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/craftos-dev/craftbot/api-gatewaynpx skills add CraftOS-dev/CraftBot --skill api-gatewaygit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWhat 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 | $0.00108 | $0.07794 |
| Opus 5 | $0.00054 | $0.03897 |
| Sonnet 5 | $0.00022 | $0.01559 |
| Haiku 4.5 | $0.00011 | $0.00779 |
Grade A, and why
api-gateway scanned grade A with 2 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.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
response = requests.post( "https://gateway.maton.ai/slack/api/chat.postMessage", Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import urllib.request, os, json How it starts
The opening of the file, as written. The whole thing — 614 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Gateway
Passthrough proxy for direct access to third-party APIs using managed OAuth connections, provided by Maton. The API gateway lets you call native API endpoints directly.
Quick Start
# Native Slack API call
python <<'EOF'
import urllib.request, os, json
data = json.dumps({'channel': 'C0123456', 'text': 'Hello from gateway!'}).encode()
req = urllib.request.Request('https://gateway.maton.ai/slack/api/chat.postMessage', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF
Base URL
https://gateway.maton.ai/{app}/{native-api-path}
Replace {app} with the service name and {native-api-path} with the actual API endpoint path.
IMPORTANT: The URL path MUST start with the connection's app name (eg. /google-mail/...). This prefix tells the gateway which app connection to use. For example, the native Gmail API path starts with gmail/v1/, so full paths look like /google-mail/gmail/v1/users/me/messages.
Authentication
All requests require the Maton API key in the Authorization header:
Authorization: Bearer $MATON_API_KEY
The API gateway automatically injects the appropriate OAuth token for the target service.
Environment Variable: You can set your API key as the MATON_API_KEY environment variable:
export MATON_API_KEY="YOUR_API_KEY"
Getting Your API Key
- Sign in or create an account at maton.ai
- Go to maton.ai/settings
- Click the copy button on the right side of API Key section to copy it
Connection Management
Connection management uses a separate base URL: https://ctrl.maton.ai
List Connections
python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections?app=slack&status=ACTIVE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- _meta.json 131 B
- .clawhub/origin.json 144 B
- LICENSE.txt 1.0 KB
- references/active-campaign.md 3.2 KB
- references/acuity-scheduling.md 3.0 KB
- references/airtable.md 3.0 KB
- references/apollo.md 4.0 KB
- references/asana.md 2.7 KB
- references/attio.md 4.8 KB
- references/basecamp.md 2.8 KB
- references/beehiiv.md 2.6 KB
- references/box.md 2.8 KB
- references/brevo.md 3.7 KB
- references/cal-com.md 3.4 KB
- references/calendly.md 2.6 KB
- references/callrail.md 3.1 KB
- references/chargebee.md 5.5 KB
- references/clickfunnels.md 5.3 KB
- references/clicksend.md 2.3 KB
- references/clickup.md 2.9 KB
- references/clio.md 6.1 KB
- references/clockify.md 3.7 KB
- references/coda.md 3.6 KB
- references/cognito-forms.md 2.4 KB
- references/companycam.md 3.6 KB
- references/confluence.md 4.6 KB
- references/constant-contact.md 2.5 KB
- references/dropbox-business.md 12 KB
- references/dropbox.md 3.1 KB
- references/elevenlabs.md 1.8 KB
- references/eventbrite.md 4.2 KB
- references/fathom.md 1.9 KB
- references/firebase.md 3.1 KB
- references/fireflies.md 1.8 KB
- references/getresponse.md 2.8 KB
- references/github.md 2.5 KB
- references/google-ads.md 3.9 KB
- references/google-analytics-admin.md 5.7 KB
- references/google-analytics-data.md 4.2 KB
- references/google-bigquery.md 3.9 KB
- references/google-calendar.md 3.7 KB
- references/google-classroom.md 2.6 KB
- references/google-contacts.md 3.3 KB
- references/google-docs.md 2.9 KB
- references/google-drive.md 5.1 KB
- references/google-forms.md 4.1 KB
- references/google-mail.md 3.6 KB
- references/google-meet.md 2.7 KB
- references/google-merchant.md 5.0 KB
- references/google-play.md 3.8 KB
- references/google-search-console.md 3.8 KB
- references/google-sheets.md 6.0 KB
- references/google-slides.md 4.5 KB
- references/google-tasks.md 3.0 KB
- references/google-workspace-admin.md 4.6 KB
- references/granola.md 1.8 KB
- references/gumroad.md 3.3 KB
- references/hubspot.md 9.8 KB
- references/instantly.md 3.0 KB
- references/jira.md 4.5 KB
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 · 614 lines · 108 tokens per session scan A 5b3b11005b54
api-gateway is a skill published in the GitHub repository CraftOS-dev/CraftBot (376 stars, last pushed 2d ago), licensed MIT. It adds 108 tokens to every session and 7,794 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
turix-mac
Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API.
browser-control
Control web pages in an existing Chromium remote-debugging session with deterministic sagui commands or the browser-only AI Agent. Use when Claude Code needs to inspect tabs, observe semantic elements, navigate, click, type, send keys, scroll, or complete a browser goal through CDP without controlling native macOS UI…
agent-smoke-test
Run manual development checks for SwiftAutoGUI AI Agent actions through the local sagui CLI. Use when Claude or Codex needs to test app-control or Accessibility BasicAction generation on macOS.
macos-control
Control macOS GUI applications via mouse automation, keyboard input, screenshots, image recognition, and AppleScript execution. Use when you need to interact with macOS app UIs, take screenshots, click buttons, type text, scroll, drag, or locate images on screen.
open-record-replay
Record a user-demonstrated macOS workflow with the Open Record/Replay CLI, inspect the captured event stream, prepare a skill evidence package, and hand it to the host agent's native skill creator. Use when the user asks the agent to watch them perform a task, record a workflow, or create/refine a reusable Computer…
artifact-storage-policy
管理 Codex 交付物的專案識別、Google Drive/GitHub 路由、檔名、儲存位置與回讀驗證;凡工作報告、外部保存、交付成果或新 repository 選擇涉及遠端儲存時使用。.