.
When to Use
- Setting up GitHub OAuth login via Nango
- Implementing GitHub App installation webhooks
- Reconciling OAuth users with GitHub App installations
- Building apps that need both user auth and repo access
- Handling Nango sync webhooks for GitHub data
Why Two Connections?
GitHub has two different authentication mechanisms that serve different purposes:
GitHub OAuth App (github integration)
- What it is: Traditional OAuth for user identity
- What it gives you: User profile (name, email, avatar, GitHub ID)
- What it DOESN'T give you: Access to repositories
- Use for: Login, "Sign in with GitHub"
GitHub App (github-app-oauth integration)
- What it is: Installable app with granular repo permissions
- What it gives you: Access to specific repos the user installed it on
- What it DOESN'T give you: User identity (it knows the installation, not who's using it)
- Use for: Reading PRs, commits, files; posting comments; webhooks
The Reconciliation Problem
OAuth App alone: "User [email protected] logged in" → but which repos can they access?
GitHub App alone: "Installation #12345 has access to repo X" → but who is the user?
Solution: Two separate OAuth flows linked by user ID:
- Login flow → User authenticates → Store user identity +
nangoConnectionId - Repo flow → Same user authorizes app → Store repos + link via
ownerId
This lets you answer: "User [email protected] can access repos X, Y, Z"
Quick Reference
| Connection Type | Nango Integration | Purpose | Stored In |
|---|---|---|---|
| User Login | github |
Authentication, identity | users.nangoConnectionId |
| Repo Access | github-app-oauth |
PR operations, file access | repos.nangoConnectionId |
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.
- 2d ago First seen · 410 lines · 37 tokens per session scan A 837a2f02b54e
github-oauth-nango-integration is a skill published in the GitHub repository AgentWorkforce/relay (806 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 3,193 once invoked, about $0.0002 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
reskin
Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…
setup-slack-channel
Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…
copilotkit-channels
Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…
runtime
@copilotkit/runtime — mount a fetch-native CopilotRuntime on any JS server, wire middleware, pick an AgentRunner, instantiate BuiltInAgent (Factory Mode with TanStack AI is the preferred default) or plug in any of 12 external agent frameworks (Mastra, LangGraph, CrewAI Crews/Flows, PydanticAI, ADK, LlamaIndex, Agno…
copilotkit-integrations
Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.