mcpbeat Sign in

Deploy Open Harness Agent Skill

Guides a user through collecting the credentials needed to deploy their own copy of Open Harness, deploying this repo on Vercel, and completing first-run setup. Use for requests about deploying, self-hosting, configuring credentials, or getting started with a fork of this app.

2k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
5770
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/vercel-labs/open-agents --skill deploy-open-harness

The instruction itself

21 sections, as written by the author

You are helping a user deploy their own copy of Open Harness.

Base your guidance on the current codebase, not on older Harness-era setup assumptions.

First rule: verify current requirements from the repo

Before giving deployment advice, read these files if you have not already:

  • README.md
  • apps/web/.env.example
  • apps/web/lib/db/client.ts
  • apps/web/lib/jwe/encrypt.ts
  • apps/web/lib/crypto.ts
  • apps/web/app/api/auth/signin/vercel/route.ts
  • apps/web/app/api/auth/vercel/callback/route.ts
  • apps/web/app/api/github/app/install/route.ts
  • apps/web/app/api/github/app/callback/route.ts
  • apps/web/lib/github/app-auth.ts
  • apps/web/lib/redis.ts
  • apps/web/lib/sandbox/config.ts

If the code and the docs disagree, trust the code and say so.

Do not rely on scripts/setup.sh.

Goals

Help the user:

  • Decide whether they want a minimal deploy or the full GitHub-enabled coding-agent flow.
  • Collect only the credentials actually required for that scope.
  • Understand where to obtain each credential.
  • Deploy this repo on Vercel.
  • Complete first-run verification.
  • Leave with a short next-steps checklist.

Safety rules

  • Never ask the user to paste secrets into chat.
  • Tell them where each value belongs, but keep secret values in Vercel project env vars or local env files.
  • Separate blockers for a minimal deploy from blockers for the full GitHub-enabled flow.
  • Be explicit when something is optional.

Scope the deployment first

Start by determining which path the user wants:

1) Minimal deploy

A working hosted app where the user can deploy it, sign in with Vercel, and use the product without GitHub repo access.

2) Full deploy

Everything in the minimal deploy, plus GitHub account linking, GitHub App installation, private repo access, pushes, and PR creation.

If the user is unsure, recommend minimal deploy first, then layer on GitHub.

Credential checklist

Use this checklist when guiding the user.

Required for the app to run

  • POSTGRES_URL
  • JWE_SECRET

Required for a usable hosted deployment

  • ENCRYPTION_KEY
  • NEXT_PUBLIC_VERCEL_APP_CLIENT_ID
  • VERCEL_APP_CLIENT_SECRET

Required for GitHub-enabled repo flows

  • NEXT_PUBLIC_GITHUB_CLIENT_ID
  • GITHUB_CLIENT_SECRET
  • GITHUB_APP_ID
  • GITHUB_APP_PRIVATE_KEY
  • NEXT_PUBLIC_GITHUB_APP_SLUG
  • GITHUB_WEBHOOK_SECRET

Optional

  • REDIS_URL or KV_URL
  • VERCEL_PROJECT_PRODUCTION_URL
  • NEXT_PUBLIC_VERCEL_PROJECT_PRODUCTION_URL
  • VERCEL_SANDBOX_BASE_SNAPSHOT_ID
  • ELEVENLABS_API_KEY

How to explain each credential

PostgreSQL

Tell the user to create a Postgres database and copy the connection string into POSTGRES_URL.

JWE secret

Explain that this is required for session encryption.

Recommended generation command:

openssl rand -base64 32 | tr '+/' '-_' | tr -d '=\n'

Encryption key

Explain that provider tokens are encrypted at rest and the value must be a 64-character hex string.

Recommended generation command:

openssl rand -hex 32

Vercel OAuth app

Tell the user to create a Vercel OAuth app and set:

  • Callback URL: https://YOUR_DOMAIN/api/auth/vercel/callback
  • For local dev: http://localhost:3000/api/auth/vercel/callback

Store the credentials as:

  • NEXT_PUBLIC_VERCEL_APP_CLIENT_ID
  • VERCEL_APP_CLIENT_SECRET

GitHub App

Tell the user they do not need a separate GitHub OAuth app. Open Harness uses the GitHub App's user authorization flow.

Tell the user to create a GitHub App and set:

  • Homepage URL: https://YOUR_DOMAIN
  • Callback URL: https://YOUR_DOMAIN/api/github/app/callback
  • Setup URL: https://YOUR_DOMAIN/api/github/app/callback
  • For local dev: homepage http://localhost:3000, callback/setup http://localhost:3000/api/github/app/callback

Also tell them to:

  • enable "Request user authorization (OAuth) during installation"
  • use the GitHub App Client ID and Client Secret for NEXT_PUBLIC_GITHUB_CLIENT_ID and GITHUB_CLIENT_SECRET
  • make the app public if they want org installs to work cleanly
  • generate a webhook secret
  • download/generate the private key

Store the values as:

  • NEXT_PUBLIC_GITHUB_CLIENT_ID
  • GITHUB_CLIENT_SECRET
  • GITHUB_APP_ID
  • GITHUB_APP_PRIVATE_KEY
  • NEXT_PUBLIC_GITHUB_APP_SLUG
  • GITHUB_WEBHOOK_SECRET

Mention that GITHUB_APP_PRIVATE_KEY can be stored either as PEM contents with escaped newlines or as a base64-encoded PEM.

Redis / KV

Explain that Redis is optional. It improves resumable streams, stop signaling, and caching, but it is not required for the first deploy.

Deployment flow

Guide the user through this sequence:

  • Fork the repo.
  • Import it into Vercel at the repo root.
  • Add the baseline env vars:
  • POSTGRES_URL
  • JWE_SECRET
  • ENCRYPTION_KEY
  • Deploy once to get a stable production URL.
  • Create the Vercel OAuth app using that production URL.
  • Add NEXT_PUBLIC_VERCEL_APP_CLIENT_ID and VERCEL_APP_CLIENT_SECRET.
  • Redeploy.
  • If the user wants the full GitHub flow, create the GitHub App using the production URL, add the GitHub env vars, and redeploy again.
  • Optionally add Redis/KV and the production URL vars.

If the user already has a custom domain ready, it is fine to use that domain from the start instead of the default vercel.app production URL.

First-run verification

For a minimal deploy, walk the user through:

  • Open the production site.
  • Sign in with Vercel.
  • Confirm they land in the app successfully.
  • Create a session and confirm the basic UI loads.

For the full deploy, also verify:

  • GitHub account linking works.
  • GitHub App installation completes.
  • Installations or repos appear in the UI.
  • A repo-backed session can start.
  • The sandbox starts and the agent can work in the repo.

If something fails, identify the missing credential or callback mismatch instead of giving generic advice.

Response format

When helping a user, prefer this structure:

  • Target scope — minimal or full.
  • Credential checklist — grouped into required now vs optional later.
  • How to get each missing credential — short, concrete instructions.
  • Deploy steps — only the next actions the user should take.
  • Verification — what to click/test after deploy.
  • Next upgrades — Redis, GitHub, voice, custom domain, snapshot override, only if relevant.

Be concise. Keep the user moving toward the next unblocker.

Other skills for the same job

different authors, same section of the catalogue
Azure Kubernetes Automatic Readiness
by microsoft
vendor ×3

Assess Kubernetes workloads and cluster configuration for AKS Automatic compatibility. Identifies incompatibilities, generates fixes, and guides migration from AKS Standard to AKS Automatic. WHEN: migrate to AKS Automatic, check AKS Automatic readiness, validate manifests for Automatic, assess cluster for Automatic compatibility, fix deployment for Automatic compatibility, identify AKS Automatic migration blockers, is my cluster ready for AKS Automatic.

13k tokens
Capacity
by microsoft
vendor ×3

Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.

6k tokens scripts
Customize
by microsoft
vendor ×3

Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).

8k tokens
Deploy Model
by microsoft
vendor ×3

Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).

26k tokens scripts
Preset
by microsoft
vendor ×3

Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (use customize), PTU deployments (use customize).

9k tokens
Lamindb
by christophacham
×3

This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.

22k tokens
Latchbio Integration
by christophacham
×3

Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.

12k tokens
Modal
by christophacham
×3

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

17k tokens

How to use it

Copy the folder

Take vercel-labs/deploy-open-harness from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.