← Back to Skills Marketplace
jpbonch

AgentScale

by João Bonchristiano · GitHub ↗ · v0.1.2
cross-platform ⚠ suspicious
784
Downloads
0
Stars
2
Active Installs
3
Versions
Install in OpenClaw
/install agentscale
Description
Deploy web apps and APIs to a public URL with a single command.
README (SKILL.md)

Free Tier

  • No signup or payment required to start.
  • Run npx agentscale register to get an API key.
  • Free deploys expire after 1 hour.
  • Limited to 1 service.

Paid Tier

  • Add credits to remove the 1-hour expiry and deploy permanently.
  • Use npx agentscale account to check your tier and credit balance.
  • When you need to add credits, use the agentspend pay command or the AgentSpend skill.

Commands

Register

npx agentscale register

Generates an API key and saves it to ~/.agentscale/config.json.

Deploy

npx agentscale deploy

Run this from your project directory. Packages the current directory and deploys it.

Options:

  • --name \x3Cname> — Service name (auto-generated if omitted)

List

npx agentscale list

Lists your services and their status.

Account

npx agentscale account

Shows your account tier (free/paid) and credit balance.

To add credits, use the agentspend pay command:

agentspend pay https://api.agentscale.co/add-credits \
  --header "x-api-key:\x3Cyour-api-key>" \
  --body '{"amount_cents": 500}'

Or pay directly with an x402 wallet by calling POST /add-credits with your x-api-key header and amount_cents in the body.

Project Requirements

  • Deploy APIs and web services. Supports Node.js, Python, Go, and more.
  • Your project needs a standard structure to be auto-detected:
    • Node.js: a package.json with a start script.
    • Python: a requirements.txt.
    • Go: a go.mod.
  • Custom domains, build commands, and start commands are not yet supported.

Environment Variables

  • AGENTSCALE_API_URL — Overrides the default API base URL. Warning: this redirects all API calls, including those carrying your API key, to the specified URL.

System Requirements

  • tar must be available on PATH (used to package projects for deploy).

Limits

  • Upload: 100 MB compressed, 500 MB decompressed.
Usage Guidance
This skill appears to do what it says (package your project and upload it to agentscale). Before installing/using it: 1) double-check the API base URL (AGENTSCALE_API_URL) — if you override it you will send your API key and uploads to that host; only point it at trusted endpoints. 2) Be careful what you run deploy from: the tool tars and uploads your current directory (the code excludes many common secret paths, but custom or unexpected secret files could still be included). 3) Note the CLI loads dotenv (.env) into the environment at runtime; don't keep secret credentials in an .env you don't want read by the tool. 4) The API key is stored under ~/.agentscale/config.json with restrictive permissions (0o600). If you need higher assurance, inspect the upstream repository/package (package.json points at a GitHub repo) and verify the API domain (https://api.agentscale.co) is legitimate before giving it access to your code. If you want me to, I can check the referenced GitHub repo or review any network endpoint you’re specifically concerned about.
Capability Analysis
Type: OpenClaw Skill Name: agentscale Version: 0.1.2 The skill is classified as suspicious due to a critical vulnerability related to the `AGENTSCALE_API_URL` environment variable. As documented in `SKILL.md` and implemented in `src/config.ts`, this variable allows overriding the default API endpoint. All API calls, including those transmitting the user's `x-api-key` and the project tarball (from `src/commands/deploy.ts`), would be redirected to this arbitrary, user-defined URL. While the `SKILL.md` includes a warning about this, it presents a significant risk for API key and data exfiltration if an attacker can manipulate this environment variable, even though the code itself does not exhibit direct malicious intent.
Capability Assessment
✓ Purpose & Capability
Name/description (deploy web apps to a public URL) match the implementation: register() obtains an API key, deploy() runs tar to package the current directory and POSTs it to an API, list()/account() call the API. No unrelated credentials, binaries, or install steps are requested.
ℹ Instruction Scope
SKILL.md and code instruct packaging the current working directory and uploading it to the service. This is expected for a deploy tool, but it means arbitrary files in the project may be sent to the remote API. The code includes a reasonable exclusion list for common secrets and config files, and SKILL.md documents tar as required, but users should still ensure no sensitive files are present in the directory when deploying.
✓ Install Mechanism
There is no install spec in the skill manifest (instruction-only). Source includes a normal Node CLI implementation and package metadata; no arbitrary remote download or archive-extract install steps are present in the skill bundle that would write unknown code to disk beyond normal CLI usage.
ℹ Credentials
The skill declares no required env vars, but supports AGENTSCALE_API_URL override (documented in SKILL.md). Code also imports dotenv/config, which will load a .env file into process.env when the CLI runs. These are coherent with a configurable client, but they increase risk: setting AGENTSCALE_API_URL to an attacker-controlled endpoint would send the saved API key and uploads to that endpoint (the SKILL.md warns about this). saveApiKey writes the API key to ~/.agentscale/config.json with 0o600 permissions (appropriate), and the code avoids requiring unrelated credentials.
✓ Persistence & Privilege
always is false and the skill does not request system-wide privileges. The only persistent artifact is ~/.agentscale/config.json which stores the API key with restrictive permissions. The skill does not modify other skills or global agent settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install agentscale
  3. After installation, invoke the skill by name or use /agentscale
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.2
- Added system and environment variable requirements for better deployment support. - Introduced a "System Requirements" section specifying that "tar" must be available on PATH. - Added a new "Environment Variables" section documenting AGENTSCALE_API_URL and its security implications. - Declared "tar" under required_tools for clearer tool prerequisites.
v0.1.1
Initial public release. - Deploy web apps and APIs to a public URL with a single command. - Supports Node.js, Python, Go, and more with auto-detection of standard project structures. - Includes commands to register, deploy, list services, and view account info. - Free and paid tier details with key usage and limits outlined. - Documentation and configuration files added for easy setup.
v0.1.0
Initial release of agentscale – deploy web apps and APIs to a public URL with one command. - Free tier available: no signup needed; deploys expire after 1 hour and limited to 1 service. - Paid tier removes expiry and service limits with credits. - Simple CLI commands: register, deploy, list, and account. - Supports Node.js, Python, and Go projects with standard structures. - Upload size limited to 100 MB compressed or 500 MB decompressed.
Metadata
Slug agentscale
Version 0.1.2
License —
All-time Installs 2
Active Installs 2
Total Versions 3
Frequently Asked Questions

What is AgentScale?

Deploy web apps and APIs to a public URL with a single command. It is an AI Agent Skill for Claude Code / OpenClaw, with 784 downloads so far.

How do I install AgentScale?

Run "/install agentscale" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is AgentScale free?

Yes, AgentScale is completely free (open-source). You can download, install and use it at no cost.

Which platforms does AgentScale support?

AgentScale is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created AgentScale?

It is built and maintained by João Bonchristiano (@jpbonch); the current version is v0.1.2.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments