Open Agents is an open-source reference application for running background coding agents through a web interface, durable workflows, isolated Vercel sandboxes, and GitHub integration. Developers fork and adapt it to let agents make code changes without keeping a local computer running. The catalogue entries provide skills, agents, and instructions for its workflow.
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 skills add vercel-labs/open-agents --skill deploy-open-harnessgit clone --depth 1 https://github.com/vercel-labs/open-agentsWrote 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.
[](https://agentmods.dev/skills/vercel-labs/open-agents/deploy-open-harness)<a href="https://agentmods.dev/skills/vercel-labs/open-agents/deploy-open-harness"><img src="https://agentmods.dev/badge/skills/vercel-labs/open-agents/deploy-open-harness.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 44 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.01629 |
| Opus 5 | $0.00030 | $0.00814 |
| Sonnet 5 | $0.00012 | $0.00326 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
deploy-open-harness 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 7d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.mdapps/web/.env.exampleapps/web/lib/db/client.tsapps/web/lib/jwe/encrypt.tsapps/web/lib/crypto.tsapps/web/app/api/auth/signin/vercel/route.tsapps/web/app/api/auth/vercel/callback/route.tsapps/web/app/api/github/app/install/route.tsapps/web/app/api/github/app/callback/route.tsapps/web/lib/github/app-auth.tsapps/web/lib/redis.tsapps/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
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.
- 7d ago First seen · 208 lines · 60 tokens per session scan A 0f010ea4c3bb
deploy-open-harness is a skill published in the GitHub repository vercel-labs/open-agents (5,805 stars, last pushed 9d ago), licensed MIT. It adds 60 tokens to every session and 1,629 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.
Other skills, from other repositories
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".
capawesome-cloud
Guides the agent through setting up and using Capawesome Cloud for Capacitor and Cordova apps. Covers three core workflows: (1) Native Builds — cloud builds for iOS and Android (Capacitor, Cordova, or native projects), signing certificates, environments, Trapeze configuration, and build artifacts; (2) Live Updates …
huggingface-jobs
Plan, launch, inspect, monitor, and cancel authenticated Hugging Face Jobs for CPU, GPU, TPU, batch, inference, and data workloads.
cloudflare-temporary-deploy
Deploy a temporary Cloudflare Workers preview with Wrangler for short-lived web app smoke tests.
vigilante-issue-implementation-on-terraform
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Terraform repository with fmt, validate, and secret-safe infrastructure guidance.
aws-cost-optimizer
Analyze and optimize AWS costs with recommendations for Reserved Instances, right-sizing, and resource cleanup. Use when reducing AWS spending, analyzing costs, or optimizing cloud infrastructure expenses.