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 frontier-ai-next/mgarlbot --skill ops_dns_regrugit clone --depth 1 https://github.com/frontier-ai-next/mgarlbotWrote 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/frontier-ai-next/mgarlbot/ops_dns_regru)<a href="https://agentmods.dev/skills/frontier-ai-next/mgarlbot/ops_dns_regru"><img src="https://agentmods.dev/badge/skills/frontier-ai-next/mgarlbot/ops_dns_regru/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/frontier-ai-next/mgarlbot/ops_dns_regru"><img src="https://agentmods.dev/badge/skills/frontier-ai-next/mgarlbot/ops_dns_regru.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 | $0.00036 | $0.00945 |
| Opus 5 | $0.00018 | $0.00473 |
| Sonnet 5 | $0.00007 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
ops_dns_regru scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -X POST "${REGRU_API_BASE_URL}/api/regru2/zone/get_resource_records" \ How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
REG.API 2 — documented calls only
Official docs: REG.API 2.
Zone base URL: ${REGRU_API_BASE_URL}/api/regru2/zone/<function> (default host https://api.reg.ru).
Bot process credentials (exported from settings into os.environ): REGRU_API_USERNAME, REGRU_API_PASSWORD, optional REGRU_DNS_ZONE (apex zone, e.g. example.ru).
Do not print the password or full API responses to the user; log-level summaries with result / error_text only.
Prerequisite
The domain must use REG.RU nameservers (ns1.reg.ru / ns2.reg.ru), otherwise the API returns DOMAIN_IS_NOT_USE_REGRU_NSS.
1) List current records
POST Content-Type: application/x-www-form-urlencoded, fields input_format=json, input_data = one-line JSON string (per docs). Zone examples include username / password inside input_data.
Build JSON with Python (avoids password showing up in ps from inline flags — use env only):
REGRU_ZONE="${REGRU_DNS_ZONE:?set REGRU_DNS_ZONE}"
INPUT_DATA="$(REGRU_ZONE="$REGRU_ZONE" python3 -c '
import json, os
z = os.environ["REGRU_ZONE"]
print(json.dumps({
"username": os.environ["REGRU_API_USERNAME"],
"password": os.environ["REGRU_API_PASSWORD"],
"domains": [{"dname": z}],
"output_content_type": "json",
}))
')"
curl -sS -X POST "${REGRU_API_BASE_URL}/api/regru2/zone/get_resource_records" \
-H "Content-Type: application/x-www-form-urlencoded" \
--data-urlencode "input_format=json" \
--data-urlencode "input_data=${INPUT_DATA}"
2) Add A (IPv4) for a subdomain — zone/add_alias
Parameters (doc §9.2): domains — list of {dname}, shared subdomain label without the zone (www, api, or @ for apex), ipaddr.
Example: subdomain app → IP 203.0.113.10:
REGRU_ZONE="${REGRU_DNS_ZONE:?set REGRU_DNS_ZONE}"
export SUB="${SUBDOMAIN:-app}"
export IP="${TARGET_IPV4:?set TARGET_IPV4}"
INPUT_DATA="$(REGRU_ZONE="$REGRU_ZONE" python3 -c '
import json, os
z, sub, ip = os.environ["REGRU_ZONE"], os.environ["SUB"], os.environ["IP"]
print(json.dumps({
"username": os.environ["REGRU_API_USERNAME"],
"password": os.environ["REGRU_API_PASSWORD"],
"domains": [{"dname": z}],
"subdomain": sub,
"ipaddr": ip,
"output_content_type": "json",
}))
')"
curl -sS -X POST "${REGRU_API_BASE_URL}/api/regru2/zone/add_alias" \
-H "Content-Type: application/x-www-form-urlencoded" \
--data-urlencode "input_format=json" \
--data-urlencode "input_data=${INPUT_DATA}"
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 · 84 lines · 36 tokens per session scan A e7ea78b388c9
ops_dns_regru is a skill published in the GitHub repository frontier-ai-next/mgarlbot (17 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 945 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (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
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
modal-serverless-gpu
Run approved CPU or GPU work through OpenScience computejob on the user's configured Modal account. Use for isolated scientific scripts, dependency provisioning, durable outputs, logs, status, cancellation, and recovery. Never invoke the Modal SDK or CLI directly.
givemeanode-agent-compute
Operate GiveMeANode GPU nodes, batch jobs, storage, and rollout sandboxes through its connected MCP server with bounded spend, durable recovery, and explicit approval for paid or destructive actions.
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.
gateway
Start and manage the Kurtosis gateway for Kubernetes. The gateway forwards local ports to the Kurtosis engine and services running in a k8s cluster. Required when using Kurtosis with Kubernetes. Use when kurtosis engine status shows nothing on k8s or services aren't reachable.