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 team-telnyx/ai --skill telnyx-email-curlgit clone --depth 1 https://github.com/team-telnyx/aiWrote 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/team-telnyx/ai/telnyx-email-curl)<a href="https://agentmods.dev/skills/team-telnyx/ai/telnyx-email-curl"><img src="https://agentmods.dev/badge/skills/team-telnyx/ai/telnyx-email-curl/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/team-telnyx/ai/telnyx-email-curl"><img src="https://agentmods.dev/badge/skills/team-telnyx/ai/telnyx-email-curl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00038 | $0.06241 |
| Opus 5 | $0.00019 | $0.03121 |
| Sonnet 5 | $0.00008 | $0.01248 |
| Haiku 4.5 | $0.00004 | $0.00624 |
Grade D, and why
telnyx-email-curl scanned grade D with 3 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 11d 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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
- **Scheduling is fail-open:** `scheduled_at` is the preferred field. If it is invalid or in the past, the API silently sends immediately. Validate the timestamp before sending and confirm the response status is `schedul Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
# Debian/Ubuntu: sudo apt-get install jq Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
name: telnyx-email-curl How it starts
The opening of the file, as written. The whole thing — 516 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Telnyx Email - curl
Installation
# curl is pre-installed on macOS, Linux, and Windows 10+
# jq is required for examples that capture IDs from responses:
# macOS: brew install jq
# Debian/Ubuntu: sudo apt-get install jq
Setup
export TELNYX_API_KEY="YOUR_API_KEY_HERE"
All examples below use $TELNYX_API_KEY for authentication.
Error Handling
All API calls can fail with network errors, rate limits (429), validation errors (400 or 422), or authentication errors (401). Preserve the response body so the Telnyx error code and detail remain available:
curl --fail-with-body \
-X POST \
-H "Authorization: Bearer $TELNYX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"from": {"email": "[email protected]", "name": "Example"},
"to": ["[email protected]"],
"subject": "Hello from Telnyx",
"text_body": "Your notification is ready."
}' \
"https://api.telnyx.com/v2/email_messages"
Common errors: 401 invalid credentials, 403 sender-domain eligibility or
verification failure, 404 resource not found, 413 body larger than
8,000,000 bytes, and 422 semantic validation or template-rendering failure.
A 429 is not necessarily a transient throughput limit: it can indicate a
reputation suspension or a daily policy limit. Inspect .errors[0].code and
.errors[0].detail before deciding whether to retry. See the full taxonomy in
references/api-details.md.
Important Notes
- Base URL: All paths in this skill are relative to
https://api.telnyx.com/v2. - Sender domain: The domain in
from.emailmust be authorized and ready for sending. A successful create response means accepted, queued, scheduled, or sandbox-created—not delivered. - Address input:
from,reply_to, and eachto/cc/bccitem accept either a string address or{ "email": "...", "name": "..." }. Recipients must be unique acrossto,cc, andbccafter case-insensitive normalization. - Body or template:
subjectis required unlesstemplate_idis supplied. Withtemplate_id, do not also sendsubject,html_body, ortext_body; pass Liquid values intemplate_variables. - Pagination: Core Email endpoints use
page_size(default 25, maximum 100) and the opaquepage_cursorreturned in.meta.page_cursor. Do not translate these names topage[size]orpage[cursor]. - Message listing:
GET /email_messagescurrently implements cursor pagination only; no message filters are exposed. Event and recipient list endpoints have their own filters.
What ships with it
1 file 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.
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.
- 11d ago First seen · 516 lines · 38 tokens per session scan D b658e1f935e2
telnyx-email-curl is a skill published in the GitHub repository team-telnyx/ai (213 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 6,241 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (tells the agent to send conversation or user data out, asks for root, 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
shopify-cli
Use when scaffolding a new Shopify app, running Shopify CLI commands (shopify app dev/deploy/generate), configuring shopify.app.toml, generating app extensions (admin/checkout/theme/function), debugging tunnels or auth issues, or working with the official Remix/Node/PHP/Ruby app templates. Trigger on 'shopify app'…
shopify-mcp
Use this skill for shopify mcp. Triggers include: 'shopify mcp', 'shopify dev mcp', 'storefront mcp', 'merchant-facing mcp', 'well-known mcp', 'shopify mcp configuration', 'custom mcp shopify', 'agentic commerce', 'shopify agent', 'claude code shopify integration', 'mcp.json', 'shopify mcp setup'.
admin-graphql
Build Shopify Admin GraphQL queries and mutations for products, orders, customers, inventory, and more. Covers cost-aware rate limiting, cursor pagination, bulk operations, global resource identifiers, and version-safe API usage.
storefront-api
Build customer-facing storefront applications with Shopify Storefront API. Access product catalogs, collections, checkout flows, cart management, and customer accounts using public/private tokens. Includes GraphQL queries, Market directives, Customer Account API, and TypeScript examples. Triggers include: 'storefront…
webhooks
Webhook delivery methods, verification, retry behavior, payload handling, and implementation patterns for Shopify events. Triggers include: 'set up webhook', 'verify webhook signature', 'webhook delivery', 'HMAC verification', 'webhook retry', 'event subscription', 'webhook payload', 'AWS EventBridge Shopify', 'Google…
admin-rest
Use the legacy REST Admin API only when maintaining an existing integration. Covers common resources, the 40-request bucket with a 2-request-per-second standard restore rate, and migration to GraphQL. New public apps must use the GraphQL Admin API.