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 infrahub-sotgit 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/infrahub-sot)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/infrahub-sot"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/infrahub-sot/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/infrahub-sot"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/infrahub-sot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 158 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- low MCP Rug Pull · line 15 pip install without ==version installs the latest release, which could include malicious changes.Fix: Pin the version: pip install package==1.2.3
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 | $0.00071 | $0.03875 |
| Opus 5 | $0.00036 | $0.01937 |
| Sonnet 5 | $0.00014 | $0.00775 |
| Haiku 4.5 | $0.00007 | $0.00387 |
Grade A, and why
infrahub-sot 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 8d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infrahub Source of Truth
MCP Server
- Repository: opsmill/infrahub-mcp
- Version: 1.1.7+ (reworked — first stable release + production hardening)
- Distribution: PyPI (
pip install infrahub-mcp), Docker (registry.opsmill.io/opsmill/infrahub-mcp), or from source - Entry point:
infrahub-mcpconsole script - Transport:
stdio(default) orstreamable-http(remote clients / auth modes) - Requires:
INFRAHUB_ADDRESS+ (INFRAHUB_API_TOKENorINFRAHUB_USERNAME+INFRAHUB_PASSWORD) - Python: 3.13+
- Dependencies:
fastmcp>=3.2.0,infrahub-sdk>=1.20.0 - Docs: docs.infrahub.app/mcp (per-client setup, auth, configuration)
What changed in the rework: the server moved to a modular
src/infrahub_mcp/layout on FastMCP 3.x, added a branch-isolated write model (writes never touch the default branch), exposes MCP resources and prompts in addition to tools, serializes schema output with TOON internally to cut tokens, and ships as a PyPI package + Docker image with optional auth, rate limiting, caching, and OpenTelemetry/Prometheus observability. The old read-only tool surface (get_node_filters,get_related_nodes,get_schema_mapping,get_schemas,get_graphql_schema,get_branches,branch_create) has been replaced — see the table below.
How Infrahub Differs
Infrahub is not just another IPAM/DCIM tool. Key differentiators:
- Schema-driven — define your own infrastructure models (not just built-in IPAM/DCIM). Devices, circuits, IP addresses, services, cloud resources — any infrastructure object can be modeled.
- Versioned branches — Git-like branching for infrastructure data. Changes are made on a branch, reviewed as a diff, and merged when approved. No more "who changed this in production?"
- GraphQL-native — full GraphQL API for flexible queries, not just REST. Query exactly the fields you need, traverse relationships in a single request.
- Relationship-first — rich relationship model between objects with relationship-level filters and traversal.
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.
- 8d ago First seen · 222 lines · 71 tokens per session scan A af6846a47d7b
infrahub-sot is a skill published in the GitHub repository automateyournetwork/netclaw (657 stars, last pushed 6d ago), licensed Apache-2.0. It adds 71 tokens to every session and 3,875 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
payload
Use when working with Payload projects (payload.config.ts, collections, fields, hooks, access control, Payload API). Use when debugging validation errors, security issues, relationship queries, transactions, or hook behavior.
graphjin-eval
Create, extend, run, baseline, and diagnose GraphJin agent evaluations through the graphjin eval CLI.
graphjin-env
Use when setting up a training or evaluation loop against a GraphJin agent environment — running the container, reading /health, driving episodes hosted or step-by-step or with your own agent over MCP, splitting train from eval, exporting trajectories, and deciding whether two rewards can be compared.
nornicdb-knowledge-policies
Author and use NornicDB knowledge-layer policies (decay profiles, parameter bundles, promotion profiles, promotion policies) from Cypher. Use when writing CREATE/ALTER/DROP/SHOW DECAY PROFILE / PROMOTION PROFILE / PROMOTION POLICY, calling nornicdb.knowledgepolicy. procedures, or reading entity scores via decayScore()…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
nornicdb-rag-procedures
Build RAG pipelines in NornicDB using Cypher procedures — db.retrieve (hybrid vector + BM25 + RRF), db.rretrieve (retrieve + rerank), db.rerank (cross-encoder), db.infer (LLM call). Use when assembling end-to-end retrieval, reranking, or RAG flows from Cypher rather than hand-rolling vector and full-text procedures…