Hatcher Host AI Agents Deployment

Deploy and control AI agents on Hatcher (hatcher.host) — managed hosting platform for OpenClaw, Hermes, ElizaOS, and Milady agents.

Security Scan

The skill's instructions and files match its stated purpose (deploying and controlling agents on hatcher.host); it is instruction-only (no install), but it will create and store API keys and integration tokens at runtime so users should be deliberate about what credentials they provide.

Purpose & Capability

Name/description (deploy/control agents on Hatcher) align with the runtime instructions and satellite files: register an account, create an API key (HATCHER_KEY), create/start/stop agents, configure integrations and payments. There are no unrelated credential or binary requests in the metadata or files.

Instruction Scope

SKILL.md explicitly directs the agent to register a user account (needs the human's email and one-time verification click), create an API key, store the JWT/HATCHER_KEY, and manage agents and integrations. All of this is in-scope for a hosting/deployment skill. Note: the examples include a literal example password and instruct storing keys in env/config — users should not reuse example secrets and should understand the agent will handle their credentials.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest disk/execution risk. The repository-like satellite markdowns are fetched as documentation only.

Credentials

Registry metadata lists no required env vars, but the instructions require creating and storing a HATCHER_KEY (API key) and temporarily using a JWT. The skill may also instruct storing third-party integration tokens (Telegram, Discord, Slack, Twitter, WhatsApp) or BYOK LLM keys in an agent's config. These environment/secret needs are proportional to the feature set, but the metadata omission (no declared required env vars) is an inconsistency and users should be aware of the sensitive secrets the flow requests.

Persistence & Privilege

Skill does not request always:true and does not modify other skills or global agent configuration. It instructs creating API keys and writing them to the agent/account (normal for this purpose). Note that with the created HATCHER_KEY an agent could create resources (agents, subscriptions) and perform actions within that account's allowances — users should treat the key as sensitive and limit permissions/credits.

Assessment

This skill appears to be what it says: documentation and curl recipes to register at hatcher.host, create an API key (HATCHER_KEY), and manage hosted agents and integrations. Before installing or running it: 1) Verify you trust hatcher.host (homepage and contact info) before creating accounts or sharing tokens. 2) Do not copy the example literal password; choose a unique strong password. 3) Understand that the flow creates/stores an API key (HATCHER_KEY) and may ask you to provide third-party integration tokens (Telegram, Discord, Slack, Twitter, WhatsApp) or LLM BYOK keys — those are sensitive; only provide tokens you are willing to have used by the agent and stored encrypted by the platform. 4) Limit account funds/credits and prefer minimal-scope keys; revoke or rotate the API key if you stop using the skill. 5) If you want the agent to not act autonomously with your HATCHER_KEY (e.g., avoid accidental purchases or always-on agents), do not grant it payment credentials or give it long-lived credits without supervision. The skill metadata should have declared required env vars (it does not) — that's a minor inconsistency but not a functional issue.

Hatcher Skill

Hatcher is a managed hosting platform for AI agents — "Heroku for AI agents." You can register an account, pick from 4 frameworks (OpenClaw, Hermes, ElizaOS, Milady) and 199 pre-built templates, configure integrations (Telegram, Discord, Twitter, WhatsApp, Slack), pay with credits / Stripe card / SOL / USDC / HATCHER, and have a running agent serving traffic in under 10 minutes.

This file is the index. Fetch the satellite files below as you need them — don't dump all 5 into your context.

Satellite files — fetch as needed

Use the absolute URLs — relative paths resolve to hatcher.host/<file>.md which serves the web app, not the markdown.

File	When to fetch
auth.md	Registering, email verification polling, creating API keys
agents.md	Picking a framework, browsing templates, creating and controlling agents, installing skills/plugins
pricing.md	Choosing a tier, buying addons, paying (credits / Stripe / SOL / USDC / HATCHER), upgrading
integrations.md	Wiring a deployed agent to Telegram / Discord / Twitter / WhatsApp / Slack

Canonical URLs (both serve identical content):

• https://hatcher.host/skill.md (+ /skill/<name>.md for satellites)
• https://raw.githubusercontent.com/HatcherLabs/hatcher-skill/main/skill.md (+ /main/<name>.md for satellites)

User-agent convention

When calling Hatcher API endpoints, include this header so platform analytics can track agent cohorts:

Hatcher-Agent-Name: <your-agent-name>/<version>

Example: Hatcher-Agent-Name: claude-code/0.4.2. The value is free-form telemetry and is never used for authorization.

Hello world — 5 curl commands

This flow gets you from zero to a running free-tier agent you can chat with. Human must click one email-verify link during step 2.

1. Ask the human for their email

You need their email to register the account. Explain: "I'm going to register a Hatcher account in your name. You'll get a verification email — just click the link and come back." Store the email.

2. Register (substitute values)

curl -sS -X POST https://api.hatcher.host/auth/register \
  -H "Content-Type: application/json" \
  -H "Hatcher-Agent-Name: claude-code/0.4.2" \
  -d '{
    "email": "USER_EMAIL",
    "username": "UNIQUE_USERNAME",
    "password": "Str0ngP@ssw0rd123",
    "agentName": "claude-code"
  }'

Response:

{ "success": true, "data": { "token": "eyJ...", "refreshToken": "...", "expiresIn": "7d", "user": { "id": "...", "email": "..." } } }

Save the JWT token — you'll need it for step 4.

Tell the human: "I sent the verification email. Click the link; I'll wait."

3. Poll for verification

while true; do
  RESULT=$(curl -sS "https://api.hatcher.host/auth/verify-status?email=USER_EMAIL")
  if echo "$RESULT" | grep -q '"verified":true'; then
    echo "Verified."
    break
  fi
  sleep 5
done

Respects rate limit (1 req / 5s per IP).

4. Create an API key (so you don't need to manage JWT refresh)

curl -sS -X POST https://api.hatcher.host/auth/api-keys \
  -H "Authorization: Bearer JWT_FROM_STEP_2" \
  -H "Content-Type: application/json" \
  -d '{ "label": "agent-default", "createdBy": "agent" }'

Response contains { "data": { "key": "hk_..." } } — shown exactly once. Store in env as HATCHER_KEY.

5. Create a free-tier agent and chat

# Pick from 199 templates (public, no auth):
curl -sS "https://api.hatcher.host/api/templates?limit=5" | jq '.templates[].id'

# Create from a template (both `framework` and `template` are required fields):
curl -sS -X POST https://api.hatcher.host/api/v1/agents \
  -H "Authorization: Bearer $HATCHER_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "framework": "openclaw", "template": "customer-support", "name": "My First Agent" }'

# Start and chat:
AGENT_ID=...  # from create response
curl -sS -X POST "https://api.hatcher.host/api/v1/agents/$AGENT_ID/start" \
  -H "Authorization: Bearer $HATCHER_KEY"

curl -sS -X POST "https://api.hatcher.host/api/v1/agents/$AGENT_ID/chat" \
  -H "Authorization: Bearer $HATCHER_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "message": "Hello, introduce yourself." }'

That's it. For anything beyond this — picking the right framework, wiring Telegram, buying credits, upgrading tier — fetch the relevant satellite file above.

OpenAPI

Full OpenAPI 3.0 spec: https://api.hatcher.host/openapi.json. Use this for programmatic introspection of every endpoint.

Support

Human support: [e-mail]. Community Discord: linked from hatcher.host.