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 5.5 | $0.00014 | $0.00378 |
| Sonnet 5.5 | $0.00007 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
ops_dns_regru scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -X POST "${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.
- 2mo 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 3mo ago), licensed MIT. It adds 36 tokens to every session and 945 once invoked, about $0.0001 per session on Opus 5.5. 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.
ops_dns_regru compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ops_dns_regrufrontier-ai-next/mgarlbot | Skill | 17 | 3mo ago | MIT | A | 36 | Claude Code, Codex |
| architecture-diagrammateaix/mateclaw | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| modal-serverless-gpusynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 54 | Claude Code, Codex |
| tianji-workermsgbyte/tianji | Skill | 3.1k | 2d ago | Apache-2.0 | A | 38 | Claude Code, Codex |
| givemeanode-agent-computesynthetic-sciences/openscience | Skill | 4.3k | 2d ago | Apache-2.0 | A | 46 | Claude Code, Codex |
| ecspressokayac/ecspresso | Skill | 1.1k | yesterday | MIT | A | 17 | Claude Code |
| cloudflare-deployHaohao-end/openagent | Skill | 748 | yesterday | MIT | A | 43 | Codex |