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 automateyournetwork/netclaw --skill bgp-registry-intelgit clone --depth 1 https://github.com/automateyournetwork/netclawWrote 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/automateyournetwork/netclaw/bgp-registry-intel)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/bgp-registry-intel"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/bgp-registry-intel/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/automateyournetwork/netclaw/bgp-registry-intel"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/bgp-registry-intel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00097 | $0.01850 |
| Opus 5 | $0.00048 | $0.00925 |
| Sonnet 5 | $0.00019 | $0.00370 |
| Haiku 4.5 | $0.00010 | $0.00185 |
Grade A, and why
bgp-registry-intel scanned grade A with 0 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BGP & Registry Intelligence
MCP Server
- Server:
bgp-intel-mcp(NetClaw-authored, spec 081 / roadmap R9) - Command:
$BGP_INTEL_MCP_CMD - Transport: stdio
- Credentials: none. Every source is a public unauthenticated API
- Mode: read-only. There is no write path
The one rule that matters most
RPKI
not-foundis NOTinvalid.
Most of the internet has no ROA. Unsigned address space is the overwhelmingly common case, not an
anomaly. If you report not-found as a hijack, a misconfiguration, or a security finding, you will
generate false incidents at scale and the operator will stop trusting you.
| State | Means | Actionable? |
|---|---|---|
valid |
A ROA authorises this origin AS | No — healthy |
invalid + reason: as |
A ROA covers this prefix; a different AS is authorised | Yes — possible hijack |
invalid + reason: length |
Correct AS, but the prefix is more specific than the ROA permits | Yes — usually a local misconfiguration, different fix |
not_found |
No ROA exists. RFC 6811 calls this NotFound | No — the normal case |
The two invalid reasons are different findings. as means someone else is announcing your space;
length usually means you announced a /24 under a /22 ROA. Never collapse them.
validation_unavailable is not not_found. If the validator is unreachable you get the former, and
the RPKI state is genuinely unknown. Do not infer "unsigned" from "could not ask", and do not fall back to
guessing from routing or registry data.
Tools (10, all read-only)
| Tool | Answers |
|---|---|
rpki_validate |
Is this prefix legitimately announced by this AS? Nothing else in NetClaw does this |
registry_lookup |
Who is this IP/prefix/ASN allocated to? |
registry_abuse_contact |
Who do I report abuse to? |
routing_as_overview |
Who holds this ASN; is it announced at all? |
routing_announced_prefixes |
What does this AS announce, and how visible is it? |
peering_network |
Network type, traffic profile, peering policy |
peering_presence |
Which IXPs and facilities? |
atlas_anchors |
Atlas anchors in a country (stable measurement targets) |
atlas_probe_count |
Can this AS be measured from inside? |
resource_report |
Everything about a resource, one call, per-section sourcing |
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 · 134 lines · 97 tokens per session scan A e952496f93b7
bgp-registry-intel is a skill published in the GitHub repository automateyournetwork/netclaw (652 stars, last pushed 4d ago), licensed Apache-2.0. It adds 97 tokens to every session and 1,850 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orchestrator
Load when routing a natural-language omics query to the correct domain skill across spatial / singlecell / genomics / proteomics / metabolomics / bulkrna domains via keyword / LLM / hybrid matching. Skip when the target skill is already known — invoke that skill directly.
lynkr
Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.
langgraph
LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph…
google-tasks-tool
Google Tasks integration for listing task lists and tasks and creating or updating tasks via OAuth2. Use when: fetching TODO lists, adding tasks, marking items complete, or switching task lists.
notion-tool
Notion integration tool for searching, reading, creating, and updating pages and databases via the API. Use when: editing Notion pages, adding database rows, or searching a workspace.
gmail-tool
Gmail integration tool for unread checks, reading bodies, and drafts via OAuth2 Gmail API access. Use when: reading inbox mail, fetching message bodies, writing drafts, or searching labeled mail.